{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/load-image","entry":"load_image","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":273,"n_papers_ran":152,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":185,"n_samples_ran":61,"n_samples_fingerprinted":2,"n_places":300,"n_places_pointer_only":88,"by_status":{"ran_honours":13,"ran_violates":1,"ran_draft_wrong":2,"ran_fixture":1,"ran":44,"unverified":124},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.15530","paper":"/paper/arxiv-2609-15530","title":"Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"Kirscher/MedReason2026","path":"docker/medreason/medreason_docker/image_utils.py","file_url":"https://github.com/Kirscher/MedReason2026/blob/HEAD/docker/medreason/medreason_docker/image_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"afde8459b77c7f89","mcp_get_code":{"code_sha256":"afde8459b77c7f89"}},{"arxiv_id":"2609.00231","paper":"/paper/arxiv-2609-00231","title":"Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"zxp555/ACFT_MM26","path":"ACFT/predict.py","file_url":"https://github.com/zxp555/ACFT_MM26/blob/HEAD/ACFT/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2608.31107","paper":"/paper/arxiv-2608-31107","title":"VeriCam: A Verification Baseline for the Classification of Unknown Data","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"lmlwojcik/VeriCam","path":"dataset.py","file_url":"https://github.com/lmlwojcik/VeriCam/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"48083a980ae78bff","mcp_get_code":{"code_sha256":"48083a980ae78bff"}},{"arxiv_id":"2608.30342","paper":"/paper/arxiv-2608-30342","title":"CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"jirongli/CapFrame","path":"GroundedSAM/utils.py","file_url":"https://github.com/jirongli/CapFrame/blob/HEAD/GroundedSAM/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b56228a2996fc54d","mcp_get_code":{"code_sha256":"b56228a2996fc54d"}},{"arxiv_id":"2608.23799","paper":"/paper/arxiv-2608-23799","title":"Restoring Without Forgetting: Continual Learning Across Image Degradations","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"AlifAshrafee/Restoring-Without-Forgetting","path":"generate_degradation_domains.py","file_url":"https://github.com/AlifAshrafee/Restoring-Without-Forgetting/blob/HEAD/generate_degradation_domains.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f7f4aca3a2748f50","mcp_get_code":{"code_sha256":"f7f4aca3a2748f50"}},{"arxiv_id":"2608.23473","paper":"/paper/arxiv-2608-23473","title":"METACASTER: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"D2I-Group/metacaster","path":"generation/core/image.py","file_url":"https://github.com/D2I-Group/metacaster/blob/HEAD/generation/core/image.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b97d9d7f7ba478a2","mcp_get_code":{"code_sha256":"b97d9d7f7ba478a2"}},{"arxiv_id":"2608.04496","paper":"/paper/arxiv-2608-04496","title":"DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Zhong-Chenchen/DIVE","path":"predict.py","file_url":"https://github.com/Zhong-Chenchen/DIVE/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2607.15299","paper":"/paper/arxiv-2607-15299","title":"MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"opendatalab/MLLM-DataEngine","path":"LLaVA/predict.py","file_url":"https://github.com/opendatalab/MLLM-DataEngine/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2607.10783","paper":"/paper/arxiv-2607-10783","title":"Toward Efficient Weakly Supervised Semantic Segmentation Using Only Low-Magnification Histopathological Images","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Dung-Dx/LowMagWSS","path":"dataset/similarity.py","file_url":"https://github.com/Dung-Dx/LowMagWSS/blob/HEAD/dataset/similarity.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39b622b983cc9988","mcp_get_code":{"code_sha256":"39b622b983cc9988"}},{"arxiv_id":"2606.31704","paper":"/paper/arxiv-2606-31704","title":"WIDER-FAIR: An Annotated Version of the WIDER-FACE Dataset for Fairness Evaluation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"bronval/Wider-Fair-Dataset","path":"utility.py","file_url":"https://github.com/bronval/Wider-Fair-Dataset/blob/HEAD/utility.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"794cae0f6e224cfd","mcp_get_code":{"code_sha256":"794cae0f6e224cfd"}},{"arxiv_id":"2606.29712","paper":"/paper/arxiv-2606-29712","title":"Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Miraclecsc/Discrete-Latent-Reasoning","path":"deepseek_codebook/hf_code/modeling_deepseekocr2.py","file_url":"https://github.com/Miraclecsc/Discrete-Latent-Reasoning/blob/HEAD/deepseek_codebook/hf_code/modeling_deepseekocr2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"423c3753d415a8e4","mcp_get_code":{"code_sha256":"423c3753d415a8e4"}},{"arxiv_id":"2606.11854","paper":"/paper/arxiv-2606-11854","title":"Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jinymusim/ART","path":"src/reasoning_with_art/modalities/image.py","file_url":"https://github.com/jinymusim/ART/blob/HEAD/src/reasoning_with_art/modalities/image.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d20c26a8c4fd692e","mcp_get_code":{"code_sha256":"d20c26a8c4fd692e"}},{"arxiv_id":"2606.04205","paper":"/paper/arxiv-2606-04205","title":"DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"sadjadeb/DetectZoo","path":"detectzoo/utils/io.py","file_url":"https://github.com/sadjadeb/DetectZoo/blob/HEAD/detectzoo/utils/io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c709b6283fcf51d","mcp_get_code":{"code_sha256":"9c709b6283fcf51d"}},{"arxiv_id":"2606.01340","paper":"/paper/arxiv-2606-01340","title":"Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"vitsch/jbdt","path":"benchmark.py","file_url":"https://github.com/vitsch/jbdt/blob/HEAD/benchmark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5056279c0594a577","mcp_get_code":{"code_sha256":"5056279c0594a577"}},{"arxiv_id":"2605.20735","paper":"/paper/arxiv-2605-20735","title":"Lowering the Barrier to IREX Participation: Open-Source Algorithms, Toolkit, and Benchmarking for Iris Recognition","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CVRL/PBM","path":"pipeline_from_file.py","file_url":"https://github.com/CVRL/PBM/blob/HEAD/pipeline_from_file.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"ca8626ab1e67ccbc","mcp_get_code":{"code_sha256":"ca8626ab1e67ccbc"}},{"arxiv_id":"2604.28123","paper":"/paper/arxiv-2604-28123","title":"Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"XIAO4579/PRISM","path":"moe/dense_model/train_dense_vl_warmup.py","file_url":"https://github.com/XIAO4579/PRISM/blob/HEAD/moe/dense_model/train_dense_vl_warmup.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c6e48cbf2dfb014e","mcp_get_code":{"code_sha256":"c6e48cbf2dfb014e"}},{"arxiv_id":"2604.13731","paper":"/paper/arxiv-2604-13731","title":"Doc-V * : Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"SeerRay-Lab/Doc-V","path":"preprocess/utils.py","file_url":"https://github.com/SeerRay-Lab/Doc-V/blob/HEAD/preprocess/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a27b1f74c7ce9098","mcp_get_code":{"code_sha256":"a27b1f74c7ce9098"}},{"arxiv_id":"2601.23184","paper":"/paper/arxiv-2601-23184","title":"ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"FanmengWang/ReGuLaR","path":"models/modeling_deepseekocr.py","file_url":"https://github.com/FanmengWang/ReGuLaR/blob/HEAD/models/modeling_deepseekocr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"423c3753d415a8e4","mcp_get_code":{"code_sha256":"423c3753d415a8e4"}},{"arxiv_id":"2601.15260","paper":"/paper/arxiv-2601-15260","title":"DrivIng: A Large-Scale Multimodal Driving Dataset with Full Digital Twin Integration","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"cvims/DrivIng","path":"dataset_scripts/driving_dataset_scripts/utils/camera.py","file_url":"https://github.com/cvims/DrivIng/blob/HEAD/dataset_scripts/driving_dataset_scripts/utils/camera.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e70a3cdabf7d1aa","mcp_get_code":{"code_sha256":"3e70a3cdabf7d1aa"}},{"arxiv_id":"2601.02443","paper":"/paper/arxiv-2601-02443","title":"Evaluating the Diagnostic Classification Ability of Multimodal Large Language Models: Insights from the Osteoarthritis Initiative","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"wanglihx/LLaVA-OA","path":"3-clip/clipeval.py","file_url":"https://github.com/wanglihx/LLaVA-OA/blob/HEAD/3-clip/clipeval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0278560e77c337d0","mcp_get_code":{"code_sha256":"0278560e77c337d0"}},{"arxiv_id":"2510.17847","paper":"/paper/arxiv-2510-17847","title":"COIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"SuDIS-ZJU/CoIDO","path":"LLaVA/predict.py","file_url":"https://github.com/SuDIS-ZJU/CoIDO/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2508.14015","paper":"/paper/arxiv-2508-14015","title":"Backdooring Self-Supervised Contrastive Learning by Noisy Alignment","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"jsrdcht/Noisy-Alignment","path":"utils.py","file_url":"https://github.com/jsrdcht/Noisy-Alignment/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c980c2e1f3ce7934","mcp_get_code":{"code_sha256":"c980c2e1f3ce7934"}},{"arxiv_id":"2508.04453","paper":"/paper/arxiv-2508-04453","title":"Boosting Visual Knowledge-Intensive Training for LVLMs Through Causality-Driven Visual Object Completion","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"XMUDeepLIT/CVC","path":"cvc/data_preparation/2-1_detect_bbox.py","file_url":"https://github.com/XMUDeepLIT/CVC/blob/HEAD/cvc/data_preparation/2-1_detect_bbox.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"66fb37b2a799a88f","mcp_get_code":{"code_sha256":"66fb37b2a799a88f"}},{"arxiv_id":"2507.17539","paper":null,"title":"arXiv:2507.17539","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"MeteorElf/FundusExpert","path":"src/quick_start.py","file_url":"https://github.com/MeteorElf/FundusExpert/blob/HEAD/src/quick_start.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c437f8b86ada6dd7","mcp_get_code":{"code_sha256":"c437f8b86ada6dd7"}},{"arxiv_id":"2507.15504","paper":null,"title":"arXiv:2507.15504","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"PKU-YuanGroup/Video-LLaVA","path":"videollava/eval/run_llava.py","file_url":"https://github.com/PKU-YuanGroup/Video-LLaVA/blob/HEAD/videollava/eval/run_llava.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2507.12455","paper":"/paper/mitigating-object-hallucinations-via-sentence","title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","date":"2025-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pspdada/SENTINEL","path":"llava/utils.py","file_url":"https://github.com/pspdada/SENTINEL/blob/HEAD/llava/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad5386da0ca6f185","mcp_get_code":{"code_sha256":"ad5386da0ca6f185"}},{"arxiv_id":"2507.06908","paper":"/paper/mind-a-multi-agent-framework-for-zero-shot","title":"MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection","date":"2025-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"destroy-lonely/MIND","path":"utils/run_llava.py","file_url":"https://github.com/destroy-lonely/MIND/blob/HEAD/utils/run_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c3f598653081f0e8","mcp_get_code":{"code_sha256":"c3f598653081f0e8"}},{"arxiv_id":"2507.04976","paper":null,"title":"arXiv:2507.04976","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"EsYoon7/UVQA","path":"llava/mm_utils.py","file_url":"https://github.com/EsYoon7/UVQA/blob/HEAD/llava/mm_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"423add5cb47d99b3","mcp_get_code":{"code_sha256":"423add5cb47d99b3"}},{"arxiv_id":"2506.18434","paper":null,"title":"arXiv:2506.18434","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"fruffini/PEFT_Prognosis","path":"src/utils/utils_datasets.py","file_url":"https://github.com/fruffini/PEFT_Prognosis/blob/HEAD/src/utils/utils_datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d82a0e80636120dc","mcp_get_code":{"code_sha256":"d82a0e80636120dc"}},{"arxiv_id":"2505.24787","paper":"/paper/draw-all-your-imagine-a-holistic-benchmark","title":"Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yczhou001/longbench-t2i","path":"utils/evaluator.py","file_url":"https://github.com/yczhou001/longbench-t2i/blob/HEAD/utils/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ff2516a7846c307","mcp_get_code":{"code_sha256":"8ff2516a7846c307"}},{"arxiv_id":"2505.20753","paper":"/paper/understand-think-and-answer-advancing-visual","title":"Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models","date":"2025-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jefferyzhan/griffon","path":"griffon/eval/model_vqa_qbench.py","file_url":"https://github.com/jefferyzhan/griffon/blob/HEAD/griffon/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2505.19474","paper":"/paper/causal-llava-causal-disentanglement-for","title":"Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ignisavium/causal-llava","path":"confounders/get_projector_confounders.py","file_url":"https://github.com/ignisavium/causal-llava/blob/HEAD/confounders/get_projector_confounders.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa077d1ca4abcd21","mcp_get_code":{"code_sha256":"aa077d1ca4abcd21"}},{"arxiv_id":"2505.19235","paper":"/paper/corematching-a-co-adaptive-sparse-inference","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangqinsi1/2025-ICML-CoreMatching","path":"predict.py","file_url":"https://github.com/wangqinsi1/2025-ICML-CoreMatching/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2505.19235","paper":"/paper/corematching-a-co-adaptive-sparse-inference","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangqinsi1/2025-ICML-CoreMatching","path":"inference.py","file_url":"https://github.com/wangqinsi1/2025-ICML-CoreMatching/blob/HEAD/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"522afabbcdf0f218","mcp_get_code":{"code_sha256":"522afabbcdf0f218"}},{"arxiv_id":"2505.18514","paper":"/paper/test-time-adaptation-with-binary-feedback","title":"Test-Time Adaptation with Binary Feedback","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taeckyung/BiTTA","path":"data_loader/DOMAINNET126Dataset.py","file_url":"https://github.com/taeckyung/BiTTA/blob/HEAD/data_loader/DOMAINNET126Dataset.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d41e65573feeba36","mcp_get_code":{"code_sha256":"d41e65573feeba36"}},{"arxiv_id":"2505.17908","paper":"/paper/comfymind-toward-general-purpose-generation","title":"ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EnVision-Research/ComfyMind","path":"script/evaluation.py","file_url":"https://github.com/EnVision-Research/ComfyMind/blob/HEAD/script/evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50b302b35ddbddda","mcp_get_code":{"code_sha256":"50b302b35ddbddda"}},{"arxiv_id":"2505.01456","paper":"/paper/unlearning-sensitive-information-in","title":"Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation","date":"2025-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vaidehi99/unlok-vqa","path":"LLaVA/predict.py","file_url":"https://github.com/vaidehi99/unlok-vqa/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2503.23463","paper":"/paper/opendrivevla-towards-end-to-end-autonomous","title":"OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model","date":"2025-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DriveVLA/OpenDriveVLA","path":"drivevla/inference_drivevla.py","file_url":"https://github.com/DriveVLA/OpenDriveVLA/blob/HEAD/drivevla/inference_drivevla.