{"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-sinusoid-encoding-table","entry":"get_sinusoid_encoding_table","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":51,"n_papers_ran":43,"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":23,"n_samples_ran":15,"n_samples_fingerprinted":11,"n_places":53,"n_places_pointer_only":17,"by_status":{"ran_honours":11,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":3,"unverified":8},"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":"2604.13307","paper":"/paper/arxiv-2604-13307","title":"Deep Spatially-Regularized and Superpixel-Based Diffusion Learning for Unsupervised Hyperspectral Image Clustering","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"vburan01/DS2DL","path":"pretrain_models.py","file_url":"https://github.com/vburan01/DS2DL/blob/HEAD/pretrain_models.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3d9050b0171c08f6","mcp_get_code":{"code_sha256":"3d9050b0171c08f6"}},{"arxiv_id":"2504.03587","paper":"/paper/autossvh-exploring-automated-frame-sampling","title":"AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing","date":"2025-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EliSpectre/CVPR25-AutoSSVH","path":"model/AutoSSVH.py","file_url":"https://github.com/EliSpectre/CVPR25-AutoSSVH/blob/HEAD/model/AutoSSVH.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5299444dd5349043","mcp_get_code":{"code_sha256":"5299444dd5349043"}},{"arxiv_id":"2501.15187","paper":"/paper/uni-sign-toward-unified-sign-language","title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","date":"2025-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zechengli19/uni-sign","path":"models.py","file_url":"https://github.com/zechengli19/uni-sign/blob/HEAD/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"672ebe50dee3907a","mcp_get_code":{"code_sha256":"672ebe50dee3907a"}},{"arxiv_id":"2412.02186","paper":"/paper/videoicl-confidence-based-iterative-in","title":"VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding","date":"2024-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kangsankim07/videoicl","path":"InternVideo/InternVideo1/Downstream/Spatial-Temporal-Action-Localization/modeling_finetune.py","file_url":"https://github.com/kangsankim07/videoicl/blob/HEAD/InternVideo/InternVideo1/Downstream/Spatial-Temporal-Action-Localization/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b2250a3d13ed688","mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"arxiv_id":"2410.05714","paper":"/paper/enhancing-temporal-modeling-of-video-llms-via","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lavi-lab/tg-vid","path":"stllm/models/utils.py","file_url":"https://github.com/lavi-lab/tg-vid/blob/HEAD/stllm/models/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2409.20537","paper":"/paper/scaling-proprioceptive-visual-learning-with","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liruiw/lerobot","path":"lerobot/common/policies/hpt/modeling_hpt.py","file_url":"https://github.com/liruiw/lerobot/blob/HEAD/lerobot/common/policies/hpt/modeling_hpt.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b7d923de2c72b94","mcp_get_code":{"code_sha256":"9b7d923de2c72b94"}},{"arxiv_id":"2409.12514","paper":"/paper/tinyvla-towards-fast-data-efficient-vision","title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","date":"2024-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyaxuanliyaxuan/TinyVLA","path":"policy_heads/models/detr_vae.py","file_url":"https://github.com/liyaxuanliyaxuan/TinyVLA/blob/HEAD/policy_heads/models/detr_vae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35f9adf6c1ae4bbd","mcp_get_code":{"code_sha256":"35f9adf6c1ae4bbd"}},{"arxiv_id":"2408.02865","paper":"/paper/2408-02865","title":"VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge","date":"2024-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HUANGLIZI/VisionUnite","path":"ImageBind/models/multimodal_preprocessors.py","file_url":"https://github.com/HUANGLIZI/VisionUnite/blob/HEAD/ImageBind/models/multimodal_preprocessors.