{"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-1d-sincos-pos-embed-from-grid","entry":"get_1d_sincos_pos_embed_from_grid","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":75,"n_papers_ran":57,"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":21,"n_samples_ran":14,"n_samples_fingerprinted":14,"n_places":77,"n_places_pointer_only":34,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":9,"ran":4,"unverified":7},"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":"2608.01298","paper":"/paper/arxiv-2608-01298","title":"UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"JN-Yun/UDT","path":"models/UDT.py","file_url":"https://github.com/JN-Yun/UDT/blob/HEAD/models/UDT.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b75bf9ed4e14ba7","mcp_get_code":{"code_sha256":"7b75bf9ed4e14ba7"}},{"arxiv_id":"2606.08414","paper":"/paper/arxiv-2606-08414","title":"PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"thu-ml/RDT2","path":"models/rdt/model.py","file_url":"https://github.com/thu-ml/RDT2/blob/HEAD/models/rdt/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"06a688b14731d363","mcp_get_code":{"code_sha256":"06a688b14731d363"}},{"arxiv_id":"2606.08063","paper":"/paper/arxiv-2606-08063","title":"Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jqtangust/Robust-U1","path":"modeling/modeling/bagel/modeling_utils.py","file_url":"https://github.com/jqtangust/Robust-U1/blob/HEAD/modeling/modeling/bagel/modeling_utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2606.06164","paper":"/paper/arxiv-2606-06164","title":"On the training of physics-informed neural operators for solving parametric partial differential equations","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"NanxiiChen/PI-CViT","path":"models/cvit.py","file_url":"https://github.com/NanxiiChen/PI-CViT/blob/HEAD/models/cvit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4814373f5d9ccbcc","mcp_get_code":{"code_sha256":"4814373f5d9ccbcc"}},{"arxiv_id":"2605.15284","paper":"/paper/arxiv-2605-15284","title":"Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"tum-pbs/tadpole","path":"tadpole/architecture/downstream/llm.py","file_url":"https://github.com/tum-pbs/tadpole/blob/HEAD/tadpole/architecture/downstream/llm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7387c0fc16222bac","mcp_get_code":{"code_sha256":"7387c0fc16222bac"}},{"arxiv_id":"2605.08724","paper":"/paper/arxiv-2605-08724","title":"SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"piooip/SynerMedGen","path":"modeling/bagel/modeling_utils.py","file_url":"https://github.com/piooip/SynerMedGen/blob/HEAD/modeling/bagel/modeling_utils.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":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2603.01759","paper":"/paper/arxiv-2603-01759","title":"Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"doem97/metalora","path":"models/satmae_vit.py","file_url":"https://github.com/doem97/metalora/blob/HEAD/models/satmae_vit.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":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2602.02603","paper":"/paper/arxiv-2602-02603","title":"EchoJEPA: A Latent Predictive Foundation Model for Echocardiography","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"bowang-lab/EchoJEPA","path":"src/models/predictor.py","file_url":"https://github.com/bowang-lab/EchoJEPA/blob/HEAD/src/models/predictor.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f6dd6f9161d38af6","mcp_get_code":{"code_sha256":"f6dd6f9161d38af6"}},{"arxiv_id":"2601.11522","paper":"/paper/arxiv-2601-11522","title":"UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ZrH42/UniX","path":"modeling/unix/modeling_utils.py","file_url":"https://github.com/ZrH42/UniX/blob/HEAD/modeling/unix/modeling_utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2508.07626","paper":"/paper/arxiv-2508-07626","title":"AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"idejie/ar","path":"models/ar/transformer_utils.py","file_url":"https://github.com/idejie/ar/blob/HEAD/models/ar/transformer_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"77d61c6dcc6c0625","mcp_get_code":{"code_sha256":"77d61c6dcc6c0625"}},{"arxiv_id":"2508.05606","paper":"/paper/arxiv-2508-05606","title":"Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Fr0zenCrane/UniCoT","path":"modeling/bagel/modeling_utils.py","file_url":"https://github.com/Fr0zenCrane/UniCoT/blob/HEAD/modeling/bagel/modeling_utils.