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c8e18ac13ca83574","mcp_get_code":{"code_sha256":"c8e18ac13ca83574"}},{"arxiv_id":"2503.20188","paper":"/paper/rethinking-vision-language-model-in-face","title":"Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector","date":"2025-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chelsea234/m2f2_det","path":"llava/serve/cli_DDVQA_det.py","file_url":"https://github.com/chelsea234/m2f2_det/blob/HEAD/llava/serve/cli_DDVQA_det.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb945d226af806a7","mcp_get_code":{"code_sha256":"bb945d226af806a7"}},{"arxiv_id":"2503.19903","paper":"/paper/scaling-vision-pre-training-to-4k-resolution","title":"Scaling Vision Pre-Training to 4K Resolution","date":"2025-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"efficient-large-model/vila","path":"server.py","file_url":"https://github.com/efficient-large-model/vila/blob/HEAD/server.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1c69e761fdf05a26","mcp_get_code":{"code_sha256":"1c69e761fdf05a26"}},{"arxiv_id":"2503.09601","paper":"/paper/rewardsds-aligning-score-distillation-via","title":"RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"itaychachy/RewardSDS","path":"evaluation/aesthetic_eval.py","file_url":"https://github.com/itaychachy/RewardSDS/blob/HEAD/evaluation/aesthetic_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"68fcd95a9ed32977","mcp_get_code":{"code_sha256":"68fcd95a9ed32977"}},{"arxiv_id":"2503.09601","paper":"/paper/rewardsds-aligning-score-distillation-via","title":"RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"itaychachy/RewardSDS","path":"evaluation/clip_eval.py","file_url":"https://github.com/itaychachy/RewardSDS/blob/HEAD/evaluation/clip_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b3be8306c7ad6d6d","mcp_get_code":{"code_sha256":"b3be8306c7ad6d6d"}},{"arxiv_id":"2503.02187","paper":"/paper/h-edit-effective-and-flexible-diffusion-based","title":"h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transform","date":"2025-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nktoan/h-edit","path":"text-guided/main_masactrl.py","file_url":"https://github.com/nktoan/h-edit/blob/HEAD/text-guided/main_masactrl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"79d9960693d3111d","mcp_get_code":{"code_sha256":"79d9960693d3111d"}},{"arxiv_id":"2502.14296","paper":"/paper/on-the-trustworthiness-of-generative","title":"On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective","date":null,"month_inferred_from_arxiv_id":"2025-02","title_source":"archive","repo":"thuccslab/figstep","path":"src/generate_prompts.py","file_url":"https://github.com/thuccslab/figstep/blob/HEAD/src/generate_prompts.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7c7ccd22930b32c","mcp_get_code":{"code_sha256":"e7c7ccd22930b32c"}},{"arxiv_id":"2502.11494","paper":"/paper/stop-looking-for-important-tokens-in","title":"Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zichenwen1/dart","path":"predict.py","file_url":"https://github.com/zichenwen1/dart/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2502.06788","paper":"/paper/evev2-improved-baselines-for-encoder-free","title":"EVEv2: Improved Baselines for Encoder-Free Vision-Language Models","date":"2025-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baaivision/EVE","path":"EVEv1/eve/eval/model_vqa_qbench.py","file_url":"https://github.com/baaivision/EVE/blob/HEAD/EVEv1/eve/eval/model_vqa_qbench.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bbe3f02e93e14ae0","mcp_get_code":{"code_sha256":"bbe3f02e93e14ae0"}},{"arxiv_id":"2502.03628","paper":"/paper/the-hidden-life-of-tokens-reducing","title":"The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering","date":"2025-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LzVv123456/VISTA","path":"mmhal_eval.py","file_url":"https://github.com/LzVv123456/VISTA/blob/HEAD/mmhal_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa84cc45b40e5710","mcp_get_code":{"code_sha256":"aa84cc45b40e5710"}},{"arxiv_id":"2501.01790","paper":"/paper/ingredients-blending-custom-photos-with-video","title":"Ingredients: Blending Custom Photos with Video Diffusion Transformers","date":"2025-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feizc/ingredients","path":"metric/face_sim_fid.py","file_url":"https://github.com/feizc/ingredients/blob/HEAD/metric/face_sim_fid.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"18703ab999a62c3e","mcp_get_code":{"code_sha256":"18703ab999a62c3e"}},{"arxiv_id":"2412.12974","paper":"/paper/attentive-eraser-unleashing-diffusion-model-s","title":"Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anonym0u3/attentiveeraser","path":"evaluation/lpips_score.py","file_url":"https://github.com/anonym0u3/attentiveeraser/blob/HEAD/evaluation/lpips_score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e6809c12159dbf7b","mcp_get_code":{"code_sha256":"e6809c12159dbf7b"}},{"arxiv_id":"2412.12359","paper":"/paper/visual-instruction-tuning-with-500x-fewer","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bibisbar/LLaVA-Steering","path":"tinyllava/eval/run_tiny_llava.py","file_url":"https://github.com/bibisbar/LLaVA-Steering/blob/HEAD/tinyllava/eval/run_tiny_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2412.07689","paper":"/paper/drivemm-all-in-one-large-multimodal-model-for","title":"DriveMM: All-in-One Large Multimodal Model for Autonomous Driving","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhijian11/DriveMM","path":"predict.py","file_url":"https://github.com/zhijian11/DriveMM/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2412.07012","paper":"/paper/provision-programmatically-scaling-vision","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jieyuz2/provision","path":"provision/annotation/attribute_llava.py","file_url":"https://github.com/jieyuz2/provision/blob/HEAD/provision/annotation/attribute_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5f90221712cb63f4","mcp_get_code":{"code_sha256":"5f90221712cb63f4"}},{"arxiv_id":"2412.05255","paper":"/paper/teamcraft-a-benchmark-for-multi-modal-multi","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","date":"2024-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"teamcraft-bench/teamcraft","path":"llava_teamcraft/predict.py","file_url":"https://github.com/teamcraft-bench/teamcraft/blob/HEAD/llava_teamcraft/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2412.04467","paper":"/paper/visionzip-longer-is-better-but-not-necessary","title":"VisionZip: Longer is Better but Not Necessary in Vision Language Models","date":"2024-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/visionzip","path":"gradio_demo.py","file_url":"https://github.com/dvlab-research/visionzip/blob/HEAD/gradio_demo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7db2c78b1f3cc693","mcp_get_code":{"code_sha256":"7db2c78b1f3cc693"}},{"arxiv_id":"2412.04317","paper":"/paper/flashsloth-lightning-multimodal-large","title":"FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression","date":"2024-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codefanw/flashsloth","path":"flashsloth/eval/model_vqa_qbench.py","file_url":"https://github.com/codefanw/flashsloth/blob/HEAD/flashsloth/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2412.03439","paper":"/paper/cleandift-diffusion-features-without-noise","title":"CleanDIFT: Diffusion Features without Noise","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CompVis/cleandift","path":"src/dataloader.py","file_url":"https://github.com/CompVis/cleandift/blob/HEAD/src/dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"740ad3754ea31e72","mcp_get_code":{"code_sha256":"740ad3754ea31e72"}},{"arxiv_id":"2411.19939","paper":"/paper/vlsbench-unveiling-visual-leakage-in","title":"VLSBench: Unveiling Visual Leakage in Multimodal Safety","date":"2024-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai45lab/vlsbench","path":"models/load_llava.py","file_url":"https://github.com/ai45lab/vlsbench/blob/HEAD/models/load_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2411.19325","paper":"/paper/geobench-vlm-benchmarking-vision-language","title":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","date":"2024-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"the-ai-alliance/geo-bench-vlm","path":"eval_geobenchvlm/internvl_cls_single.py","file_url":"https://github.com/the-ai-alliance/geo-bench-vlm/blob/HEAD/eval_geobenchvlm/internvl_cls_single.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"98f235b8bce2e606","mcp_get_code":{"code_sha256":"98f235b8bce2e606"}},{"arxiv_id":"2411.11360","paper":"/paper/ccexpert-advancing-mllm-capability-in-remote","title":"CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meize0729/ccexpert","path":"predict.py","file_url":"https://github.com/meize0729/ccexpert/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2411.05383","paper":"/paper/towards-low-resource-harmful-meme-detection","title":"Towards Low-Resource Harmful Meme Detection with LMM Agents","date":"2024-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jianzhao-huang/lorehm","path":"utils/run_llava.py","file_url":"https://github.com/jianzhao-huang/lorehm/blob/HEAD/utils/run_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2411.02902","paper":"/paper/membership-inference-attacks-against-large","title":"Membership Inference Attacks against Large Vision-Language Models","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LIONS-EPFL/VL-MIA","path":"run_with_text.py","file_url":"https://github.com/LIONS-EPFL/VL-MIA/blob/HEAD/run_with_text.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2411.02902","paper":"/paper/membership-inference-attacks-against-large","title":"Membership Inference Attacks against Large Vision-Language Models","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LIONS-EPFL/VL-MIA","path":"run_with_img.py","file_url":"https://github.com/LIONS-EPFL/VL-MIA/blob/HEAD/run_with_img.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"016ce1ddc61eea2c","mcp_get_code":{"code_sha256":"016ce1ddc61eea2c"}},{"arxiv_id":"2411.02712","paper":"/paper/v-dpo-mitigating-hallucination-in-large","title":"V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuxixie/v-dpo","path":"llava_dpo/eval/model_vqa_qbench.py","file_url":"https://github.com/yuxixie/v-dpo/blob/HEAD/llava_dpo/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2410.22313","paper":"/paper/senna-bridging-large-vision-language-models","title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/senna","path":"data_tools/senna_qa_utils.py","file_url":"https://github.com/hustvl/senna/blob/HEAD/data_tools/senna_qa_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e66e1c21f77a1ac3","mcp_get_code":{"code_sha256":"e66e1c21f77a1ac3"}},{"arxiv_id":"2410.20084","paper":"/paper/univst-a-unified-framework-for-training-free","title":"UniVST: A Unified Framework for Training-free Localized Video Style Transfer","date":"2024-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QuanjianSong/UniVST","path":"src/cal_optica_flow.py","file_url":"https://github.com/QuanjianSong/UniVST/blob/HEAD/src/cal_optica_flow.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b5d651334526030f","mcp_get_code":{"code_sha256":"b5d651334526030f"}},{"arxiv_id":"2410.19079","paper":"/paper/bifrost-3d-aware-image-compositing-with","title":"BIFRÖST: 3D-Aware Image compositing with Language Instructions","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lingxiao-li/Bifrost","path":"LLaVA_Bifrost/predict.py","file_url":"https://github.com/lingxiao-li/Bifrost/blob/HEAD/LLaVA_Bifrost/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2410.16236","paper":"/paper/llava-kd-a-framework-of-distilling-multimodal","title":"LLaVA-KD: A Framework of Distilling Multimodal Large Language Models","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Fantasyele/LLaVA-KD","path":"llavakd/eval/run_tiny_llava.py","file_url":"https://github.com/Fantasyele/LLaVA-KD/blob/HEAD/llavakd/eval/run_tiny_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2410.15778","paper":"/paper/reducing-hallucinations-in-vision-language","title":"Reducing Hallucinations in Vision-Language Models via Latent Space Steering","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shengliu66/vti","path":"experiments/eval/run_mmhal_vti.py","file_url":"https://github.com/shengliu66/vti/blob/HEAD/experiments/eval/run_mmhal_vti.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"76cb05a76ebdeb15","mcp_get_code":{"code_sha256":"76cb05a76ebdeb15"}},{"arxiv_id":"2410.14324","paper":"/paper/hico-hierarchical-controllable-diffusion","title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"360cvgroup/hico_t2i","path":"infer-avg.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/infer-avg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f81993bbb1d7686b","mcp_get_code":{"code_sha256":"f81993bbb1d7686b"}},{"arxiv_id":"2410.13360","paper":"/paper/remember-retrieve-and-generate-understanding","title":"RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hoar012/rap-mllm","path":"retriever.py","file_url":"https://github.com/hoar012/rap-mllm/blob/HEAD/retriever.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7a70c70cfc4f8bbb","mcp_get_code":{"code_sha256":"7a70c70cfc4f8bbb"}},{"arxiv_id":"2410.13360","paper":"/paper/remember-retrieve-and-generate-understanding","title":"RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hoar012/rap-mllm","path":"eval/TQA.py","file_url":"https://github.com/hoar012/rap-mllm/blob/HEAD/eval/TQA.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"20281a9b344a9430","mcp_get_code":{"code_sha256":"20281a9b344a9430"}},{"arxiv_id":"2410.13085","paper":"/paper/mmed-rag-versatile-multimodal-rag-system-for","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"richard-peng-xia/MMed-RAG","path":"train/dpo/predict.py","file_url":"https://github.com/richard-peng-xia/MMed-RAG/blob/HEAD/train/dpo/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2410.11758","paper":"/paper/latent-action-pretraining-from-videos","title":"Latent Action Pretraining from Videos","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LatentActionPretraining/LAPA","path":"laq/inference_sthv2.py","file_url":"https://github.com/LatentActionPretraining/LAPA/blob/HEAD/laq/inference_sthv2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ca8f8ec94f51579","mcp_get_code":{"code_sha256":"0ca8f8ec94f51579"}},{"arxiv_id":"2410.07167","paper":"/paper/deciphering-cross-modal-alignment-in-large","title":"Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shikiw/modality-integration-rate","path":"predict.py","file_url":"https://github.com/shikiw/modality-integration-rate/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2410.07113","paper":"/paper/personalized-visual-instruction-tuning","title":"Personalized Visual Instruction Tuning","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sterzhang/pvit","path":"personalize-llava/predict.py","file_url":"https://github.com/sterzhang/pvit/blob/HEAD/personalize-llava/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2410.06169","paper":"/paper/quadratic-is-not-what-you-need-for-multimodal","title":"Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangAIPI/YOPO_MLLM_Pruning","path":"LLaVA/predict.py","file_url":"https://github.com/ZhangAIPI/YOPO_MLLM_Pruning/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2410.04417","paper":"/paper/sparsevlm-visual-token-sparsification-for","title":"SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference","date":"2024-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gumpest/SparseVLMs","path":"predict.py","file_url":"https://github.com/Gumpest/SparseVLMs/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2410.03263","paper":"/paper/test-time-adaptation-for-regression-by","title":"Test-time Adaptation for Regression by Subspace Alignment","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kzkadc/regression-tta","path":"dataset/image_utils.py","file_url":"https://github.com/kzkadc/regression-tta/blob/HEAD/dataset/image_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"89b23899ddc80a79","mcp_get_code":{"code_sha256":"89b23899ddc80a79"}},{"arxiv_id":"2410.00418","paper":"/paper/posterior-mean-rectified-flow-towards-minimum","title":"Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ohayonguy/PMRF","path":"evaluation/calculate_cos_dist.py","file_url":"https://github.com/ohayonguy/PMRF/blob/HEAD/evaluation/calculate_cos_dist.