{"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/get-abs-pos","entry":"get_abs_pos","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":15,"n_papers_ran":10,"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":9,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":15,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":1,"unverified":5},"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":"2605.18903","paper":"/paper/arxiv-2605-18903","title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"lluosi/RDB-CL","path":"ETrain/Models/Qwen/visual.py","file_url":"https://github.com/lluosi/RDB-CL/blob/HEAD/ETrain/Models/Qwen/visual.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50c4398a8645438a","mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"arxiv_id":"2504.18397","paper":"/paper/unsupervised-visual-chain-of-thought","title":"Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization","date":"2025-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kesenzhao/uv-cot","path":"omnilmm/model/omnilmm.py","file_url":"https://github.com/kesenzhao/uv-cot/blob/HEAD/omnilmm/model/omnilmm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50c4398a8645438a","mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"arxiv_id":"2504.13181","paper":"/paper/perception-encoder-the-best-visual-embeddings","title":"Perception Encoder: The best visual embeddings are not at the output of the network","date":"2025-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/perception_models","path":"apps/detection/DETA_pe/models/pev1.py","file_url":"https://github.com/facebookresearch/perception_models/blob/HEAD/apps/detection/DETA_pe/models/pev1.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":"f733619c7c9a0a40","mcp_get_code":{"code_sha256":"f733619c7c9a0a40"}},{"arxiv_id":"2501.03895","paper":"/paper/llava-mini-efficient-image-and-video-large","title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","date":"2025-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ictnlp/llava-mini","path":"llavamini/model/llavamini_arch.py","file_url":"https://github.com/ictnlp/llava-mini/blob/HEAD/llavamini/model/llavamini_arch.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b81967d61f64e430","mcp_get_code":{"code_sha256":"b81967d61f64e430"}},{"arxiv_id":"2412.13871","paper":"/paper/llava-uhd-v2-an-mllm-integrating-high","title":"LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/llava-uhd","path":"llava/model/multimodal_projector/uhd_v1_resampler.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/llava/model/multimodal_projector/uhd_v1_resampler.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":"17e90d5853a48fa7","mcp_get_code":{"code_sha256":"17e90d5853a48fa7"}},{"arxiv_id":"2411.18933","paper":"/paper/efficient-track-anything","title":"Efficient Track Anything","date":"2024-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yformer/EfficientSAM","path":"efficient_sam/efficient_sam_encoder.py","file_url":"https://github.com/yformer/EfficientSAM/blob/HEAD/efficient_sam/efficient_sam_encoder.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":"08851a6454104549","mcp_get_code":{"code_sha256":"08851a6454104549"}},{"arxiv_id":"2408.01800","paper":"/paper/2408-01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","date":"2024-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenBMB/MiniCPM-o","path":"omnilmm/model/resampler.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/omnilmm/model/resampler.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50c4398a8645438a","mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"arxiv_id":"2407.08683","paper":"/paper/seed-story-multimodal-long-story-generation","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","date":"2024-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tencentarc/seed-story","path":"src/models/qwen_visual.py","file_url":"https://github.com/tencentarc/seed-story/blob/HEAD/src/models/qwen_visual.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50c4398a8645438a","mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"arxiv_id":"2405.19298","paper":"/paper/adaptive-image-quality-assessment-via","title":"Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Q-Future/Compare2Score","path":"q_align/model/visual_encoder.py","file_url":"https://github.com/Q-Future/Compare2Score/blob/HEAD/q_align/model/visual_encoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90a8e3b4b2b4aaf0","mcp_get_code":{"code_sha256":"90a8e3b4b2b4aaf0"}},{"arxiv_id":"2405.17220","paper":"/paper/rlaif-v-aligning-mllms-through-open-source-ai","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openbmb/omnilmm","path":"omnilmm/model/resampler.py","file_url":"https://github.com/openbmb/omnilmm/blob/HEAD/omnilmm/model/resampler.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50c4398a8645438a","mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"arxiv_id":"2402.13561","paper":"/paper/cognitive-visual-language-mapper-advancing","title":"Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hitsz-tmg/cognitive-visual-language-mapper","path":"Qwen/Qwen_VL/visual.py","file_url":"https://github.com/hitsz-tmg/cognitive-visual-language-mapper/blob/HEAD/Qwen/Qwen_VL/visual.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50c4398a8645438a","mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"arxiv_id":"2401.10222","paper":"/paper/supervised-fine-tuning-in-turn-improves","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","date":"2024-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tencentarc/visft","path":"mmf/models/visft/eva_vit_g.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/eva_vit_g.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":"a3619d3754ec34c3","mcp_get_code":{"code_sha256":"a3619d3754ec34c3"}},{"arxiv_id":"2312.05251","paper":"/paper/reconstructing-hands-in-3d-with-transformers","title":"Reconstructing Hands in 3D with Transformers","date":"2023-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geopavlakos/hamer","path":"hamer/models/backbones/vit.py","file_url":"https://github.com/geopavlakos/hamer/blob/HEAD/hamer/models/backbones/vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1ffc8911891db30","mcp_get_code":{"code_sha256":"f1ffc8911891db30"}},{"arxiv_id":"2311.16922","paper":"/paper/mitigating-object-hallucinations-in-large","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/vcd","path":"experiments/Qwen_VL/visual.py","file_url":"https://github.com/damo-nlp-sg/vcd/blob/HEAD/experiments/Qwen_VL/visual.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50c4398a8645438a","mcp_get_code":{"code_sha256":"50c4398a8645438a"}},{"arxiv_id":"2303.05675","paper":"/paper/humanbench-towards-general-human-centric","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","date":"2023-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenGVLab/HumanBench","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8dc7dc2bedef1191","mcp_get_code":{"code_sha256":"8dc7dc2bedef1191"}}]}