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":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2507.04447","paper":"/paper/dreamvla-a-vision-language-action-model-1","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","date":"2025-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zhangwenyao1/DreamVLA","path":"models/dreamvla_model.py","file_url":"https://github.com/Zhangwenyao1/DreamVLA/blob/HEAD/models/dreamvla_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"2506.21803","paper":null,"title":"arXiv:2506.21803","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"HKU-MedAI/MELP","path":"src/melp/backbone/pos_embed.py","file_url":"https://github.com/HKU-MedAI/MELP/blob/HEAD/src/melp/backbone/pos_embed.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2506.16504","paper":"/paper/hunyuan3d-2-5-towards-high-fidelity-3d-assets","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","date":"2025-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tencent/hunyuan3d-2","path":"hy3dgen/shapegen/models/conditioner.py","file_url":"https://github.com/tencent/hunyuan3d-2/blob/HEAD/hy3dgen/shapegen/models/conditioner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7700f3428f58afbe","mcp_get_code":{"code_sha256":"7700f3428f58afbe"}},{"arxiv_id":"2506.13750","paper":"/paper/test3r-learning-to-reconstruct-3d-at-test","title":"Test3R: Learning to Reconstruct 3D at Test Time","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nopqaq/test3r","path":"croco/models/pos_embed.py","file_url":"https://github.com/nopqaq/test3r/blob/HEAD/croco/models/pos_embed.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2506.11777","paper":"/paper/self-supervised-learning-of-echocardiographic","title":"Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation","date":"2025-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mdivyanshu97/discovr","path":"models/modeling_pretrain.py","file_url":"https://github.com/mdivyanshu97/discovr/blob/HEAD/models/modeling_pretrain.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"44aacaf688b398e0","mcp_get_code":{"code_sha256":"44aacaf688b398e0"}},{"arxiv_id":"2505.14683","paper":"/paper/emerging-properties-in-unified-multimodal","title":"Emerging Properties in Unified Multimodal Pretraining","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neverbiasu/ComfyUI-BAGEL","path":"modeling/bagel/modeling_utils.py","file_url":"https://github.com/neverbiasu/ComfyUI-BAGEL/blob/HEAD/modeling/bagel/modeling_utils.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":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2504.12576","paper":"/paper/cm3ae-a-unified-rgb-frame-and-event-voxel","title":"CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework","date":"2025-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"event-ahu/cm3ae","path":"pos_embed.py","file_url":"https://github.com/event-ahu/cm3ae/blob/HEAD/pos_embed.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2503.18746","paper":"/paper/linguistics-aware-masked-image-modeling-for","title":"Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition","date":"2025-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangyifei01/LMIM","path":"lmim_pretrain/models_lmim.py","file_url":"https://github.com/zhangyifei01/LMIM/blob/HEAD/lmim_pretrain/models_lmim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2501.03575","paper":"/paper/cosmos-world-foundation-model-platform-for","title":"Cosmos World Foundation Model Platform for Physical AI","date":"2025-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nvidia-cosmos/cosmos-predict1","path":"cosmos_predict1/autoregressive/modules/embedding.py","file_url":"https://github.com/nvidia-cosmos/cosmos-predict1/blob/HEAD/cosmos_predict1/autoregressive/modules/embedding.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":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2412.15109","paper":"/paper/predictive-inverse-dynamics-models-are","title":"Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation","date":null,"month_inferred_from_arxiv_id":"2024-12","title_source":"archive","repo":"openrobotlab/seer","path":"models/seer_model.py","file_url":"https://github.com/openrobotlab/seer/blob/HEAD/models/seer_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":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"2412.12095","paper":"/paper/causal-diffusion-transformers-for-generative","title":"Causal Diffusion Transformers for Generative Modeling","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2411.16969","paper":"/paper/zoomldm-latent-diffusion-model-for-multi","title":"ZoomLDM: Latent Diffusion Model for multi-scale image generation","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvlab-stonybrook/ZoomLDM","path":"cdm_dit/models.py","file_url":"https://github.com/cvlab-stonybrook/ZoomLDM/blob/HEAD/cdm_dit/models.