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d8d6d771a1dadff4","mcp_get_code":{"code_sha256":"d8d6d771a1dadff4"}},{"arxiv_id":"2409.17663","paper":"/paper/explanation-bottleneck-models","title":"Explanation Bottleneck Models","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yshinya6/xbm","path":"xbm-llava/predict.py","file_url":"https://github.com/yshinya6/xbm/blob/HEAD/xbm-llava/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2409.17143","paper":"/paper/attention-prompting-on-image-for-large-vision","title":"Attention Prompting on Image for Large Vision-Language Models","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yu-rp/apiprompting","path":"API/API_LLaVA/functions.py","file_url":"https://github.com/yu-rp/apiprompting/blob/HEAD/API/API_LLaVA/functions.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2409.15180","paper":"/paper/a-comprehensive-survey-with-critical-analysis","title":"A Comprehensive Survey with Critical Analysis for Deepfake Speech Detection","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"tamlhp/dfd_benchmark","path":"detect_img.py","file_url":"https://github.com/tamlhp/dfd_benchmark/blob/HEAD/detect_img.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce6fddcb44354b77","mcp_get_code":{"code_sha256":"ce6fddcb44354b77"}},{"arxiv_id":"2409.13682","paper":"/paper/remembr-building-and-reasoning-over-long","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","date":"2024-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA-AI-IOT/remembr","path":"remembr/captioners/vila_captioner.py","file_url":"https://github.com/NVIDIA-AI-IOT/remembr/blob/HEAD/remembr/captioners/vila_captioner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"20b5922e237d1de7","mcp_get_code":{"code_sha256":"20b5922e237d1de7"}},{"arxiv_id":"2409.10994","paper":"/paper/less-is-more-a-simple-yet-effective-token","title":"Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs","date":"2024-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/trim","path":"predict.py","file_url":"https://github.com/freedomintelligence/trim/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2409.10197","paper":"/paper/fit-and-prune-fast-and-training-free-visual","title":"Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models","date":"2024-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ywh187/fitprune","path":"LLaVA_NEXT/predict.py","file_url":"https://github.com/ywh187/fitprune/blob/HEAD/LLaVA_NEXT/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2409.04796","paper":"/paper/enhancing-outlier-knowledge-for-few-shot-out","title":"Enhancing Outlier Knowledge for Few-Shot Out-of-Distribution Detection with Extensible Local Prompts","date":"2024-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AuroraZengfh/Local-Prompt","path":"utils/grad_cam.py","file_url":"https://github.com/AuroraZengfh/Local-Prompt/blob/HEAD/utils/grad_cam.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7458439441af1cea","mcp_get_code":{"code_sha256":"7458439441af1cea"}},{"arxiv_id":"2409.02919","paper":"/paper/hiprompt-tuning-free-higher-resolution","title":"HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts","date":"2024-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Liuxinyv/HiPrompt","path":"LLaVA/predict.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2409.02889","paper":"/paper/longllava-scaling-multi-modal-llms-to-1000","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","date":"2024-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/longllava","path":"llava/mm_utils.py","file_url":"https://github.com/freedomintelligence/longllava/blob/HEAD/llava/mm_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d51fcf23e1e8c26f","mcp_get_code":{"code_sha256":"d51fcf23e1e8c26f"}},{"arxiv_id":"2409.01392","paper":"/paper/genagent-build-collaborative-ai-systems-with","title":"ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xxyQwQ/ComfyBench","path":"script/evaluation.py","file_url":"https://github.com/xxyQwQ/ComfyBench/blob/HEAD/script/evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50b302b35ddbddda","mcp_get_code":{"code_sha256":"50b302b35ddbddda"}},{"arxiv_id":"2409.01179","paper":"/paper/recoverable-compression-a-multimodal-vision","title":"Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"banjiuyufen/Recoverable-Compression","path":"predict.py","file_url":"https://github.com/banjiuyufen/Recoverable-Compression/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2409.00638","paper":"/paper/igev-iterative-multi-range-geometry-encoding","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","date":"2024-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gangweix/igev","path":"IGEV-Stereo/demo_imgs.py","file_url":"https://github.com/gangweix/igev/blob/HEAD/IGEV-Stereo/demo_imgs.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c521de8b851930a","mcp_get_code":{"code_sha256":"6c521de8b851930a"}},{"arxiv_id":"2408.16266","paper":"/paper/improving-diffusion-based-data-augmentation","title":"Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scuwyh2000/diff-ii","path":"get_inversion.py","file_url":"https://github.com/scuwyh2000/diff-ii/blob/HEAD/get_inversion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e9fa9ecafcd8097f","mcp_get_code":{"code_sha256":"e9fa9ecafcd8097f"}},{"arxiv_id":"2408.15881","paper":"/paper/llava-mod-making-llava-tiny-via-moe-knowledge","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shufangxun/llava-mod","path":"llavamod/eval/run_llava.py","file_url":"https://github.com/shufangxun/llava-mod/blob/HEAD/llavamod/eval/run_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2408.12109","paper":"/paper/rovrm-a-robust-visual-reward-model-optimized","title":"RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data","date":"2024-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangclnlp/vision-llm-alignment","path":"eval/predict_llava.py","file_url":"https://github.com/wangclnlp/vision-llm-alignment/blob/HEAD/eval/predict_llava.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2408.03735","paper":"/paper/advancing-multimodal-large-language-models","title":"Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation","date":"2024-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xjjxmu/qslaw","path":"predict.py","file_url":"https://github.com/xjjxmu/qslaw/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2408.00491","paper":"/paper/2408-00491","title":"GalleryGPT: Analyzing Paintings with Large Multimodal Models","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"steven640pixel/gallerygpt","path":"llava/eval/run_llava.py","file_url":"https://github.com/steven640pixel/gallerygpt/blob/HEAD/llava/eval/run_llava.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2407.21771","paper":"/paper/paying-more-attention-to-image-a-training","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","date":"2024-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hasanar1f/llava-hallunication-fix","path":"modPAI/run_llava.py","file_url":"https://github.com/hasanar1f/llava-hallunication-fix/blob/HEAD/modPAI/run_llava.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1b77429ad5bf1632","mcp_get_code":{"code_sha256":"1b77429ad5bf1632"}},{"arxiv_id":"2407.18121","paper":"/paper/efficient-inference-of-vision-instruction","title":"Efficient Inference of Vision Instruction-Following Models with Elastic Cache","date":"2024-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuzuyan/elasticcache","path":"convert_rouge_llava.py","file_url":"https://github.com/liuzuyan/elasticcache/blob/HEAD/convert_rouge_llava.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb945d226af806a7","mcp_get_code":{"code_sha256":"bb945d226af806a7"}},{"arxiv_id":"2407.17850","paper":"/paper/flexiedit-frequency-aware-latent-refinement","title":"FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing","date":"2024-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kookie12/FlexiEdit","path":"inference_flexiedit.py","file_url":"https://github.com/kookie12/FlexiEdit/blob/HEAD/inference_flexiedit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"83dfe7de8ca77508","mcp_get_code":{"code_sha256":"83dfe7de8ca77508"}},{"arxiv_id":"2407.16837","paper":"/paper/compbench-a-comparative-reasoning-benchmark","title":"MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raptormai/compbench","path":"preprocessing/soccernet/merge_left_right_imgs_llava_finetune.py","file_url":"https://github.com/raptormai/compbench/blob/HEAD/preprocessing/soccernet/merge_left_right_imgs_llava_finetune.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0ec33995a5dc05d1","mcp_get_code":{"code_sha256":"0ec33995a5dc05d1"}},{"arxiv_id":"2407.14505","paper":"/paper/t2v-compbench-a-comprehensive-benchmark-for","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KaiyueSun98/T2V-CompBench","path":"LLaVA/llava/eval/compbench_eval_dynamic_attr.py","file_url":"https://github.com/KaiyueSun98/T2V-CompBench/blob/HEAD/LLaVA/llava/eval/compbench_eval_dynamic_attr.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2407.14505","paper":"/paper/t2v-compbench-a-comprehensive-benchmark-for","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KaiyueSun98/T2V-CompBench","path":"LLaVA/llava/eval/compbench_eval_action_binding.py","file_url":"https://github.com/KaiyueSun98/T2V-CompBench/blob/HEAD/LLaVA/llava/eval/compbench_eval_action_binding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2407.06581","paper":"/paper/vision-language-models-are-blind","title":"Vision language models are blind: Failing to translate detailed visual features into words","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anguyen8/vision-llms-are-blind","path":"src/LinearProbe/LLaVA-NeXT/predict.py","file_url":"https://github.com/anguyen8/vision-llms-are-blind/blob/HEAD/src/LinearProbe/LLaVA-NeXT/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2407.05131","paper":"/paper/rule-reliable-multimodal-rag-for-factuality","title":"RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models","date":"2024-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"richard-peng-xia/rule","path":"predict.py","file_url":"https://github.com/richard-peng-xia/rule/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2406.20098","paper":"/paper/web2code-a-large-scale-webpage-to-code","title":"Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MBZUAI-LLM/web2code","path":"web2code/predict.py","file_url":"https://github.com/MBZUAI-LLM/web2code/blob/HEAD/web2code/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2406.20095","paper":"/paper/llara-supercharging-robot-learning-data-for","title":"LLaRA: Supercharging Robot Learning Data for Vision-Language Policy","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LostXine/LLaRA","path":"train-llava/predict.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/train-llava/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2406.15334","paper":"/paper/multimodal-task-vectors-enable-many-shot","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","date":"2024-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brandon3964/multimodal-task-vector","path":"MTV/models.py","file_url":"https://github.com/brandon3964/multimodal-task-vector/blob/HEAD/MTV/models.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3275ed06c9e635d8","mcp_get_code":{"code_sha256":"3275ed06c9e635d8"}},{"arxiv_id":"2406.14794","paper":"/paper/imageflownet-forecasting-multiscale","title":"ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images","date":"2024-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ChenLiu-1996/ImageFlowNet","path":"src/datasets/brain_gbm.py","file_url":"https://github.com/ChenLiu-1996/ImageFlowNet/blob/HEAD/src/datasets/brain_gbm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"79571a3353d2a699","mcp_get_code":{"code_sha256":"79571a3353d2a699"}},{"arxiv_id":"2406.12742","paper":"/paper/benchmarking-multi-image-understanding-in","title":"Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dtennant/mirb_eval","path":"utils/utils.py","file_url":"https://github.com/dtennant/mirb_eval/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2a0bf8b452c624f0","mcp_get_code":{"code_sha256":"2a0bf8b452c624f0"}},{"arxiv_id":"2406.12235","paper":"/paper/holmes-vad-towards-unbiased-and-explainable","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pipixin321/holmesvad","path":"demo/utils.py","file_url":"https://github.com/pipixin321/holmesvad/blob/HEAD/demo/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6843e61b5d422c22","mcp_get_code":{"code_sha256":"6843e61b5d422c22"}},{"arxiv_id":"2406.11833","paper":"/paper/mmdu-a-multi-turn-multi-image-dialog","title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuziyu77/mmdu","path":"model_generation/mmdu_LLaVa_gen_ans.py","file_url":"https://github.com/liuziyu77/mmdu/blob/HEAD/model_generation/mmdu_LLaVa_gen_ans.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2406.10995","paper":"/paper/concept-skill-transferability-based-data","title":"Concept-skill Transferability-based Data Selection for Large Vision-Language Models","date":"2024-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"g-jwlee/coincide_code","path":"COINCIDE_train/predict.py","file_url":"https://github.com/g-jwlee/coincide_code/blob/HEAD/COINCIDE_train/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2406.08100","paper":"/paper/multimodal-table-understanding","title":"Multimodal Table Understanding","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"spursgozmy/table-llava","path":"llava/eval/model_vqa_qbench.py","file_url":"https://github.com/spursgozmy/table-llava/blob/HEAD/llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2406.07230","paper":"/paper/needle-in-a-multimodal-haystack","title":"Needle In A Multimodal Haystack","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/mm-niah","path":"prepare_rag.py","file_url":"https://github.com/opengvlab/mm-niah/blob/HEAD/prepare_rag.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"210abccc49444195","mcp_get_code":{"code_sha256":"210abccc49444195"}},{"arxiv_id":"2405.15973","paper":"/paper/enhancing-visual-language-modality-alignment","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umd-huang-lab/sima","path":"predict.py","file_url":"https://github.com/umd-huang-lab/sima/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2405.14974","paper":"/paper/lova3-learning-to-visual-question-answering","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/LOVA3","path":"llava/eval/model_vqa_qbench.py","file_url":"https://github.com/showlab/LOVA3/blob/HEAD/llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2405.14295","paper":"/paper/focus-anywhere-for-fine-grained-multi-page","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ucas-HaoranWei/Vary","path":"Vary-master/vary/demo/run_opt.py","file_url":"https://github.com/Ucas-HaoranWei/Vary/blob/HEAD/Vary-master/vary/demo/run_opt.