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35a743e50e17e66d","mcp_get_code":{"code_sha256":"35a743e50e17e66d"}},{"arxiv_id":"2406.18070","paper":"/paper/egovideo-exploring-egocentric-foundation","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/egovideo","path":"eccv-2022/modeling_finetune.py","file_url":"https://github.com/opengvlab/egovideo/blob/HEAD/eccv-2022/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b2250a3d13ed688","mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"arxiv_id":"2406.07471","paper":"/paper/ophnet-a-large-scale-video-benchmark-for","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minghu0830/ophnet-benchmark","path":"baselines/task2/backbone/videomaev2/models/modeling_finetune.py","file_url":"https://github.com/minghu0830/ophnet-benchmark/blob/HEAD/baselines/task2/backbone/videomaev2/models/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2405.14700","paper":"/paper/sparse-tuning-adapting-vision-transformers","title":"Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuting20/sparse-tuning","path":"models/vit_video.py","file_url":"https://github.com/liuting20/sparse-tuning/blob/HEAD/models/vit_video.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b2250a3d13ed688","mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"arxiv_id":"2404.17176","paper":"/paper/moviechat-question-aware-sparse-memory-for","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","date":"2024-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rese1f/MovieChat","path":"MovieChat/models/multimodal_preprocessors.py","file_url":"https://github.com/rese1f/MovieChat/blob/HEAD/MovieChat/models/multimodal_preprocessors.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"35a743e50e17e66d","mcp_get_code":{"code_sha256":"35a743e50e17e66d"}},{"arxiv_id":"2404.05559","paper":"/paper/tim-a-time-interval-machine-for-audio-visual","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","date":"2024-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JacobChalk/TIM","path":"feature_extractors/VideoMAE/modeling_finetune.py","file_url":"https://github.com/JacobChalk/TIM/blob/HEAD/feature_extractors/VideoMAE/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2404.04624","paper":"/paper/bridging-the-gap-between-end-to-end-and-two","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mxin262/bridging-text-spotting","path":"adet/modeling/bridge.py","file_url":"https://github.com/mxin262/bridging-text-spotting/blob/HEAD/adet/modeling/bridge.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e270b1e0375e984c","mcp_get_code":{"code_sha256":"e270b1e0375e984c"}},{"arxiv_id":"2404.00308","paper":"/paper/st-llm-large-language-models-are-effective-1","title":"ST-LLM: Large Language Models Are Effective Temporal Learners","date":"2024-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TencentARC/ST-LLM","path":"stllm/models/utils.py","file_url":"https://github.com/TencentARC/ST-LLM/blob/HEAD/stllm/models/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2403.20254","paper":"/paper/benchmarking-the-robustness-of-temporal","title":"Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alvin-Zeng/temporal-robustness-benchmark","path":"extract_corrupted_feature_code/videomae_v2/models/modeling_finetune.py","file_url":"https://github.com/Alvin-Zeng/temporal-robustness-benchmark/blob/HEAD/extract_corrupted_feature_code/videomae_v2/models/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2403.09626","paper":"/paper/video-mamba-suite-state-space-model-as-a","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/video-mamba-suite","path":"video-mamba-suite/action-recognition/models/modeling_finetune.py","file_url":"https://github.com/opengvlab/video-mamba-suite/blob/HEAD/video-mamba-suite/action-recognition/models/modeling_finetune.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9c6fc8c1ddfbfac","mcp_get_code":{"code_sha256":"f9c6fc8c1ddfbfac"}},{"arxiv_id":"2311.18825","paper":"/paper/cast-cross-attention-in-space-and-time-for-1","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"khu-vll/cast","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"9b2250a3d13ed688","mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"arxiv_id":"2311.06231","paper":"/paper/learning-human-action-recognition","title":"Learning Human Action Recognition Representations Without Real Humans","date":"2023-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"howardzh01/ppma","path":"code/omnivision/models/vision_transformer.py","file_url":"https://github.com/howardzh01/ppma/blob/HEAD/code/omnivision/models/vision_transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"35a743e50e17e66d","mcp_get_code":{"code_sha256":"35a743e50e17e66d"}},{"arxiv_id":"2310.12973","paper":"/paper/frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziqipang/lm4visualencoding","path":"video_understanding/modeling_finetune.py","file_url":"https://github.com/ziqipang/lm4visualencoding/blob/HEAD/video_understanding/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2310.01852","paper":"/paper/languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhihaozhang97/ru-ai","path":"imagebind/models/multimodal_preprocessors.py","file_url":"https://github.com/zhihaozhang97/ru-ai/blob/HEAD/imagebind/models/multimodal_preprocessors.