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2411.12164","paper":"/paper/urbandit-a-foundation-model-for-open-world","title":"UrbanDiT: A Foundation Model for Open-World Urban Spatio-Temporal Learning","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsinghua-fib-lab/UrbanDiT","path":"src/Embed.py","file_url":"https://github.com/tsinghua-fib-lab/UrbanDiT/blob/HEAD/src/Embed.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"2411.11409","paper":"/paper/ikea-manuals-at-work-4d-grounding-of-assembly","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yunongLiu1/IKEA-Manuals-at-Work","path":"src/IKEAVideo/featurizers/MAE.py","file_url":"https://github.com/yunongLiu1/IKEA-Manuals-at-Work/blob/HEAD/src/IKEAVideo/featurizers/MAE.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2411.01842","paper":"/paper/elastst-towards-robust-varied-horizon","title":"ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/ProbTS","path":"probts/utils/position_emb.py","file_url":"https://github.com/microsoft/ProbTS/blob/HEAD/probts/utils/position_emb.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2410.09575","paper":"/paper/reconstructive-visual-instruction-tuning","title":"Reconstructive Visual Instruction Tuning","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haochen-wang409/ross","path":"ross/model/utils.py","file_url":"https://github.com/haochen-wang409/ross/blob/HEAD/ross/model/utils.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":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"2409.17808","paper":"/paper/generative-modeling-of-molecular-dynamics","title":"Generative Modeling of Molecular Dynamics Trajectories","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bjing2016/mdgen","path":"mdgen/model/latent_model.py","file_url":"https://github.com/bjing2016/mdgen/blob/HEAD/mdgen/model/latent_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2409.16280","paper":"/paper/monoformer-one-transformer-for-both-diffusion","title":"MonoFormer: One Transformer for Both Diffusion and Autoregression","date":"2024-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MonoFormer/MonoFormer","path":"models/modeling.py","file_url":"https://github.com/MonoFormer/MonoFormer/blob/HEAD/models/modeling.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2409.13079","paper":"/paper/embedding-geometries-of-contrastive-language","title":"Embedding Geometries of Contrastive Language-Image Pre-Training","date":"2024-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eify/open_clip","path":"src/open_clip/pos_embed.py","file_url":"https://github.com/eify/open_clip/blob/HEAD/src/open_clip/pos_embed.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2408.14368","paper":"/paper/gr-mg-leveraging-partially-annotated-data-via","title":"GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy","date":"2024-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/GR-MG","path":"policy/model/vision_transformer.py","file_url":"https://github.com/bytedance/GR-MG/blob/HEAD/policy/model/vision_transformer.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":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"2408.11001","paper":"/paper/megafusion-extend-diffusion-models-towards","title":"MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning","date":"2024-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoningwu3639/MegaFusion","path":"SD3-MegaFusion/model/embedding.py","file_url":"https://github.com/haoningwu3639/MegaFusion/blob/HEAD/SD3-MegaFusion/model/embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"63384d1943c486c1","mcp_get_code":{"code_sha256":"63384d1943c486c1"}},{"arxiv_id":"2407.16564","paper":"/paper/audio-prompt-adapter-unleashing-music-editing","title":"Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fundwotsai2001/ap-adapter","path":"audio_encoder/models_mae.py","file_url":"https://github.com/fundwotsai2001/ap-adapter/blob/HEAD/audio_encoder/models_mae.