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2405.12107","paper":"/paper/imp-highly-capable-large-multimodal-models","title":"Imp: Highly Capable Large Multimodal Models for Mobile Devices","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"milvlg/imp","path":"imp_llava/eval/model_vqa_qbench.py","file_url":"https://github.com/milvlg/imp/blob/HEAD/imp_llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2405.03121","paper":"/paper/anitalker-animate-vivid-and-diverse-talking","title":"AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding","date":"2024-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-lance/anitalker","path":"code/webgui.py","file_url":"https://github.com/x-lance/anitalker/blob/HEAD/code/webgui.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"67358df25a58f1ef","mcp_get_code":{"code_sha256":"67358df25a58f1ef"}},{"arxiv_id":"2404.18630","paper":"/paper/4d-dress-a-4d-dataset-of-real-world-human","title":"4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations","date":"2024-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-ait/4d-dress","path":"dataset/utility.py","file_url":"https://github.com/eth-ait/4d-dress/blob/HEAD/dataset/utility.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3a090c430afce4c1","mcp_get_code":{"code_sha256":"3a090c430afce4c1"}},{"arxiv_id":"2404.10618","paper":"/paper/private-attribute-inference-from-images-with","title":"Private Attribute Inference from Images with Vision-Language Models","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/privacy-inference-multimodal","path":"Experimentation/LLaVa-NeXT/run_llava.py","file_url":"https://github.com/eth-sri/privacy-inference-multimodal/blob/HEAD/Experimentation/LLaVa-NeXT/run_llava.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2404.10501","paper":"/paper/self-supervised-visual-preference-alignment","title":"Self-Supervised Visual Preference Alignment","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kevinz-code/SeVa","path":"seva/llava/eval/model_vqa_qbench.py","file_url":"https://github.com/Kevinz-code/SeVa/blob/HEAD/seva/llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2404.05163","paper":"/paper/semantic-flow-learning-semantic-field-of","title":"Semantic Flow: Learning Semantic Field of Dynamic Scenes from Monocular Videos","date":"2024-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianfr/Semantic-Flow","path":"train/utils/generate_flow.py","file_url":"https://github.com/tianfr/Semantic-Flow/blob/HEAD/train/utils/generate_flow.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c521de8b851930a","mcp_get_code":{"code_sha256":"6c521de8b851930a"}},{"arxiv_id":"2403.18814","paper":"/paper/mini-gemini-mining-the-potential-of-multi","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/minigemini","path":"predict.py","file_url":"https://github.com/dvlab-research/minigemini/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2403.18775","paper":"/paper/imagenet-d-benchmarking-neural-network","title":"ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenshuang-zhang/imagenet_d","path":"LLaVA/predict.py","file_url":"https://github.com/chenshuang-zhang/imagenet_d/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2403.18775","paper":"/paper/imagenet-d-benchmarking-neural-network","title":"ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenshuang-zhang/imagenet_d","path":"LLaVA/llava/serve/eval_imagenet_d.py","file_url":"https://github.com/chenshuang-zhang/imagenet_d/blob/HEAD/LLaVA/llava/serve/eval_imagenet_d.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb945d226af806a7","mcp_get_code":{"code_sha256":"bb945d226af806a7"}},{"arxiv_id":"2403.18252","paper":"/paper/beyond-embeddings-the-promise-of-visual-table","title":"Beyond Embeddings: The Promise of Visual Table in Visual Reasoning","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lavi-lab/visual-table","path":"llava/eval/model_vqa_qbench.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2403.16999","paper":"/paper/visual-cot-unleashing-chain-of-thought","title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepcs233/visual-cot","path":"llava/eval/model_vqa_qbench.py","file_url":"https://github.com/deepcs233/visual-cot/blob/HEAD/llava/eval/model_vqa_qbench.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bbe3f02e93e14ae0","mcp_get_code":{"code_sha256":"bbe3f02e93e14ae0"}},{"arxiv_id":"2403.13805","paper":"/paper/rar-retrieving-and-ranking-augmented-mllms","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","date":"2024-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuziyu77/rar","path":"Few_shot/retrieve_and_rerank.py","file_url":"https://github.com/liuziyu77/rar/blob/HEAD/Few_shot/retrieve_and_rerank.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2403.13164","paper":"/paper/vl-icl-bench-the-devil-in-the-details-of","title":"VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ys-zong/vl-icl","path":"utils/utils.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a0bf8b452c624f0","mcp_get_code":{"code_sha256":"2a0bf8b452c624f0"}},{"arxiv_id":"2403.11299","paper":"/paper/sq-llava-self-questioning-for-large-vision","title":"SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant","date":"2024-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heliossun/sq-llava","path":"sqllava/eval/run_llava.py","file_url":"https://github.com/heliossun/sq-llava/blob/HEAD/sqllava/eval/run_llava.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2403.02910","paper":"/paper/imgtrojan-jailbreaking-vision-language-models","title":"ImgTrojan: Jailbreaking Vision-Language Models with ONE Image","date":"2024-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xijia-tao/imgtrojan","path":"finetune/infer_example.py","file_url":"https://github.com/xijia-tao/imgtrojan/blob/HEAD/finetune/infer_example.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb945d226af806a7","mcp_get_code":{"code_sha256":"bb945d226af806a7"}},{"arxiv_id":"2403.00486","paper":"/paper/selective-stereo-adaptive-frequency","title":"Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"windsrain/selective-stereo","path":"Selective-IGEV/demo_imgs.py","file_url":"https://github.com/windsrain/selective-stereo/blob/HEAD/Selective-IGEV/demo_imgs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7531666246aabe0e","mcp_get_code":{"code_sha256":"7531666246aabe0e"}},{"arxiv_id":"2402.19474","paper":"/paper/the-all-seeing-project-v2-towards-general","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/all-seeing","path":"all-seeing-v2/predict.py","file_url":"https://github.com/opengvlab/all-seeing/blob/HEAD/all-seeing-v2/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2402.14683","paper":"/paper/visual-hallucinations-of-multi-modal-large","title":"Visual Hallucinations of Multi-modal Large Language Models","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenhuang2000/vhtest","path":"Evaluation/LLaVA/llava_oeq_version.py","file_url":"https://github.com/wenhuang2000/vhtest/blob/HEAD/Evaluation/LLaVA/llava_oeq_version.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bb945d226af806a7","mcp_get_code":{"code_sha256":"bb945d226af806a7"}},{"arxiv_id":"2402.14545","paper":"/paper/less-is-more-mitigating-multimodal","title":"Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuezih/less-is-more","path":"LLaVA/predict.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2402.12688","paper":"/paper/robust-wide-robust-watermarking-against","title":"Robust-Wide: Robust Watermarking against Instruction-driven Image Editing","date":null,"month_inferred_from_arxiv_id":"2024-02","title_source":"archive","repo":"hurunyi/robust-wide","path":"evaluate.py","file_url":"https://github.com/hurunyi/robust-wide/blob/HEAD/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e093542bc06414d7","mcp_get_code":{"code_sha256":"e093542bc06414d7"}},{"arxiv_id":"2402.11411","paper":"/paper/aligning-modalities-in-vision-large-language","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiyangzhou/povid","path":"predict.py","file_url":"https://github.com/yiyangzhou/povid/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2402.10884","paper":"/paper/multi-modal-preference-alignment-remedies","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"findalexli/mllm-dpo","path":"llava/eval/model_vqa_qbench.py","file_url":"https://github.com/findalexli/mllm-dpo/blob/HEAD/llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2402.06659","paper":"/paper/shadowcast-stealthy-data-poisoning-attacks","title":"Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umd-huang-lab/VLM-Poisoning","path":"LLaVA/predict.py","file_url":"https://github.com/umd-huang-lab/VLM-Poisoning/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2402.06659","paper":"/paper/shadowcast-stealthy-data-poisoning-attacks","title":"Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umd-huang-lab/VLM-Poisoning","path":"eval_poison_llava.py","file_url":"https://github.com/umd-huang-lab/VLM-Poisoning/blob/HEAD/eval_poison_llava.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb945d226af806a7","mcp_get_code":{"code_sha256":"bb945d226af806a7"}},{"arxiv_id":"2402.06659","paper":"/paper/shadowcast-stealthy-data-poisoning-attacks","title":"Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umd-huang-lab/VLM-Poisoning","path":"poison_llava.py","file_url":"https://github.com/umd-huang-lab/VLM-Poisoning/blob/HEAD/poison_llava.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1780d801d03a6325","mcp_get_code":{"code_sha256":"1780d801d03a6325"}},{"arxiv_id":"2402.03312","paper":"/paper/test-time-adaptation-for-depth-completion","title":"Test-Time Adaptation for Depth Completion","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seobbro/TTA-depth-completion","path":"src/data_utils.py","file_url":"https://github.com/seobbro/TTA-depth-completion/blob/HEAD/src/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"32c07ecf481369ad","mcp_get_code":{"code_sha256":"32c07ecf481369ad"}},{"arxiv_id":"2402.02207","paper":"/paper/safety-fine-tuning-at-almost-no-cost-a","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ys-zong/vlguard","path":"utils/utils.py","file_url":"https://github.com/ys-zong/vlguard/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb00c4a25d41c6bf","mcp_get_code":{"code_sha256":"bb00c4a25d41c6bf"}},{"arxiv_id":"2401.12869","paper":"/paper/trove-inducing-verifiable-and-efficient","title":"TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zorazrw/trove","path":"server/gqa.py","file_url":"https://github.com/zorazrw/trove/blob/HEAD/server/gqa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"code_sha256_prefix":"89498f1816854476","mcp_get_code":{"code_sha256":"89498f1816854476"}},{"arxiv_id":"2401.10891","paper":"/paper/depth-anything-unleashing-the-power-of-large","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"spacewalk01/depth-anything-tensorrt","path":"python/depth_anything/util/transform.py","file_url":"https://github.com/spacewalk01/depth-anything-tensorrt/blob/HEAD/python/depth_anything/util/transform.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"24a768b877a487a4","mcp_get_code":{"code_sha256":"24a768b877a487a4"}},{"arxiv_id":"2401.06591","paper":"/paper/prometheus-vision-vision-language-model-as-a","title":"Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaistai/prometheus-vision","path":"llava/eval/model_vqa_qbench.py","file_url":"https://github.com/kaistai/prometheus-vision/blob/HEAD/llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2401.04861","paper":"/paper/ctnerf-cross-time-transformer-for-dynamic","title":"CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video","date":"2024-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingy038/ctnerf","path":"utils/generate_flow.py","file_url":"https://github.com/xingy038/ctnerf/blob/HEAD/utils/generate_flow.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c521de8b851930a","mcp_get_code":{"code_sha256":"6c521de8b851930a"}},{"arxiv_id":"2401.02906","paper":"/paper/mllm-protector-ensuring-mllm-s-safety-without","title":"MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance","date":"2024-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pipilurj/mllm-protector","path":"predict.py","file_url":"https://github.com/pipilurj/mllm-protector/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2401.01887","paper":"/paper/leap-vo-long-term-effective-any-point","title":"LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry","date":"2024-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wrchen530/leapvo","path":"main/stream.py","file_url":"https://github.com/wrchen530/leapvo/blob/HEAD/main/stream.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"df1ca9601675493f","mcp_get_code":{"code_sha256":"df1ca9601675493f"}},{"arxiv_id":"2401.01651","paper":"/paper/aigcbench-comprehensive-evaluation-of-image","title":"AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI","date":"2024-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"benchcouncil/aigcbench","path":"utils.py","file_url":"https://github.com/benchcouncil/aigcbench/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"88518226837c7910","mcp_get_code":{"code_sha256":"88518226837c7910"}},{"arxiv_id":"2312.17116","paper":"/paper/generalizable-visual-reinforcement-learning","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wadiuvatzy/sam-g","path":"efficientvit/demo_sam_model.py","file_url":"https://github.com/wadiuvatzy/sam-g/blob/HEAD/efficientvit/demo_sam_model.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb3d4f05a88ee013","mcp_get_code":{"code_sha256":"bb3d4f05a88ee013"}},{"arxiv_id":"2312.15736","paper":"/paper/towards-real-world-blind-face-restoration-1","title":"Towards Real-World Blind Face Restoration with Generative Diffusion Prior","date":"2023-12-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenxx89/bfrffusion","path":"metrics/calculate_cos_dist.py","file_url":"https://github.com/chenxx89/bfrffusion/blob/HEAD/metrics/calculate_cos_dist.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d8d6d771a1dadff4","mcp_get_code":{"code_sha256":"d8d6d771a1dadff4"}},{"arxiv_id":"2312.14867","paper":"/paper/viescore-towards-explainable-metrics-for","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","date":"2023-12-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TIGER-AI-Lab/VIEScore","path":"viescore/mllm_tools/utils.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ec33995a5dc05d1","mcp_get_code":{"code_sha256":"0ec33995a5dc05d1"}},{"arxiv_id":"2312.11370","paper":"/paper/g-llava-solving-geometric-problem-with-multi","title":"G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pipilurj/g-llava","path":"gllava/eval/run_llava.py","file_url":"https://github.com/pipilurj/g-llava/blob/HEAD/gllava/eval/run_llava.