{"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/clip-loss","entry":"clip_loss","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":35,"n_papers_ran":18,"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":19,"n_samples_ran":14,"n_samples_fingerprinted":11,"n_places":36,"n_places_pointer_only":17,"by_status":{"ran_honours":1,"ran_violates":1,"ran_draft_wrong":7,"ran_fixture":1,"ran":4,"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":"2608.20382","paper":"/paper/arxiv-2608-20382","title":"Decoupled Vision-Language System for Multimodal Understanding and Generation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"YifanXu74/Libra","path":"libra/models/clip/modeling_clip.py","file_url":"https://github.com/YifanXu74/Libra/blob/HEAD/libra/models/clip/modeling_clip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2607.09126","paper":"/paper/arxiv-2607-09126","title":"VTaMo: Video-Text Alignment Model for Sign Language Translation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"junyi2005/vtamo","path":"vtamo/clip_loss.py","file_url":"https://github.com/junyi2005/vtamo/blob/HEAD/vtamo/clip_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8892fce2748859a1","mcp_get_code":{"code_sha256":"8892fce2748859a1"}},{"arxiv_id":"2605.00800","paper":"/paper/arxiv-2605-00800","title":"Generating Statistical Charts with Validation-Driven LLM Workflows","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"pavlin-policar/llm-chart-generation","path":"generation_pipeline/model_scripts/0_train_vit_clip.py","file_url":"https://github.com/pavlin-policar/llm-chart-generation/blob/HEAD/generation_pipeline/model_scripts/0_train_vit_clip.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":"89367cb0848f8519","mcp_get_code":{"code_sha256":"89367cb0848f8519"}},{"arxiv_id":"2510.14741","paper":"/paper/arxiv-2510-14741","title":"DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"perceivelab/dexter","path":"dexter/models/modeling_clip.py","file_url":"https://github.com/perceivelab/dexter/blob/HEAD/dexter/models/modeling_clip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2509.03897","paper":"/paper/arxiv-2509-03897","title":"SPECS: Specificity-Enhanced CLIPScore for Long Image Caption Evaluation","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"mbzuai-nlp/SPECS","path":"model/model_spec.py","file_url":"https://github.com/mbzuai-nlp/SPECS/blob/HEAD/model/model_spec.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"11ea502213a91170","mcp_get_code":{"code_sha256":"11ea502213a91170"}},{"arxiv_id":"2507.06210","paper":"/paper/cultureclip-empowering-clip-with-cultural","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","date":"2025-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lukahhcm/cultureclip","path":"model_finetune/loss.py","file_url":"https://github.com/lukahhcm/cultureclip/blob/HEAD/model_finetune/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1d31de1c8207e447","mcp_get_code":{"code_sha256":"1d31de1c8207e447"}},{"arxiv_id":"2505.05071","paper":"/paper/fg-clip-fine-grained-visual-and-textual","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","date":"2025-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"360CVGroup/FG-CLIP","path":"fgclip2/model/strcs/fgclip2.py","file_url":"https://github.com/360CVGroup/FG-CLIP/blob/HEAD/fgclip2/model/strcs/fgclip2.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":"e8c40917a9682d02","mcp_get_code":{"code_sha256":"e8c40917a9682d02"}},{"arxiv_id":"2503.17782","paper":"/paper/goal-global-local-object-alignment-learning","title":"GOAL: Global-local Object Alignment Learning","date":"2025-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PerceptualAI-Lab/GOAL","path":"goal.py","file_url":"https://github.com/PerceptualAI-Lab/GOAL/blob/HEAD/goal.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1591524e14c110fe","mcp_get_code":{"code_sha256":"1591524e14c110fe"}},{"arxiv_id":"2503.11367","paper":"/paper/cornstarch-distributed-multimodal-training","title":"Cornstarch: Distributed Multimodal Training Must Be Multimodality-Aware","date":null,"month_inferred_from_arxiv_id":"2025-03","title_source":"archive","repo":"cornstarch-org/Cornstarch","path":"cornstarch/models/evaclip/modeling_evaclip.py","file_url":"https://github.com/cornstarch-org/Cornstarch/blob/HEAD/cornstarch/models/evaclip/modeling_evaclip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2502.11431","paper":"/paper/any-information-is-just-worth-one-single","title":"Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VectorSpaceLab/MegaPairs","path":"modeling_MMRet_CLIP.py","file_url":"https://github.com/VectorSpaceLab/MegaPairs/blob/HEAD/modeling_MMRet_CLIP.