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35a743e50e17e66d","mcp_get_code":{"code_sha256":"35a743e50e17e66d"}},{"arxiv_id":"2309.09858","paper":"/paper/unsupervised-open-vocabulary-object","title":"Unsupervised Open-Vocabulary Object Localization in Videos","date":"2023-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/object-centric-vol","path":"models/videomae.py","file_url":"https://github.com/amazon-science/object-centric-vol/blob/HEAD/models/videomae.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2309.09431","paper":"/paper/factoformer-factorized-hyperspectral","title":"FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining","date":"2023-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csiro-robotics/factoformer","path":"pretraining/utils.py","file_url":"https://github.com/csiro-robotics/factoformer/blob/HEAD/pretraining/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"28fcf01c3871bad4","mcp_get_code":{"code_sha256":"28fcf01c3871bad4"}},{"arxiv_id":"2309.07911","paper":"/paper/disentangling-spatial-and-temporal-learning","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","date":"2023-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba-mmai-research/dist","path":"models/base/vit_video.py","file_url":"https://github.com/alibaba-mmai-research/dist/blob/HEAD/models/base/vit_video.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"790ff3bdfa86f045","mcp_get_code":{"code_sha256":"790ff3bdfa86f045"}},{"arxiv_id":"2309.00615","paper":"/paper/point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziyuguo99/point-bind_point-llm","path":"Point-LLM/ImageBind/models/multimodal_preprocessors.py","file_url":"https://github.com/ziyuguo99/point-bind_point-llm/blob/HEAD/Point-LLM/ImageBind/models/multimodal_preprocessors.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35a743e50e17e66d","mcp_get_code":{"code_sha256":"35a743e50e17e66d"}},{"arxiv_id":"2308.04549","paper":"/paper/prune-spatio-temporal-tokens-by-semantic","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","date":"2023-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mark12ding/sta","path":"model_vit.py","file_url":"https://github.com/mark12ding/sta/blob/HEAD/model_vit.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"9b2250a3d13ed688","mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"arxiv_id":"2307.02227","paper":"/paper/mae-dfer-efficient-masked-autoencoder-for","title":"MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunlicai/mae-dfer","path":"modeling_finetune.py","file_url":"https://github.com/sunlicai/mae-dfer/blob/HEAD/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b2250a3d13ed688","mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"arxiv_id":"2306.11363","paper":"/paper/masked-diffusion-models-are-fast-learners","title":"Masked Diffusion Models Are Fast Distribution Learners","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiachenlei/maskdm","path":"models/mask_uvit.py","file_url":"https://github.com/jiachenlei/maskdm/blob/HEAD/models/mask_uvit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7dff50b3dd446750","mcp_get_code":{"code_sha256":"7dff50b3dd446750"}},{"arxiv_id":"2305.16355","paper":"/paper/pandagpt-one-model-to-instruction-follow-them","title":"PandaGPT: One Model To Instruction-Follow Them All","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yxuansu/pandagpt","path":"code/model/ImageBind/models/multimodal_preprocessors.py","file_url":"https://github.com/yxuansu/pandagpt/blob/HEAD/code/model/ImageBind/models/multimodal_preprocessors.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"35a743e50e17e66d","mcp_get_code":{"code_sha256":"35a743e50e17e66d"}},{"arxiv_id":"2305.05665","paper":"/paper/imagebind-one-embedding-space-to-bind-them","title":"ImageBind: One Embedding Space To Bind Them All","date":"2023-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/imagebind","path":"imagebind/models/imagebind_model.py","file_url":"https://github.com/facebookresearch/imagebind/blob/HEAD/imagebind/models/imagebind_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d4f1ab1a5a3b3c4d","mcp_get_code":{"code_sha256":"d4f1ab1a5a3b3c4d"}},{"arxiv_id":"2304.14065","paper":"/paper/lightweight-pre-trained-transformers-for","title":"Lightweight, Pre-trained Transformers for Remote Sensing Timeseries","date":"2023-04-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nasaharvest/presto","path":"single_file_presto.py","file_url":"https://github.com/nasaharvest/presto/blob/HEAD/single_file_presto.