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2312.10656","paper":"/paper/vidtome-video-token-merging-for-zero-shot","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","date":"2023-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lixirui142/VidToMe","path":"utils/utils.py","file_url":"https://github.com/lixirui142/VidToMe/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"08704c5df640348e","mcp_get_code":{"code_sha256":"08704c5df640348e"}},{"arxiv_id":"2312.06731","paper":"/paper/genixer-empowering-multimodal-large-language","title":"Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaohengyuan1/genixer","path":"Genixer_LLaVA/llava/eval/model_vqa_qbench.py","file_url":"https://github.com/zhaohengyuan1/genixer/blob/HEAD/Genixer_LLaVA/llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2312.03594","paper":"/paper/a-task-is-worth-one-word-learning-with-task","title":"A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"open-mmlab/mmagic","path":"mmagic/apis/inferencers/controlnet_animation_inferencer.py","file_url":"https://github.com/open-mmlab/mmagic/blob/HEAD/mmagic/apis/inferencers/controlnet_animation_inferencer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2e8cf78365bf16a1","mcp_get_code":{"code_sha256":"2e8cf78365bf16a1"}},{"arxiv_id":"2312.03046","paper":"/paper/diversified-in-domain-synthesis-with","title":"Diversified in-domain synthesis with efficient fine-tuning for few-shot classification","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vturrisi/disef","path":"generation/synthetic_augmentation_pipeline.py","file_url":"https://github.com/vturrisi/disef/blob/HEAD/generation/synthetic_augmentation_pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52321defb194c04d","mcp_get_code":{"code_sha256":"52321defb194c04d"}},{"arxiv_id":"2312.02908","paper":"/paper/deep-learning-segmentation-of-spiral-arms-and","title":"Deep Learning Segmentation of Spiral Arms and Bars","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mwalmsley/zoobot-3d","path":"zoobot_3d/pytorch_dataset.py","file_url":"https://github.com/mwalmsley/zoobot-3d/blob/HEAD/zoobot_3d/pytorch_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e86b6a1fbe7fe28d","mcp_get_code":{"code_sha256":"e86b6a1fbe7fe28d"}},{"arxiv_id":"2311.16711","paper":"/paper/ledits-limitless-image-editing-using-text-to","title":"LEDITS++: Limitless Image Editing using Text-to-Image Models","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-research/ledits_pp","path":"src/leditspp/pipeline_stable_diffusion_xl_ledits.py","file_url":"https://github.com/ml-research/ledits_pp/blob/HEAD/src/leditspp/pipeline_stable_diffusion_xl_ledits.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"875f3a7a1739c2b1","mcp_get_code":{"code_sha256":"875f3a7a1739c2b1"}},{"arxiv_id":"2311.07562","paper":"/paper/gpt-4v-in-wonderland-large-multimodal-models","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzxslp/mm-navigator","path":"call_gpt4.py","file_url":"https://github.com/zzxslp/mm-navigator/blob/HEAD/call_gpt4.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4fc4c9e17e2de6f3","mcp_get_code":{"code_sha256":"4fc4c9e17e2de6f3"}},{"arxiv_id":"2311.07470","paper":"/paper/finding-and-editing-multi-modal-neurons-in","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opanhw/MM_Neurons","path":"src/load_datasets.py","file_url":"https://github.com/opanhw/MM_Neurons/blob/HEAD/src/load_datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2311.07362","paper":"/paper/volcano-mitigating-multimodal-hallucination","title":"Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaistai/volcano","path":"llava/eval/volcano_gavie.py","file_url":"https://github.com/kaistai/volcano/blob/HEAD/llava/eval/volcano_gavie.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2311.06783","paper":"/paper/q-instruct-improving-low-level-visual","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","date":"2023-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Q-Future/Q-Instruct","path":"eval_scripts/llava_v1.5/eval_image_quality.py","file_url":"https://github.com/Q-Future/Q-Instruct/blob/HEAD/eval_scripts/llava_v1.5/eval_image_quality.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2311.06783","paper":"/paper/q-instruct-improving-low-level-visual","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","date":"2023-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Q-Future/Q-Instruct","path":"eval_scripts/mplug_owl_2/eval_image_quality.py","file_url":"https://github.com/Q-Future/Q-Instruct/blob/HEAD/eval_scripts/mplug_owl_2/eval_image_quality.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb945d226af806a7","mcp_get_code":{"code_sha256":"bb945d226af806a7"}},{"arxiv_id":"2311.04584","paper":"/paper/weakly-supervised-deepfake-localization-in","title":"Weakly-supervised deepfake localization in diffusion-generated images","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bit-ml/dolos","path":"dolos/methods/patch_forensics/train_full_supervision.py","file_url":"https://github.com/bit-ml/dolos/blob/HEAD/dolos/methods/patch_forensics/train_full_supervision.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"33f18f258b316cbc","mcp_get_code":{"code_sha256":"33f18f258b316cbc"}},{"arxiv_id":"2310.19248","paper":"/paper/impress-evaluating-the-resilience-of","title":"IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AAAAAAsuka/Impress","path":"pg_metric.py","file_url":"https://github.com/AAAAAAsuka/Impress/blob/HEAD/pg_metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c79b613cdc952e7","mcp_get_code":{"code_sha256":"1c79b613cdc952e7"}},{"arxiv_id":"2310.18894","paper":null,"title":"arXiv:2310.18894","date":null,"month_inferred_from_arxiv_id":"2023-10","title_source":null,"repo":"Crazy-Jack/nips2023_shape_vs_texture","path":"texture-synthesis-visualization/utilities.py","file_url":"https://github.com/Crazy-Jack/nips2023_shape_vs_texture/blob/HEAD/texture-synthesis-visualization/utilities.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ee16f2af124dd27","mcp_get_code":{"code_sha256":"9ee16f2af124dd27"}},{"arxiv_id":"2310.15061","paper":"/paper/the-bla-benchmark-investigating-basic","title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shin-ee-chen/BLA","path":"evaluation_models/blip2/predict.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/predict.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e564057cbee4961d","mcp_get_code":{"code_sha256":"e564057cbee4961d"}},{"arxiv_id":"2310.12790","paper":"/paper/anomaly-heterogeneity-learning-for-open-set","title":"Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mala-lab/ahl","path":"datasets/cutmix_feature_extraction.py","file_url":"https://github.com/mala-lab/ahl/blob/HEAD/datasets/cutmix_feature_extraction.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2db0fc5eaae5bc82","mcp_get_code":{"code_sha256":"2db0fc5eaae5bc82"}},{"arxiv_id":"2310.08588","paper":"/paper/octopus-embodied-vision-language-programmer","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongyh20/octopus","path":"octopus/LLaVA/predict.py","file_url":"https://github.com/dongyh20/octopus/blob/HEAD/octopus/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2310.03185","paper":"/paper/misusing-tools-in-large-language-models-with","title":"Misusing Tools in Large Language Models With Visual Adversarial Examples","date":"2023-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZihanWangKi/VLMToolMisuse","path":"model.py","file_url":"https://github.com/ZihanWangKi/VLMToolMisuse/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9df31def7420adb","mcp_get_code":{"code_sha256":"f9df31def7420adb"}},{"arxiv_id":"2310.01779","paper":"/paper/halle-switch-rethinking-and-controlling","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bronyayang/HallE_Switch","path":"eval/model_controller.py","file_url":"https://github.com/bronyayang/HallE_Switch/blob/HEAD/eval/model_controller.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2310.01506","paper":"/paper/direct-inversion-boosting-diffusion-based","title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cure-lab/directinversion","path":"run_editing_masactrl.py","file_url":"https://github.com/cure-lab/directinversion/blob/HEAD/run_editing_masactrl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"79d9960693d3111d","mcp_get_code":{"code_sha256":"79d9960693d3111d"}},{"arxiv_id":"2309.05281","paper":"/paper/class-incremental-grouping-network-for","title":"Class-Incremental Grouping Network for Continual Audio-Visual Learning","date":"2023-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stonemo/cign","path":"datasets.py","file_url":"https://github.com/stonemo/cign/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"989269e62e59af83","mcp_get_code":{"code_sha256":"989269e62e59af83"}},{"arxiv_id":"2309.03904","paper":"/paper/exploring-sparse-moe-in-gans-for-text","title":"Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis","date":"2023-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhujiapeng/aurora","path":"utils/image_utils.py","file_url":"https://github.com/zhujiapeng/aurora/blob/HEAD/utils/image_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"11932a80d2ccef24","mcp_get_code":{"code_sha256":"11932a80d2ccef24"}},{"arxiv_id":"2308.13566","paper":"/paper/mllm-dataengine-an-iterative-refinement","title":"MLLM-DataEngine: An Iterative Refinement Approach for MLLM","date":"2023-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendatalab/mllm-dataengine","path":"LLaVA/predict.py","file_url":"https://github.com/opendatalab/mllm-dataengine/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2308.08479","paper":"/paper/dedode-detect-don-t-describe-describe-don-t","title":"DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching","date":"2023-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fabio-sim/DeDoDe-ONNX-TensorRT","path":"DeDoDe/utils.py","file_url":"https://github.com/fabio-sim/DeDoDe-ONNX-TensorRT/blob/HEAD/DeDoDe/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8e8f5b59e512cdbb","mcp_get_code":{"code_sha256":"8e8f5b59e512cdbb"}},{"arxiv_id":"2308.06595","paper":"/paper/visit-bench-a-benchmark-for-vision-language","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","date":"2023-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlfoundations/VisIT-Bench","path":"baselines/llava_modeling.py","file_url":"https://github.com/mlfoundations/VisIT-Bench/blob/HEAD/baselines/llava_modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2307.10490","paper":"/paper/ab-using-images-and-sounds-for-indirect","title":"Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs","date":"2023-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ebagdasa/multimodal_injection","path":"llava/llava_injection.py","file_url":"https://github.com/ebagdasa/multimodal_injection/blob/HEAD/llava/llava_injection.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2307.07494","paper":"/paper/tall-thumbnail-layout-for-deepfake-video","title":"TALL: Thumbnail Layout for Deepfake Video Detection","date":"2023-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rainy-xu/tall4deepfake","path":"video_dataset.py","file_url":"https://github.com/rainy-xu/tall4deepfake/blob/HEAD/video_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4d43ca38bd196b3","mcp_get_code":{"code_sha256":"d4d43ca38bd196b3"}},{"arxiv_id":"2307.05898","paper":"/paper/rectifying-noisy-labels-with-sequential-prior","title":"Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation","date":"2023-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beileicui/ms-tfal","path":"generate_noise/multi_class_mask_to_multiple_one_class_mask.py","file_url":"https://github.com/beileicui/ms-tfal/blob/HEAD/generate_noise/multi_class_mask_to_multiple_one_class_mask.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"438a3262d13c4288","mcp_get_code":{"code_sha256":"438a3262d13c4288"}},{"arxiv_id":"2307.01770","paper":"/paper/fast-optimal-transport-through-sliced","title":"Fast Optimal Transport through Sliced Wasserstein Generalized Geodesics","date":"2023-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MaheyG/SWGG","path":"code/utils_ICP.py","file_url":"https://github.com/MaheyG/SWGG/blob/HEAD/code/utils_ICP.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee959ae4d23366a2","mcp_get_code":{"code_sha256":"ee959ae4d23366a2"}},{"arxiv_id":"2306.09124","paper":"/paper/diffender-diffusion-based-adversarial-defense","title":"DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kkkcx/diffender","path":"DIFFender_text_demo.py","file_url":"https://github.com/kkkcx/diffender/blob/HEAD/DIFFender_text_demo.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62369766df3c3f9a","mcp_get_code":{"code_sha256":"62369766df3c3f9a"}},{"arxiv_id":"2306.00526","paper":"/paper/layout-and-task-aware-instruction-prompt-for","title":"Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenjinw/latin-prompt","path":"utils/docvqa.py","file_url":"https://github.com/wenjinw/latin-prompt/blob/HEAD/utils/docvqa.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"db4bf2624e9f59ae","mcp_get_code":{"code_sha256":"db4bf2624e9f59ae"}},{"arxiv_id":"2305.10973","paper":"/paper/drag-your-gan-interactive-point-based","title":"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold","date":"2023-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/internchat","path":"iGPT/models/husky.py","file_url":"https://github.com/opengvlab/internchat/blob/HEAD/iGPT/models/husky.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4552e857b0cf7ef7","mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}},{"arxiv_id":"2303.10087","paper":"/paper/refinement-for-absolute-pose-regression-with","title":"Neural Refinement for Absolute Pose Regression with Feature Synthesis","date":"2023-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ActiveVisionLab/NeFeS","path":"dataset_loaders/cambridge_scenes.py","file_url":"https://github.com/ActiveVisionLab/NeFeS/blob/HEAD/dataset_loaders/cambridge_scenes.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b5a8fceac6859e6","mcp_get_code":{"code_sha256":"9b5a8fceac6859e6"}},{"arxiv_id":"2209.09341","paper":"/paper/a-simple-and-powerful-global-optimization-for","title":"A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation","date":"2022-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ponimatkin/ssl-vos","path":"generate_flow_raft.py","file_url":"https://github.com/ponimatkin/ssl-vos/blob/HEAD/generate_flow_raft.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"119d8e90bff2f749","mcp_get_code":{"code_sha256":"119d8e90bff2f749"}},{"arxiv_id":"2209.09634","paper":"/paper/a-closer-look-at-weakly-supervised-audio","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","date":"2022-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stonemo/slavc","path":"datasets.py","file_url":"https://github.com/stonemo/slavc/blob/HEAD/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"989269e62e59af83","mcp_get_code":{"code_sha256":"989269e62e59af83"}},{"arxiv_id":"2208.13721","paper":"/paper/countr-transformer-based-generalised-visual","title":"CounTR: Transformer-based Generalised Visual Counting","date":"2022-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Verg-Avesta/CounTR","path":"demo_zero.py","file_url":"https://github.com/Verg-Avesta/CounTR/blob/HEAD/demo_zero.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1f53c50f46429972","mcp_get_code":{"code_sha256":"1f53c50f46429972"}},{"arxiv_id":"2207.02696","paper":"/paper/yolov7-trainable-bag-of-freebies-sets-new","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","date":"2022-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhanghuiyao/yolov7_mindspore","path":"utils/augumentations.py","file_url":"https://github.com/zhanghuiyao/yolov7_mindspore/blob/HEAD/utils/augumentations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96c97809b6f786f8","mcp_get_code":{"code_sha256":"96c97809b6f786f8"}},{"arxiv_id":"2206.05096","paper":"/paper/skill-transfer-for-temporally-extended-task","title":"LTL-Transfer: Skill Transfer for Temporal Task Specification","date":null,"month_inferred_from_arxiv_id":"2022-06","title_source":"archive","repo":"h2r/ltl_transfer","path":"src/visualize_classifiers.py","file_url":"https://github.com/h2r/ltl_transfer/blob/HEAD/src/visualize_classifiers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"64de1d5392d1fba5","mcp_get_code":{"code_sha256":"64de1d5392d1fba5"}},{"arxiv_id":"2206.02078","paper":"/paper/straggler-resilient-personalized-federated","title":"Straggler-Resilient Personalized Federated Learning","date":"2022-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shenzebang/SRPFL","path":"my_sample.py","file_url":"https://github.com/shenzebang/SRPFL/blob/HEAD/my_sample.