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"198ed04eaf39466a","mcp_get_code":{"code_sha256":"198ed04eaf39466a"}},{"arxiv_id":"2411.00683","paper":"/paper/taxabind-a-unified-embedding-space-for","title":"TaxaBind: A Unified Embedding Space for Ecological Applications","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mvrl/taxabind","path":"TaxaBind/EnvBind/model.py","file_url":"https://github.com/mvrl/taxabind/blob/HEAD/TaxaBind/EnvBind/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"29a311684e27a509","mcp_get_code":{"code_sha256":"29a311684e27a509"}},{"arxiv_id":"2410.22149","paper":"/paper/capacity-control-is-an-effective-memorization","title":"Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raman1121/diffusion_memorization_hpo","path":"difffit/modeling_clip.py","file_url":"https://github.com/raman1121/diffusion_memorization_hpo/blob/HEAD/difffit/modeling_clip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2410.07157","paper":"/paper/instructg2i-synthesizing-images-from","title":"InstructG2I: Synthesizing Images from Multimodal Attributed Graphs","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PeterGriffinJin/InstructG2I","path":"instructg2i/GraphQFormer.py","file_url":"https://github.com/PeterGriffinJin/InstructG2I/blob/HEAD/instructg2i/GraphQFormer.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2410.03176","paper":"/paper/investigating-and-mitigating-object","title":"Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yufang-Liu/clip_hallucination","path":"finetune_clip/modeling_clip.py","file_url":"https://github.com/Yufang-Liu/clip_hallucination/blob/HEAD/finetune_clip/modeling_clip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2409.19961","paper":"/paper/multimodal-llm-enhanced-cross-lingual-cross","title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lijiabei-7/leccr","path":"LECCR/models/clip_vit.py","file_url":"https://github.com/lijiabei-7/leccr/blob/HEAD/LECCR/models/clip_vit.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":"e5b89b1f72c319ed","mcp_get_code":{"code_sha256":"e5b89b1f72c319ed"}},{"arxiv_id":"2409.19865","paper":"/paper/tokenbinder-text-video-retrieval-with-one-to","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bingqingzhang/TokenBinder","path":"src/modeling/CLIP.py","file_url":"https://github.com/bingqingzhang/TokenBinder/blob/HEAD/src/modeling/CLIP.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5b89b1f72c319ed","mcp_get_code":{"code_sha256":"e5b89b1f72c319ed"}},{"arxiv_id":"2409.15657","paper":"/paper/mmpt-multimodal-prompt-tuning-for-zero-shot","title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","date":"2024-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"william-wang618/m2pt","path":"M2PT/model/llava_archPT.py","file_url":"https://github.com/william-wang618/m2pt/blob/HEAD/M2PT/model/llava_archPT.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"017dd63ed48e15f1","mcp_get_code":{"code_sha256":"017dd63ed48e15f1"}},{"arxiv_id":"2408.16829","paper":"/paper/maven-a-multimodal-foundation-model-for","title":"Maven: A Multimodal Foundation Model for Supernova Science","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thomashelfer/multimodal-supernovae","path":"src/loss.py","file_url":"https://github.com/thomashelfer/multimodal-supernovae/blob/HEAD/src/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca4c88ac11df70b3","mcp_get_code":{"code_sha256":"ca4c88ac11df70b3"}},{"arxiv_id":"2405.10140","paper":"/paper/libra-building-decoupled-vision-system-on","title":"Libra: Building Decoupled Vision System on Large Language Models","date":"2024-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifanxu74/libra","path":"libra/models/clip/modeling_clip.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/clip/modeling_clip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2403.06659","paper":"/paper/zero-shot-ecg-classification-with-multimodal","title":"Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cheliu-computation/merl","path":"utils/utils_loss.py","file_url":"https://github.com/cheliu-computation/merl/blob/HEAD/utils/utils_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19c632192cb40d5c","mcp_get_code":{"code_sha256":"19c632192cb40d5c"}},{"arxiv_id":"2402.10404","paper":"/paper/explaining-generative-diffusion-models-via","title":"Explaining generative diffusion models via visual analysis for interpretable decision-making process","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ian-jihoonpark/X-Diffusion","path":"models/clip_encoder.py","file_url":"https://github.com/ian-jihoonpark/X-Diffusion/blob/HEAD/models/clip_encoder.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2312.03781","paper":"/paper/lite-mind-towards-efficient-and-versatile","title":"Lite-Mind: Towards Efficient and Robust Brain Representation Network","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gongzix/lite-mind","path":"src/engine.py","file_url":"https://github.com/gongzix/lite-mind/blob/HEAD/src/engine.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"507ba10a0f424439","mcp_get_code":{"code_sha256":"507ba10a0f424439"}},{"arxiv_id":"2312.01522","paper":"/paper/g2d-from-global-to-dense-radiography","title":"G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training","date":"2023-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cheliu-computation/g2d-neurips24","path":"PRETRAIN/utils/loss.py","file_url":"https://github.com/cheliu-computation/g2d-neurips24/blob/HEAD/PRETRAIN/utils/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"19c632192cb40d5c","mcp_get_code":{"code_sha256":"19c632192cb40d5c"}},{"arxiv_id":"2309.16429","paper":"/paper/diverse-and-aligned-audio-to-video-generation","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guyyariv/TempoTokens","path":"modules/text_encoder/modeling_clip_tempotokens.py","file_url":"https://github.com/guyyariv/TempoTokens/blob/HEAD/modules/text_encoder/modeling_clip_tempotokens.