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"68ff931ff8b48cce","mcp_get_code":{"code_sha256":"68ff931ff8b48cce"}},{"arxiv_id":"2304.14065","paper":"/paper/lightweight-pre-trained-transformers-for","title":"Lightweight, Pre-trained Transformers for Remote Sensing Timeseries","date":"2023-04-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nasaharvest/presto","path":"presto/presto.py","file_url":"https://github.com/nasaharvest/presto/blob/HEAD/presto/presto.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5e50178bfd9083d2","mcp_get_code":{"code_sha256":"5e50178bfd9083d2"}},{"arxiv_id":"2303.16198","paper":"/paper/forecasting-localized-weather-impacts-on","title":"Multi-modal learning for geospatial vegetation forecasting","date":"2023-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"earthnet2021/earthnet-models-pytorch","path":"earthnet_models_pytorch/model/contextformer.py","file_url":"https://github.com/earthnet2021/earthnet-models-pytorch/blob/HEAD/earthnet_models_pytorch/model/contextformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e8438e23b2df6a9","mcp_get_code":{"code_sha256":"3e8438e23b2df6a9"}},{"arxiv_id":"2303.16058","paper":"/paper/unmasked-teacher-towards-training-efficient","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","date":"2023-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/unmasked_teacher","path":"single_modality/action_detection/modeling_finetune.py","file_url":"https://github.com/opengvlab/unmasked_teacher/blob/HEAD/single_modality/action_detection/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2302.14042","paper":"/paper/knowledge-enhanced-pre-training-for-auto","title":"Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaoman-zhang/kad","path":"A3_CLIP/models/vit.py","file_url":"https://github.com/xiaoman-zhang/kad/blob/HEAD/A3_CLIP/models/vit.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b2250a3d13ed688","mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"arxiv_id":"2212.04636","paper":"/paper/ego-body-pose-estimation-via-ego-head-pose","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","date":"2022-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lijiaman/egoego_release","path":"egoego/model/transformer_module.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/transformer_module.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38165c64626f844a","mcp_get_code":{"code_sha256":"38165c64626f844a"}},{"arxiv_id":"2208.07049","paper":"/paper/self-supervised-vision-transformers-for","title":"Self-Supervised Vision Transformers for Malware Detection","date":"2022-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sachith500/sherlock","path":"modeling_finetune.py","file_url":"https://github.com/sachith500/sherlock/blob/HEAD/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b2250a3d13ed688","mcp_get_code":{"code_sha256":"9b2250a3d13ed688"}},{"arxiv_id":"2203.14415","paper":"/paper/mugs-a-multi-granular-self-supervised","title":"Mugs: A Multi-Granular Self-Supervised Learning Framework","date":"2022-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/mugs","path":"eval/eval_finetuning/model_for_finetuning.py","file_url":"https://github.com/sail-sg/mugs/blob/HEAD/eval/eval_finetuning/model_for_finetuning.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":"a45ecd9b366b453e","mcp_get_code":{"code_sha256":"a45ecd9b366b453e"}},{"arxiv_id":"2203.12602","paper":"/paper/videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MCG-NJU/VideoMAE-Action-Detection","path":"modeling_finetune.py","file_url":"https://github.com/MCG-NJU/VideoMAE-Action-Detection/blob/HEAD/modeling_finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"da651e3979a18f84","mcp_get_code":{"code_sha256":"da651e3979a18f84"}},{"arxiv_id":"2109.15166","paper":"/paper/portaspeech-portable-and-high-quality","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","date":"2021-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/PortaSpeech","path":"model/linguistic_encoder.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/model/linguistic_encoder.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"arxiv_id":"2106.03153","paper":"/paper/meta-stylespeech-multi-speaker-adaptive-text","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","date":"2021-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/StyleSpeech","path":"model/modules.py","file_url":"https://github.com/keonlee9420/StyleSpeech/blob/HEAD/model/modules.