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91339fc6f68d3a1f","mcp_get_code":{"code_sha256":"91339fc6f68d3a1f"}},{"arxiv_id":"2205.14756","paper":"/paper/efficientvit-enhanced-linear-attention-for","title":"EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction","date":"2022-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mit-han-lab/efficientvit","path":"applications/efficientvit_sam/demo_efficientvit_sam_model.py","file_url":"https://github.com/mit-han-lab/efficientvit/blob/HEAD/applications/efficientvit_sam/demo_efficientvit_sam_model.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bb3d4f05a88ee013","mcp_get_code":{"code_sha256":"bb3d4f05a88ee013"}},{"arxiv_id":"2205.03146","paper":"/paper/clip-clop-clip-guided-collage-and","title":"CLIP-CLOP: CLIP-Guided Collage and Photomontage","date":"2022-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepmind/arnheim","path":"arnheim_3/src/video_utils.py","file_url":"https://github.com/deepmind/arnheim/blob/HEAD/arnheim_3/src/video_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"982696c5a2af8719","mcp_get_code":{"code_sha256":"982696c5a2af8719"}},{"arxiv_id":"2204.10377","paper":"/paper/contrastive-test-time-adaptation","title":"Contrastive Test-Time Adaptation","date":"2022-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DianCh/AdaContrast","path":"target.py","file_url":"https://github.com/DianCh/AdaContrast/blob/HEAD/target.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d41e65573feeba36","mcp_get_code":{"code_sha256":"d41e65573feeba36"}},{"arxiv_id":"2204.00559","paper":"/paper/dfnet-enhance-aboslute-pose-regression-with","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","date":"2022-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"activevisionlab/dfnet","path":"dataset_loaders/cambridge_scenes.py","file_url":"https://github.com/activevisionlab/dfnet/blob/HEAD/dataset_loaders/cambridge_scenes.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b5a8fceac6859e6","mcp_get_code":{"code_sha256":"9b5a8fceac6859e6"}},{"arxiv_id":"2203.12691","paper":"/paper/learning-to-generate-line-drawings-that","title":"Learning to generate line drawings that convey geometry and semantics","date":"2022-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"carolineec/informative-drawings","path":"utils_pl.py","file_url":"https://github.com/carolineec/informative-drawings/blob/HEAD/utils_pl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d363fa05027abd2","mcp_get_code":{"code_sha256":"7d363fa05027abd2"}},{"arxiv_id":"2203.12082","paper":"/paper/planemvs-3d-plane-reconstruction-from-multi","title":"PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oppo-us-research/planemvs","path":"data_preparation/pre_process.py","file_url":"https://github.com/oppo-us-research/planemvs/blob/HEAD/data_preparation/pre_process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fafa963ecd5d41cf","mcp_get_code":{"code_sha256":"fafa963ecd5d41cf"}},{"arxiv_id":"2203.11876","paper":"/paper/open-vocabulary-detr-with-conditional","title":"Open-Vocabulary DETR with Conditional Matching","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hchoi256/i-halla-v1.0","path":"utils.py","file_url":"https://github.com/hchoi256/i-halla-v1.0/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2bdfadf4cfb18cd8","mcp_get_code":{"code_sha256":"2bdfadf4cfb18cd8"}},{"arxiv_id":"2201.04127","paper":"/paper/humannerf-free-viewpoint-rendering-of-moving","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","date":"2022-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chungyiweng/humannerf","path":"core/utils/image_util.py","file_url":"https://github.com/chungyiweng/humannerf/blob/HEAD/core/utils/image_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dc4348e81c92f172","mcp_get_code":{"code_sha256":"dc4348e81c92f172"}},{"arxiv_id":"2112.05682","paper":"/paper/self-attention-does-not-need-o-n-2-memory","title":"Self-attention Does Not Need $O(n^2)$ Memory","date":"2021-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jihaonew/mm-instruct","path":"predict.py","file_url":"https://github.com/jihaonew/mm-instruct/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2112.00374","paper":"/paper/clipstyler-image-style-transfer-with-a-single","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","date":"2021-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paper11667/clipstyler","path":"train_fast.py","file_url":"https://github.com/paper11667/clipstyler/blob/HEAD/train_fast.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b173e8a151572458","mcp_get_code":{"code_sha256":"b173e8a151572458"}},{"arxiv_id":"2112.00374","paper":"/paper/clipstyler-image-style-transfer-with-a-single","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","date":"2021-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paper11667/clipstyler","path":"utils.py","file_url":"https://github.com/paper11667/clipstyler/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"47b1c768170e3fc8","mcp_get_code":{"code_sha256":"47b1c768170e3fc8"}},{"arxiv_id":"2111.07677","paper":"/paper/fastflow-unsupervised-anomaly-detection-and","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","date":"2021-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RistoranteRist/FastFlow","path":"utils.py","file_url":"https://github.com/RistoranteRist/FastFlow/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9be60eff7630c2b3","mcp_get_code":{"code_sha256":"9be60eff7630c2b3"}},{"arxiv_id":"2111.00941","paper":"/paper/turning-traffic-monitoring-cameras-into","title":"Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation","date":"2021-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zijianhu/traffic_density_estimation","path":"camera_calibration/util_files/io.py","file_url":"https://github.com/zijianhu/traffic_density_estimation/blob/HEAD/camera_calibration/util_files/io.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"89a772d7569a0da7","mcp_get_code":{"code_sha256":"89a772d7569a0da7"}},{"arxiv_id":"2110.15678","paper":"/paper/a-shading-guided-generative-implicit-model","title":"A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis","date":"2021-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingangpan/shadegan","path":"inversion.py","file_url":"https://github.com/xingangpan/shadegan/blob/HEAD/inversion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b3cb093d06a4dbf6","mcp_get_code":{"code_sha256":"b3cb093d06a4dbf6"}},{"arxiv_id":"2106.14104","paper":"/paper/an-image-classifier-can-suffice-video","title":"Can An Image Classifier Suffice For Action Recognition?","date":"2021-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/sifar-pytorch","path":"video_dataset.py","file_url":"https://github.com/ibm/sifar-pytorch/blob/HEAD/video_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d4d43ca38bd196b3","mcp_get_code":{"code_sha256":"d4d43ca38bd196b3"}},{"arxiv_id":"2104.07689","paper":"/paper/dual-contrastive-learning-for-unsupervised","title":"Dual Contrastive Learning for Unsupervised Image-to-Image Translation","date":"2021-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Deopoler/DCLGAN-Keras","path":"utils.py","file_url":"https://github.com/Deopoler/DCLGAN-Keras/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c29e9a0f14c25a2f","mcp_get_code":{"code_sha256":"c29e9a0f14c25a2f"}},{"arxiv_id":"2104.04191","paper":"/paper/si-score-an-image-dataset-for-fine-grained","title":"SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size","date":"2021-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/si-score","path":"dataset_generator.py","file_url":"https://github.com/google-research/si-score/blob/HEAD/dataset_generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4b80482911c3de43","mcp_get_code":{"code_sha256":"4b80482911c3de43"}},{"arxiv_id":"2103.15726","paper":"/paper/slimmable-compressive-autoencoders-for","title":"Slimmable Compressive Autoencoders for Practical Neural Image Compression","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FireFYF/SlimCAE","path":"SlimCAE.py","file_url":"https://github.com/FireFYF/SlimCAE/blob/HEAD/SlimCAE.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"73e536923a734076","mcp_get_code":{"code_sha256":"73e536923a734076"}},{"arxiv_id":"2008.05975","paper":"/paper/deep-learning-to-quantify-pulmonary-edema-in","title":"Deep Learning to Quantify Pulmonary Edema in Chest Radiographs","date":"2020-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RayRuizhiLiao/resnet_chestxray","path":"resnet_chestxray/model_utils.py","file_url":"https://github.com/RayRuizhiLiao/resnet_chestxray/blob/HEAD/resnet_chestxray/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"506454818ffce899","mcp_get_code":{"code_sha256":"506454818ffce899"}},{"arxiv_id":"2008.05030","paper":"/paper/how-much-should-i-trust-you-modeling","title":"Reliable Post hoc Explanations: Modeling Uncertainty in Explainability","date":"2020-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dylan-slack/modeling-uncertainty-local-explainability","path":"bayes/data_routines.py","file_url":"https://github.com/dylan-slack/modeling-uncertainty-local-explainability/blob/HEAD/bayes/data_routines.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90517ea60254868b","mcp_get_code":{"code_sha256":"90517ea60254868b"}},{"arxiv_id":"2007.01947","paper":"/paper/mining-cross-image-semantics-for-weakly","title":"Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation","date":"2020-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GuoleiSun/MCIS_wsss","path":"segmentation/examples/seg/eval_res.py","file_url":"https://github.com/GuoleiSun/MCIS_wsss/blob/HEAD/segmentation/examples/seg/eval_res.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"43515ef58eb01b2a","mcp_get_code":{"code_sha256":"43515ef58eb01b2a"}},{"arxiv_id":"2006.08381","paper":"/paper/dreamcoder-growing-generalizable","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","date":"2020-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ellisk42/ec","path":"prototypical-networks/protonet_score.py","file_url":"https://github.com/ellisk42/ec/blob/HEAD/prototypical-networks/protonet_score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"0db3e7eae4cf7eff","mcp_get_code":{"code_sha256":"0db3e7eae4cf7eff"}},{"arxiv_id":"2005.09007","paper":"/paper/u-2-net-going-deeper-with-nested-u-structure","title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","date":"2020-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RoadoneP/aloha","path":"style_utils.py","file_url":"https://github.com/RoadoneP/aloha/blob/HEAD/style_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4969a06ac02c02d2","mcp_get_code":{"code_sha256":"4969a06ac02c02d2"}},{"arxiv_id":"2005.05999","paper":"/paper/fast-deep-multi-patch-hierarchical-network","title":"Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing","date":"2020-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saikatdutta/Stacked_DMSHN_bokeh","path":"PerceptualSimilarity/util/util.py","file_url":"https://github.com/saikatdutta/Stacked_DMSHN_bokeh/blob/HEAD/PerceptualSimilarity/util/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"722a1d429018eccd","mcp_get_code":{"code_sha256":"722a1d429018eccd"}},{"arxiv_id":"2005.01004","paper":"/paper/explaining-how-deep-neural-networks-forget-by","title":"Explaining How Deep Neural Networks Forget by Deep Visualization","date":"2020-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"giangnguyen2412/dissect_catastrophic_forgetting","path":"infer.py","file_url":"https://github.com/giangnguyen2412/dissect_catastrophic_forgetting/blob/HEAD/infer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a0f14235aa1b017","mcp_get_code":{"code_sha256":"0a0f14235aa1b017"}},{"arxiv_id":"2004.10016","paper":"/paper/unsupervised-domain-adaptation-through-inter","title":"Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition","date":"2020-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MRLoghmani/relative-rotation","path":"code/data_loader.py","file_url":"https://github.com/MRLoghmani/relative-rotation/blob/HEAD/code/data_loader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"989269e62e59af83","mcp_get_code":{"code_sha256":"989269e62e59af83"}},{"arxiv_id":"2003.14407","paper":"/paper/probabilistic-pixel-adaptive-refinement","title":"Probabilistic Pixel-Adaptive Refinement Networks","date":"2020-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"visinf/ppac_refinement","path":"src/datasets/data_utils.py","file_url":"https://github.com/visinf/ppac_refinement/blob/HEAD/src/datasets/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b221b31cf1101ed6","mcp_get_code":{"code_sha256":"b221b31cf1101ed6"}},{"arxiv_id":"2003.13678","paper":"/paper/designing-network-design-spaces","title":"Designing Network Design Spaces","date":"2020-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alessiacosmos/Basic-RegNet-pytorch","path":"utils/dataset.py","file_url":"https://github.com/Alessiacosmos/Basic-RegNet-pytorch/blob/HEAD/utils/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"086239779f8ee4d5","mcp_get_code":{"code_sha256":"086239779f8ee4d5"}},{"arxiv_id":"2003.12039","paper":"/paper/raft-recurrent-all-pairs-field-transforms-for","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","date":"2020-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wpr1018001/rethinking-low-quality-optical-flow","path":"RAFT/inference_demo.py","file_url":"https://github.com/wpr1018001/rethinking-low-quality-optical-flow/blob/HEAD/RAFT/inference_demo.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c521de8b851930a","mcp_get_code":{"code_sha256":"6c521de8b851930a"}},{"arxiv_id":"2003.08685","paper":"/paper/leveraging-frequency-analysis-for-deep-fake","title":"Leveraging Frequency Analysis for Deep Fake Image Recognition","date":"2020-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RUB-SysSec/GANDCTAnalysis","path":"src/image.py","file_url":"https://github.com/RUB-SysSec/GANDCTAnalysis/blob/HEAD/src/image.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c156c4355abbec4","mcp_get_code":{"code_sha256":"8c156c4355abbec4"}},{"arxiv_id":"2001.02890","paper":"/paper/deep-plastic-surgery-robust-and-controllable","title":"Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches","date":"2020-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-group/deepps","path":"src/utils.py","file_url":"https://github.com/vita-group/deepps/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69938ee381038024","mcp_get_code":{"code_sha256":"69938ee381038024"}},{"arxiv_id":"1910.13955","paper":"/paper/ldls-3-d-object-segmentation-through-label","title":"LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images","date":"2019-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brian-h-wang/LDLS","path":"lidar_segmentation/utils.py","file_url":"https://github.com/brian-h-wang/LDLS/blob/HEAD/lidar_segmentation/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d903c7fc91f6765","mcp_get_code":{"code_sha256":"5d903c7fc91f6765"}},{"arxiv_id":"1906.07983","paper":"/paper/explanations-can-be-manipulated-and-geometry","title":"Explanations can be manipulated and geometry is to blame","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pankessel/explanations_can_be_manipulated","path":"src/nn/utils.py","file_url":"https://github.com/pankessel/explanations_can_be_manipulated/blob/HEAD/src/nn/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"edebbcde61e1bbc1","mcp_get_code":{"code_sha256":"edebbcde61e1bbc1"}},{"arxiv_id":"1906.03973","paper":"/paper/e-lpips-robust-perceptual-image-similarity","title":"E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensembles","date":"2019-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mkettune/elpips","path":"ex_bary10.py","file_url":"https://github.com/mkettune/elpips/blob/HEAD/ex_bary10.