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2306.08183","paper":"/paper/zeroforge-feedforward-text-to-shape-without","title":"ZeroForge: Feedforward Text-to-Shape Without 3D Supervision","date":"2023-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"km3888/zeroforge","path":"zf_training.py","file_url":"https://github.com/km3888/zeroforge/blob/HEAD/zf_training.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc8b8865eb2b1f91","mcp_get_code":{"code_sha256":"cc8b8865eb2b1f91"}},{"arxiv_id":"2306.02583","paper":"/paper/stable-diffusion-is-unstable-1","title":"Stable Diffusion is Unstable","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"duchengbin8/Stable_Diffusion_is_Unstable","path":"m_clip.py","file_url":"https://github.com/duchengbin8/Stable_Diffusion_is_Unstable/blob/HEAD/m_clip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2305.13050","paper":"/paper/audiotoken-adaptation-of-text-conditioned-1","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guyyariv/AudioToken","path":"modules/clip_text_model/modeling_clip.py","file_url":"https://github.com/guyyariv/AudioToken/blob/HEAD/modules/clip_text_model/modeling_clip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2210.07795","paper":"/paper/efficientvlm-fast-and-accurate-vision","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"swaggy-tn/efficientvlm","path":"efficient_models/eff_vit.py","file_url":"https://github.com/swaggy-tn/efficientvlm/blob/HEAD/efficient_models/eff_vit.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"e5b89b1f72c319ed","mcp_get_code":{"code_sha256":"e5b89b1f72c319ed"}},{"arxiv_id":"2210.00312","paper":"/paper/multimodal-analogical-reasoning-over","title":"Multimodal Analogical Reasoning over Knowledge Graphs","date":"2022-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/MKGformer","path":"MKG/models/modeling_clip.py","file_url":"https://github.com/zjunlp/MKGformer/blob/HEAD/MKG/models/modeling_clip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5b89b1f72c319ed","mcp_get_code":{"code_sha256":"e5b89b1f72c319ed"}},{"arxiv_id":"2210.00312","paper":"/paper/multimodal-analogical-reasoning-over","title":"Multimodal Analogical Reasoning over Knowledge Graphs","date":"2022-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/MKG_Analogy","path":"MarT/models/modeling_clip.py","file_url":"https://github.com/zjunlp/MKG_Analogy/blob/HEAD/MarT/models/modeling_clip.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1aa7f7b75b2418fa","mcp_get_code":{"code_sha256":"1aa7f7b75b2418fa"}},{"arxiv_id":"2209.06430","paper":"/paper/clip-vip-adapting-pre-trained-image-text","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","date":"2022-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/xpretrain","path":"CLIP-ViP/src/modeling/CLIP_ViP.py","file_url":"https://github.com/microsoft/xpretrain/blob/HEAD/CLIP-ViP/src/modeling/CLIP_ViP.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e5b89b1f72c319ed","mcp_get_code":{"code_sha256":"e5b89b1f72c319ed"}},{"arxiv_id":"2206.00621","paper":"/paper/cross-view-language-modeling-towards-unified","title":"Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training","date":"2022-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zengyan-97/cclm","path":"models/clip_vit.py","file_url":"https://github.com/zengyan-97/cclm/blob/HEAD/models/clip_vit.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"e5b89b1f72c319ed","mcp_get_code":{"code_sha256":"e5b89b1f72c319ed"}},{"arxiv_id":"2203.03897","paper":"/paper/geodesic-multi-modal-mixup-for-robust-fine","title":"Geodesic Multi-Modal Mixup for Robust Fine-Tuning","date":"2022-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"changdaeoh/multimodal-mixup","path":"loss.py","file_url":"https://github.com/changdaeoh/multimodal-mixup/blob/HEAD/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cb73c26e3ce88785","mcp_get_code":{"code_sha256":"cb73c26e3ce88785"}},{"arxiv_id":"2012.12469","paper":"/paper/augmenting-policy-learning-with-routines","title":"Augmenting Policy Learning with Routines Discovered from a Single Demonstration","date":"2020-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjtuytc/AAAI21-RoutineAugmentedPolicyLearning","path":"torchrl_with_routines/algo/a2c.py","file_url":"https://github.com/sjtuytc/AAAI21-RoutineAugmentedPolicyLearning/blob/HEAD/torchrl_with_routines/algo/a2c.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c89cc9faf6bdbd1","mcp_get_code":{"code_sha256":"7c89cc9faf6bdbd1"}},{"arxiv_id":"aaai_28565","paper":null,"title":"arXiv:aaai_28565","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zhangxulu1996/Compositional-Inversion","path":"model/modeling_clip.py","file_url":"https://github.com/zhangxulu1996/Compositional-Inversion/blob/HEAD/model/modeling_clip.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2ca34eca05d40cd","mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"arxiv_id":"2024.findings-emnlp.965","paper":null,"title":"arXiv:2024.findings-emnlp.965","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Chauncey-Jheng/PCRL-MRG","path":"llama_recipes/models/PCRL_llama/modeling_PCRL_llama.py","file_url":"https://github.com/Chauncey-Jheng/PCRL-MRG/blob/HEAD/llama_recipes/models/PCRL_llama/modeling_PCRL_llama.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":"9cebce9bbb39f3de","mcp_get_code":{"code_sha256":"9cebce9bbb39f3de"}}]}