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"arxiv_id":"2103.14574","paper":"/paper/parallel-tacotron-2-a-non-autoregressive","title":"Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling","date":null,"month_inferred_from_arxiv_id":"2021-03","title_source":"archive","repo":"keonlee9420/Cross-Speaker-Emotion-Transfer","path":"model/modules.py","file_url":"https://github.com/keonlee9420/Cross-Speaker-Emotion-Transfer/blob/HEAD/model/modules.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"arxiv_id":"2006.06873","paper":"/paper/fastpitch-parallel-text-to-speech-with-pitch","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/FastPitchFormant","path":"model/modules.py","file_url":"https://github.com/keonlee9420/FastPitchFormant/blob/HEAD/model/modules.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"arxiv_id":"2006.04558","paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mtresearcher/FastSpeech2","path":"transformer/Models.py","file_url":"https://github.com/mtresearcher/FastSpeech2/blob/HEAD/transformer/Models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"arxiv_id":"2002.03079","paper":"/paper/blank-language-models","title":"Blank Language Models","date":"2020-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Varal7/blank_language_model","path":"transformer/Models.py","file_url":"https://github.com/Varal7/blank_language_model/blob/HEAD/transformer/Models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"arxiv_id":"1911.07757","paper":"/paper/satellite-image-time-series-classification","title":"Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention","date":"2019-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maja601/pytorch-psetae","path":"models/tae.py","file_url":"https://github.com/maja601/pytorch-psetae/blob/HEAD/models/tae.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"49a272e908e62940","mcp_get_code":{"code_sha256":"49a272e908e62940"}},{"arxiv_id":"1910.02481","paper":"/paper/learn-to-explain-efficiently-via-neural-logic","title":"Learn to Explain Efficiently via Neural Logic Inductive Learning","date":"2019-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gblackout/NLIL","path":"model/Models.py","file_url":"https://github.com/gblackout/NLIL/blob/HEAD/model/Models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huanghonggit/Mask-Language-Model","path":"model/bert.py","file_url":"https://github.com/huanghonggit/Mask-Language-Model/blob/HEAD/model/bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dcca3917b85d56dc","mcp_get_code":{"code_sha256":"dcca3917b85d56dc"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Matthewdowney18/Transformer_Dialogue","path":"src/transformer/Models.py","file_url":"https://github.com/Matthewdowney18/Transformer_Dialogue/blob/HEAD/src/transformer/Models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graykode/nlp-tutorial","path":"5-1.Transformer/Transformer.py","file_url":"https://github.com/graykode/nlp-tutorial/blob/HEAD/5-1.Transformer/Transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"138cf0fec8960156","mcp_get_code":{"code_sha256":"138cf0fec8960156"}},{"arxiv_id":"Zheng_CO2-Net_A_Physics-Informed_Spatio-Temporal_Model_for_Global_Surface_CO2_Reconstruction_ICCV_2025_paper","paper":null,"title":"arXiv:Zheng_CO2-Net_A_Physics-Informed_Spatio-Temporal_Model_for_Global_Surface_CO2_Reconstruction_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Leamonz/CORE","path":"models/spatial_expert.py","file_url":"https://github.com/Leamonz/CORE/blob/HEAD/models/spatial_expert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35a743e50e17e66d","mcp_get_code":{"code_sha256":"35a743e50e17e66d"}},{"arxiv_id":"2023.findings-emnlp.672","paper":null,"title":"arXiv:2023.findings-emnlp.672","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"guihuzhang/FactSpotter","path":"g2t_gen_code/code/modeling_kgpt.py","file_url":"https://github.com/guihuzhang/FactSpotter/blob/HEAD/g2t_gen_code/code/modeling_kgpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38165c64626f844a","mcp_get_code":{"code_sha256":"38165c64626f844a"}},{"arxiv_id":"2020.emnlp-main.697","paper":null,"title":"arXiv:2020.emnlp-main.697","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wenhuchen/KGPT","path":"code/Model.py","file_url":"https://github.com/wenhuchen/KGPT/blob/HEAD/code/Model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f8f22937463d3c5","mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}}]}