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"3e19a6296d2c7cc9","mcp_get_code":{"code_sha256":"3e19a6296d2c7cc9"}},{"arxiv_id":"1906.03973","paper":"/paper/e-lpips-robust-perceptual-image-similarity","title":"E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensembles","date":"2019-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mkettune/elpips","path":"train_dataset.py","file_url":"https://github.com/mkettune/elpips/blob/HEAD/train_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"0c9e93c8e464e175","mcp_get_code":{"code_sha256":"0c9e93c8e464e175"}},{"arxiv_id":"1905.01354","paper":"/paper/controllable-artistic-text-style-transfer-via","title":"Controllable Artistic Text Style Transfer via Shape-Matching GAN","date":"2019-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TAMU-VITA/ShapeMatchingGAN","path":"src/utils.py","file_url":"https://github.com/TAMU-VITA/ShapeMatchingGAN/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02b3c5d79d16ca7f","mcp_get_code":{"code_sha256":"02b3c5d79d16ca7f"}},{"arxiv_id":"1904.12785","paper":"/paper/190412785","title":"Style Transfer by Relaxed Optimal Transport and Self-Similarity","date":"2019-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bekkermans/style_transfer","path":"utils.py","file_url":"https://github.com/bekkermans/style_transfer/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9cbf559fc8ce1028","mcp_get_code":{"code_sha256":"9cbf559fc8ce1028"}},{"arxiv_id":"1904.06487","paper":"/paper/semi-supervised-domain-adaptation-via-minimax","title":"Semi-supervised Domain Adaptation via Minimax Entropy","date":"2019-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PrasannaPulakurthi/SPM","path":"image_list.py","file_url":"https://github.com/PrasannaPulakurthi/SPM/blob/HEAD/image_list.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d41e65573feeba36","mcp_get_code":{"code_sha256":"d41e65573feeba36"}},{"arxiv_id":"1904.01941","paper":"/paper/character-region-awareness-for-text-detection","title":"Character Region Awareness for Text Detection","date":"2019-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nunenuh/craft.pytorch","path":"craft/datasets/utils.py","file_url":"https://github.com/nunenuh/craft.pytorch/blob/HEAD/craft/datasets/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c6c3b5dabfc3b506","mcp_get_code":{"code_sha256":"c6c3b5dabfc3b506"}},{"arxiv_id":"1902.06426","paper":"/paper/2017-robotic-instrument-segmentation","title":"2017 Robotic Instrument Segmentation Challenge","date":"2019-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ternaus/robot-surgery-segmentation","path":"dataset.py","file_url":"https://github.com/ternaus/robot-surgery-segmentation/blob/HEAD/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"438a3262d13c4288","mcp_get_code":{"code_sha256":"438a3262d13c4288"}},{"arxiv_id":"1901.10277","paper":"/paper/self-supervised-deep-image-denoising","title":"High-Quality Self-Supervised Deep Image Denoising","date":"2019-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"6b60f5ef4a30c694","mcp_get_code":{"code_sha256":"6b60f5ef4a30c694"}},{"arxiv_id":"1901.01379","paper":"/paper/deep-reinforcement-learning-for-imbalanced","title":"Deep Reinforcement Learning for Imbalanced Classification","date":"2019-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Denbergvanthijs/imbDRL","path":"imbDRL/data.py","file_url":"https://github.com/Denbergvanthijs/imbDRL/blob/HEAD/imbDRL/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cc6338a2307b8a02","mcp_get_code":{"code_sha256":"cc6338a2307b8a02"}},{"arxiv_id":"1812.01803","paper":"/paper/ecc-energy-constrained-deep-neural-network","title":"ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model","date":"2018-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyang1990/energy_constrained_compression","path":"cityscapes.py","file_url":"https://github.com/hyang1990/energy_constrained_compression/blob/HEAD/cityscapes.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1c803ce4388e0644","mcp_get_code":{"code_sha256":"1c803ce4388e0644"}},{"arxiv_id":"1811.10830","paper":"/paper/from-recognition-to-cognition-visual","title":"From Recognition to Cognition: Visual Commonsense Reasoning","date":"2018-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karanchahal/play-with-vcr","path":"dataloaders/box_utils.py","file_url":"https://github.com/karanchahal/play-with-vcr/blob/HEAD/dataloaders/box_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3781075867d2d4ea","mcp_get_code":{"code_sha256":"3781075867d2d4ea"}},{"arxiv_id":"1811.10828","paper":"/paper/a-frank-wolfe-framework-for-efficient-and","title":"A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks","date":"2018-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uclaml/Frank-Wolfe-AdvML","path":"setup_resnet.py","file_url":"https://github.com/uclaml/Frank-Wolfe-AdvML/blob/HEAD/setup_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f82301bf2c63f02f","mcp_get_code":{"code_sha256":"f82301bf2c63f02f"}},{"arxiv_id":"1811.03194","paper":"/paper/ad-versarial-perceptual-ad-blocking-meets","title":"AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning","date":"2018-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ftramer/ad-versarial","path":"page-based/utils.py","file_url":"https://github.com/ftramer/ad-versarial/blob/HEAD/page-based/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b7e77d2bb35e1278","mcp_get_code":{"code_sha256":"b7e77d2bb35e1278"}},{"arxiv_id":"1808.08718","paper":"/paper/wide-activation-for-efficient-and-accurate","title":"Wide Activation for Efficient and Accurate Image Super-Resolution","date":"2018-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"krasserm/super-resolution","path":"utils.py","file_url":"https://github.com/krasserm/super-resolution/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0ab4dee93051e84f","mcp_get_code":{"code_sha256":"0ab4dee93051e84f"}},{"arxiv_id":"1806.02323","paper":"/paper/fast-and-accurate-online-video-object","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","date":"2018-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JingchunCheng/FAVOS","path":"demo/infer_davis16.py","file_url":"https://github.com/JingchunCheng/FAVOS/blob/HEAD/demo/infer_davis16.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e601b9f0b353497","mcp_get_code":{"code_sha256":"5e601b9f0b353497"}},{"arxiv_id":"1805.09817","paper":"/paper/stereo-magnification-learning-view-synthesis","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","date":"2018-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google/stereo-magnification","path":"evaluate.py","file_url":"https://github.com/google/stereo-magnification/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bb124e60d84aa001","mcp_get_code":{"code_sha256":"bb124e60d84aa001"}},{"arxiv_id":"1804.02767","paper":"/paper/yolov3-an-incremental-improvement","title":"YOLOv3: An Incremental Improvement","date":"2018-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuedongli1/yolov3_mindspore","path":"utils/augumentations.py","file_url":"https://github.com/yuedongli1/yolov3_mindspore/blob/HEAD/utils/augumentations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96c97809b6f786f8","mcp_get_code":{"code_sha256":"96c97809b6f786f8"}},{"arxiv_id":"1804.02767","paper":"/paper/yolov3-an-incremental-improvement","title":"YOLOv3: An Incremental Improvement","date":"2018-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mvxxx/mimuw-hats","path":"model/api/loader.py","file_url":"https://github.com/mvxxx/mimuw-hats/blob/HEAD/model/api/loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9568d9f06a61b755","mcp_get_code":{"code_sha256":"9568d9f06a61b755"}},{"arxiv_id":"1803.10417","paper":"/paper/the-ham10000-dataset-a-large-collection-of","title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","date":"2018-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shunk031/chainer-skin-lesion-detector","path":"src/make_dataset.py","file_url":"https://github.com/shunk031/chainer-skin-lesion-detector/blob/HEAD/src/make_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca2fbbf8fc3dc4a4","mcp_get_code":{"code_sha256":"ca2fbbf8fc3dc4a4"}},{"arxiv_id":"1803.04189","paper":"/paper/noise2noise-learning-image-restoration","title":"Noise2Noise: Learning Image Restoration without Clean Data","date":"2018-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzskyy0301/ML_PROJECT","path":"dataset_tool_tf.py","file_url":"https://github.com/zzskyy0301/ML_PROJECT/blob/HEAD/dataset_tool_tf.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6b60f5ef4a30c694","mcp_get_code":{"code_sha256":"6b60f5ef4a30c694"}},{"arxiv_id":"1711.05225","paper":"/paper/chexnet-radiologist-level-pneumonia-detection","title":"CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning","date":"2017-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Mnpr/OC-DeepLearning","path":"Utils/img_utils.py","file_url":"https://github.com/Mnpr/OC-DeepLearning/blob/HEAD/Utils/img_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc1bdcf24dd0d85e","mcp_get_code":{"code_sha256":"bc1bdcf24dd0d85e"}},{"arxiv_id":"1710.09412","paper":"/paper/mixup-beyond-empirical-risk-minimization","title":"mixup: Beyond Empirical Risk Minimization","date":"2017-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tanmaypandey7/wheat-detection","path":"utils/utils/datasets.py","file_url":"https://github.com/tanmaypandey7/wheat-detection/blob/HEAD/utils/utils/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"96c97809b6f786f8","mcp_get_code":{"code_sha256":"96c97809b6f786f8"}},{"arxiv_id":"1710.07557","paper":"/paper/real-time-convolutional-neural-networks-for","title":"Real-time Convolutional Neural Networks for Emotion and Gender Classification","date":"2017-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oarriaga/face_classification","path":"src/utils/inference.py","file_url":"https://github.com/oarriaga/face_classification/blob/HEAD/src/utils/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"09594e7b78e84cce","mcp_get_code":{"code_sha256":"09594e7b78e84cce"}},{"arxiv_id":"1709.06750","paper":"/paper/segflow-joint-learning-for-video-object","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","date":"2017-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JingchunCheng/SegFlow","path":"demo/infer_DAVIS.py","file_url":"https://github.com/JingchunCheng/SegFlow/blob/HEAD/demo/infer_DAVIS.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5b10c7ee24adc622","mcp_get_code":{"code_sha256":"5b10c7ee24adc622"}},{"arxiv_id":"1611.07865","paper":"/paper/controlling-perceptual-factors-in-neural","title":"Controlling Perceptual Factors in Neural Style Transfer","date":"2016-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"b6dd9b05db159537","mcp_get_code":{"code_sha256":"b6dd9b05db159537"}},{"arxiv_id":"1611.07004","paper":"/paper/image-to-image-translation-with-conditional","title":"Image-to-Image Translation with Conditional Adversarial Networks","date":"2016-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepware/pix2pix","path":"pix2pix.py","file_url":"https://github.com/deepware/pix2pix/blob/HEAD/pix2pix.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"36ad246b38854e59","mcp_get_code":{"code_sha256":"36ad246b38854e59"}},{"arxiv_id":"1611.07004","paper":"/paper/image-to-image-translation-with-conditional","title":"Image-to-Image Translation with Conditional Adversarial Networks","date":"2016-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nishantcoder97/cgandemo","path":"demo/image_util.py","file_url":"https://github.com/nishantcoder97/cgandemo/blob/HEAD/demo/image_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e762668bcdfb8fe","mcp_get_code":{"code_sha256":"9e762668bcdfb8fe"}},{"arxiv_id":"1611.07004","paper":"/paper/image-to-image-translation-with-conditional","title":"Image-to-Image Translation with Conditional Adversarial Networks","date":"2016-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nishantcoder97/cgandemo","path":"static/images_generator.py","file_url":"https://github.com/nishantcoder97/cgandemo/blob/HEAD/static/images_generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff63e0c2dbca4863","mcp_get_code":{"code_sha256":"ff63e0c2dbca4863"}},{"arxiv_id":"1611.07004","paper":"/paper/image-to-image-translation-with-conditional","title":"Image-to-Image Translation with Conditional Adversarial Networks","date":"2016-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sdnr1/c-gan_pix2pix","path":"initializeDataset.py","file_url":"https://github.com/sdnr1/c-gan_pix2pix/blob/HEAD/initializeDataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee206c135e00a4bc","mcp_get_code":{"code_sha256":"ee206c135e00a4bc"}},{"arxiv_id":"1611.07004","paper":"/paper/image-to-image-translation-with-conditional","title":"Image-to-Image Translation with Conditional Adversarial Networks","date":"2016-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yenchenlin/pix2pix-tensorflow","path":"utils.py","file_url":"https://github.com/yenchenlin/pix2pix-tensorflow/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4dfc2772571a07f4","mcp_get_code":{"code_sha256":"4dfc2772571a07f4"}},{"arxiv_id":"1608.04644","paper":"/paper/towards-evaluating-the-robustness-of-neural","title":"Towards Evaluating the Robustness of Neural Networks","date":"2016-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zetongqi/attacking_neural_networks","path":"CW_l2attack.py","file_url":"https://github.com/zetongqi/attacking_neural_networks/blob/HEAD/CW_l2attack.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0cb12596aa3c0436","mcp_get_code":{"code_sha256":"0cb12596aa3c0436"}},{"arxiv_id":"1607.08022","paper":"/paper/instance-normalization-the-missing-ingredient","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","date":"2016-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brightyoun/Video-Style-Transfer","path":"utils.py","file_url":"https://github.com/brightyoun/Video-Style-Transfer/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"698dca7627594fdb","mcp_get_code":{"code_sha256":"698dca7627594fdb"}},{"arxiv_id":"1606.07770","paper":"/paper/captioning-images-with-diverse-objects","title":"Captioning Images with Diverse Objects","date":"2016-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"willT97/Zero-shot-Image-Captioner","path":"noc_evaluate.py","file_url":"https://github.com/willT97/Zero-shot-Image-Captioner/blob/HEAD/noc_evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cdc30c9b4e39ad78","mcp_get_code":{"code_sha256":"cdc30c9b4e39ad78"}},{"arxiv_id":"1606.05328","paper":"/paper/conditional-image-generation-with-pixelcnn","title":"Conditional Image Generation with PixelCNN Decoders","date":"2016-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eyalbetzalel/pytorch-generative","path":"pytorch_generative/colab_utils.py","file_url":"https://github.com/eyalbetzalel/pytorch-generative/blob/HEAD/pytorch_generative/colab_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6e93d4d24f711246","mcp_get_code":{"code_sha256":"6e93d4d24f711246"}},{"arxiv_id":"1606.02147","paper":"/paper/enet-a-deep-neural-network-architecture-for","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","date":"2016-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alililia/ascend_E-NET","path":"src/eval310.py","file_url":"https://github.com/alililia/ascend_E-NET/blob/HEAD/src/eval310.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1c803ce4388e0644","mcp_get_code":{"code_sha256":"1c803ce4388e0644"}},{"arxiv_id":"1606.02147","paper":"/paper/enet-a-deep-neural-network-architecture-for","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","date":"2016-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alililia/ascend_E-NET","path":"src/dataset.py","file_url":"https://github.com/alililia/ascend_E-NET/blob/HEAD/src/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"127533b21bcc84b5","mcp_get_code":{"code_sha256":"127533b21bcc84b5"}},{"arxiv_id":"1604.07316","paper":"/paper/end-to-end-learning-for-self-driving-cars","title":"End to End Learning for Self-Driving Cars","date":"2016-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jaganadhg/tf2x_eval","path":"src/preprocess.py","file_url":"https://github.com/jaganadhg/tf2x_eval/blob/HEAD/src/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9d511f7658db9f74","mcp_get_code":{"code_sha256":"9d511f7658db9f74"}},{"arxiv_id":"1604.07316","paper":"/paper/end-to-end-learning-for-self-driving-cars","title":"End to End Learning for Self-Driving Cars","date":"2016-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jm12138/car-behavioral-cloning-paddle","path":"car/utils.py","file_url":"https://github.com/jm12138/car-behavioral-cloning-paddle/blob/HEAD/car/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b982f37276160f7e","mcp_get_code":{"code_sha256":"b982f37276160f7e"}},{"arxiv_id":"1603.08155","paper":"/paper/perceptual-losses-for-real-time-style","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","date":"2016-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gordicaleksa/pytorch-neural-style-transfer-fast","path":"utils/utils.py","file_url":"https://github.com/gordicaleksa/pytorch-neural-style-transfer-fast/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3827515ddabe45d4","mcp_get_code":{"code_sha256":"3827515ddabe45d4"}},{"arxiv_id":"1603.08155","paper":"/paper/perceptual-losses-for-real-time-style","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","date":"2016-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oneTaken/pytorch_fast_style_transfer","path":"utils.py","file_url":"https://github.com/oneTaken/pytorch_fast_style_transfer/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fad8df79e0e300cc","mcp_get_code":{"code_sha256":"fad8df79e0e300cc"}},{"arxiv_id":"1602.07868","paper":"/paper/weight-normalization-a-simple","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","date":"2016-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"krasserm/wdsr","path":"utils.py","file_url":"https://github.com/krasserm/wdsr/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0ab4dee93051e84f","mcp_get_code":{"code_sha256":"0ab4dee93051e84f"}},{"arxiv_id":"1512.04150","paper":"/paper/learning-deep-features-for-discriminative","title":"Learning Deep Features for Discriminative Localization","date":"2015-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"philipperemy/tensorflow-class-activation-mapping","path":"utils.py","file_url":"https://github.com/philipperemy/tensorflow-class-activation-mapping/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3d17be084f03b272","mcp_get_code":{"code_sha256":"3d17be084f03b272"}},{"arxiv_id":"1512.03385","paper":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamanphoebe/motiondetection","path":"custom_raft.py","file_url":"https://github.com/kamanphoebe/motiondetection/blob/HEAD/custom_raft.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c521de8b851930a","mcp_get_code":{"code_sha256":"6c521de8b851930a"}},{"arxiv_id":"1511.06335","paper":"/paper/unsupervised-deep-embedding-for-clustering","title":"Unsupervised Deep Embedding for Clustering Analysis","date":"2015-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"piiswrong/dec","path":"caffe/python/caffe/io.py","file_url":"https://github.com/piiswrong/dec/blob/HEAD/caffe/python/caffe/io.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"03ede571f838f5f3","mcp_get_code":{"code_sha256":"03ede571f838f5f3"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dstein64/pastiche","path":"pastiche/pastiche.py","file_url":"https://github.com/dstein64/pastiche/blob/HEAD/pastiche/pastiche.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6dd9b05db159537","mcp_get_code":{"code_sha256":"b6dd9b05db159537"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NateKoenig/https-github.com-Kautenja-a-neural-algorithm-of-artistic-style","path":"neural_stylization/util/img_util.py","file_url":"https://github.com/NateKoenig/https-github.com-Kautenja-a-neural-algorithm-of-artistic-style/blob/HEAD/neural_stylization/util/img_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d94e5a160f0488b5","mcp_get_code":{"code_sha256":"d94e5a160f0488b5"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Shilpil/style-transfer","path":"load_process_img.py","file_url":"https://github.com/Shilpil/style-transfer/blob/HEAD/load_process_img.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40059d7d76951964","mcp_get_code":{"code_sha256":"40059d7d76951964"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"divyanshu092/Photorealistic_Style_Transfer","path":"Code/utils.py","file_url":"https://github.com/divyanshu092/Photorealistic_Style_Transfer/blob/HEAD/Code/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77be836993cd1ffa","mcp_get_code":{"code_sha256":"77be836993cd1ffa"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gordicaleksa/pytorch-neural-style-transfer","path":"utils/utils.py","file_url":"https://github.com/gordicaleksa/pytorch-neural-style-transfer/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b0bcb02119abab6","mcp_get_code":{"code_sha256":"4b0bcb02119abab6"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"itzpankajpanwar/Style-Transfer","path":"style_transfer.py","file_url":"https://github.com/itzpankajpanwar/Style-Transfer/blob/HEAD/style_transfer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7e2780993f07583d","mcp_get_code":{"code_sha256":"7e2780993f07583d"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jtiger958/style-transfer-pytorch","path":"utils/utils.py","file_url":"https://github.com/jtiger958/style-transfer-pytorch/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff55f83b36e933d4","mcp_get_code":{"code_sha256":"ff55f83b36e933d4"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaswanthpalaghat/Implementing-Neural-Style-Transfer","path":"nst.py","file_url":"https://github.com/yaswanthpalaghat/Implementing-Neural-Style-Transfer/blob/HEAD/nst.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3cd5ad1d9a08c788","mcp_get_code":{"code_sha256":"3cd5ad1d9a08c788"}},{"arxiv_id":"1502.03044","paper":"/paper/show-attend-and-tell-neural-image-caption","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","date":"2015-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"martincss/first-captioning","path":"preprocess_encode_images.py","file_url":"https://github.com/martincss/first-captioning/blob/HEAD/preprocess_encode_images.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0bb3778f118bff1","mcp_get_code":{"code_sha256":"b0bb3778f118bff1"}},{"arxiv_id":"1411.4555","paper":"/paper/show-and-tell-a-neural-image-caption","title":"Show and Tell: A Neural Image Caption Generator","date":"2014-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Cathy-t/HELLO_image","path":"src/sample.py","file_url":"https://github.com/Cathy-t/HELLO_image/blob/HEAD/src/sample.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7eeb3c0e4ec601d","mcp_get_code":{"code_sha256":"d7eeb3c0e4ec601d"}},{"arxiv_id":"1312.6199","paper":"/paper/intriguing-properties-of-neural-networks","title":"Intriguing properties of neural networks","date":"2013-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anishathalye/neural-hash-collider","path":"util.py","file_url":"https://github.com/anishathalye/neural-hash-collider/blob/HEAD/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a49f3466e8eb1d1c","mcp_get_code":{"code_sha256":"a49f3466e8eb1d1c"}},{"arxiv_id":"ijcai2025_1122","paper":null,"title":"arXiv:ijcai2025_1122","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"mao-code/SmartSpatial","path":"utils.py","file_url":"https://github.com/mao-code/SmartSpatial/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b4387a53defbe759","mcp_get_code":{"code_sha256":"b4387a53defbe759"}},{"arxiv_id":"aaai_35495","paper":null,"title":"arXiv:aaai_35495","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"salesforce/BLIP","path":"predict.py","file_url":"https://github.com/salesforce/BLIP/blob/HEAD/predict.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"e564057cbee4961d","mcp_get_code":{"code_sha256":"e564057cbee4961d"}},{"arxiv_id":"aaai_28503","paper":null,"title":"arXiv:aaai_28503","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yuhongwei22/MFA","path":"attack/dataset.py","file_url":"https://github.com/yuhongwei22/MFA/blob/HEAD/attack/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8cb9cdaf94262270","mcp_get_code":{"code_sha256":"8cb9cdaf94262270"}},{"arxiv_id":"Zhang_On_the_Out-Of-Distribution_Generalization_of_Large_Multimodal_Models_CVPR_2025_paper","paper":null,"title":"arXiv:Zhang_On_the_Out-Of-Distribution_Generalization_of_Large_Multimodal_Models_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jiansheng-li/OOD-Generalization-of-LMMs","path":"LLaVA/predict.py","file_url":"https://github.com/jiansheng-li/OOD-Generalization-of-LMMs/blob/HEAD/LLaVA/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"Wang_Timestep-Aware_Diffusion_Model_for_Extreme_Image_Rescaling_ICCV_2025_paper","paper":null,"title":"arXiv:Wang_Timestep-Aware_Diffusion_Model_for_Extreme_Image_Rescaling_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wwangcece/TADM","path":"src/get_z.py","file_url":"https://github.com/wwangcece/TADM/blob/HEAD/src/get_z.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7b436779405da093","mcp_get_code":{"code_sha256":"7b436779405da093"}},{"arxiv_id":"Qian_Reasoning_to_Attend_Try_to_Understand_How_SEG_Token_Works_CVPR_2025_paper","paper":null,"title":"arXiv:Qian_Reasoning_to_Attend_Try_to_Understand_How_SEG_Token_Works_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"rui-qian/READ","path":"dataloaders/base_dataset.py","file_url":"https://github.com/rui-qian/READ/blob/HEAD/dataloaders/base_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2a0650029fe451f","mcp_get_code":{"code_sha256":"f2a0650029fe451f"}},{"arxiv_id":"Li_MBQ_Modality-Balanced_Quantization_for_Large_Vision-Language_Models_CVPR_2025_paper","paper":null,"title":"arXiv:Li_MBQ_Modality-Balanced_Quantization_for_Large_Vision-Language_Models_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"thu-nics/MBQ","path":"qmllm/calibration/coco_vl.py","file_url":"https://github.com/thu-nics/MBQ/blob/HEAD/qmllm/calibration/coco_vl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0921f960e75f4e82","mcp_get_code":{"code_sha256":"0921f960e75f4e82"}},{"arxiv_id":"Kwon_CLIPstyler_Image_Style_Transfer_With_a_Single_Text_Condition_CVPR_2022_paper","paper":null,"title":"arXiv:Kwon_CLIPstyler_Image_Style_Transfer_With_a_Single_Text_Condition_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cyclomon/CLIPstyler","path":"train_fast.py","file_url":"https://github.com/cyclomon/CLIPstyler/blob/HEAD/train_fast.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b173e8a151572458","mcp_get_code":{"code_sha256":"b173e8a151572458"}},{"arxiv_id":"Kwon_CLIPstyler_Image_Style_Transfer_With_a_Single_Text_Condition_CVPR_2022_paper","paper":null,"title":"arXiv:Kwon_CLIPstyler_Image_Style_Transfer_With_a_Single_Text_Condition_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cyclomon/CLIPstyler","path":"utils.py","file_url":"https://github.com/cyclomon/CLIPstyler/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"47b1c768170e3fc8","mcp_get_code":{"code_sha256":"47b1c768170e3fc8"}},{"arxiv_id":"Danish_GEOBench-VLM_Benchmarking_Vision-Language_Models_for_Geospatial_Tasks_ICCV_2025_paper","paper":null,"title":"arXiv:Danish_GEOBench-VLM_Benchmarking_Vision-Language_Models_for_Geospatial_Tasks_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"The-AI-Alliance/GEO-Bench-VLM","path":"eval_geobenchvlm/internvl_cls_single.py","file_url":"https://github.com/The-AI-Alliance/GEO-Bench-VLM/blob/HEAD/eval_geobenchvlm/internvl_cls_single.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"98f235b8bce2e606","mcp_get_code":{"code_sha256":"98f235b8bce2e606"}},{"arxiv_id":"Cao_MAPLM_A_Real-World_Large-Scale_Vision-Language_Benchmark_for_Map_and_Traffic_CVPR_2024_paper","paper":null,"title":"arXiv:Cao_MAPLM_A_Real-World_Large-Scale_Vision-Language_Benchmark_for_Map_and_Traffic_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LLVM-AD/MAPLM","path":"baseline/evaluation/inference.py","file_url":"https://github.com/LLVM-AD/MAPLM/blob/HEAD/baseline/evaluation/inference.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2025.findings-acl.979","paper":null,"title":"arXiv:2025.findings-acl.979","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Mrshenshen/FRUIT","path":"models/caption.py","file_url":"https://github.com/Mrshenshen/FRUIT/blob/HEAD/models/caption.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2025.findings-acl.359","paper":null,"title":"arXiv:2025.findings-acl.359","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"G-JWLee/TAMP","path":"predict.py","file_url":"https://github.com/G-JWLee/TAMP/blob/HEAD/predict.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2024.findings-naacl.226","paper":null,"title":"arXiv:2024.findings-naacl.226","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nguyennm1024/OSCaR","path":"llava/eval/model_vqa_qbench.py","file_url":"https://github.com/nguyennm1024/OSCaR/blob/HEAD/llava/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2024.findings-emnlp.775","paper":null,"title":"arXiv:2024.findings-emnlp.775","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YuxiXie/V-DPO","path":"llava_dpo/eval/model_vqa_qbench.py","file_url":"https://github.com/YuxiXie/V-DPO/blob/HEAD/llava_dpo/eval/model_vqa_qbench.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2024.findings-emnlp.268","paper":null,"title":"arXiv:2024.findings-emnlp.268","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HZQ950419/Math-LLaVA","path":"llava/eval/run_llava.py","file_url":"https://github.com/HZQ950419/Math-LLaVA/blob/HEAD/llava/eval/run_llava.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b3c1cb391672ccb","mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"arxiv_id":"2024.findings-acl.573","paper":null,"title":"arXiv:2024.findings-acl.573","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wenhuang2000/VHTest","path":"Evaluation/LLaVA/llava_oeq_version.py","file_url":"https://github.com/wenhuang2000/VHTest/blob/HEAD/Evaluation/LLaVA/llava_oeq_version.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bb945d226af806a7","mcp_get_code":{"code_sha256":"bb945d226af806a7"}},{"arxiv_id":"2023.findings-emnlp.268","paper":null,"title":"arXiv:2023.findings-emnlp.268","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YuxiXie/ECHo","path":"ToM_CoT_reasoning/prompt_captioning.py","file_url":"https://github.com/YuxiXie/ECHo/blob/HEAD/ToM_CoT_reasoning/prompt_captioning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8af1a0450c6ece90","mcp_get_code":{"code_sha256":"8af1a0450c6ece90"}}]}