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2407.07311","paper":"/paper/vitime-a-visual-intelligence-based-foundation","title":"ViTime: A Visual Intelligence-Based Foundation Model for Time Series Forecasting","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ikeyang/vitime","path":"model/ViTimeAutoencoder.py","file_url":"https://github.com/ikeyang/vitime/blob/HEAD/model/ViTimeAutoencoder.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2406.18846","paper":"/paper/afbench-a-large-scale-benchmark-for-airfoil","title":"AFBench: A Large-scale Benchmark for Airfoil Design","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":"archive","repo":"hitcslj/AFBench","path":"models/dit.py","file_url":"https://github.com/hitcslj/AFBench/blob/HEAD/models/dit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cecc649cd728624","mcp_get_code":{"code_sha256":"0cecc649cd728624"}},{"arxiv_id":"2406.07476","paper":"/paper/videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/inf-clip","path":"inf_clip/models/pos_embed.py","file_url":"https://github.com/damo-nlp-sg/inf-clip/blob/HEAD/inf_clip/models/pos_embed.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":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2405.17403","paper":"/paper/a-closer-look-at-time-steps-is-worthy-of","title":"A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1zeryu/speed","path":"speed/networks/dit/mdt.py","file_url":"https://github.com/1zeryu/speed/blob/HEAD/speed/networks/dit/mdt.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":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2405.17403","paper":"/paper/a-closer-look-at-time-steps-is-worthy-of","title":"A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1zeryu/speed","path":"speed/networks/pixart/PixArt.py","file_url":"https://github.com/1zeryu/speed/blob/HEAD/speed/networks/pixart/PixArt.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":"7700f3428f58afbe","mcp_get_code":{"code_sha256":"7700f3428f58afbe"}},{"arxiv_id":"2405.13998","paper":"/paper/bridging-operator-learning-and-conditioned","title":"CViT: Continuous Vision Transformer for Operator Learning","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"predictiveintelligencelab/cvit","path":"src/model.py","file_url":"https://github.com/predictiveintelligencelab/cvit/blob/HEAD/src/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4814373f5d9ccbcc","mcp_get_code":{"code_sha256":"4814373f5d9ccbcc"}},{"arxiv_id":"2405.04312","paper":"/paper/inf-dit-upsampling-any-resolution-image-with","title":"Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/inf-dit","path":"dit/embeddings.py","file_url":"https://github.com/thudm/inf-dit/blob/HEAD/dit/embeddings.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":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2404.12766","paper":"/paper/continual-learning-on-a-diet-learning-from","title":"Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation","date":"2024-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wx-zhang/continual-learning-on-a-diet","path":"model/pose_embed.py","file_url":"https://github.com/wx-zhang/continual-learning-on-a-diet/blob/HEAD/model/pose_embed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2404.04478","paper":"/paper/diffusion-rwkv-scaling-rwkv-like","title":"Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feizc/diffusion-rwkv","path":"models_drwkv.py","file_url":"https://github.com/feizc/diffusion-rwkv/blob/HEAD/models_drwkv.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2404.03482","paper":"/paper/adaglimpse-active-visual-exploration-with","title":"AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apardyl/adaglimpse","path":"architectures/mae_utils.py","file_url":"https://github.com/apardyl/adaglimpse/blob/HEAD/architectures/mae_utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"2403.15378","paper":"/paper/long-clip-unlocking-the-long-text-capability","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beichenzbc/long-clip","path":"open_clip_long/pos_embed.py","file_url":"https://github.com/beichenzbc/long-clip/blob/HEAD/open_clip_long/pos_embed.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":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2403.09502","paper":"/paper/equiav-leveraging-equivariance-for-audio","title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JongSuk1/EquiAV","path":"models/pos_embed.py","file_url":"https://github.com/JongSuk1/EquiAV/blob/HEAD/models/pos_embed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2403.07815","paper":"/paper/chronos-learning-the-language-of-time-series","title":"Chronos: Learning the Language of Time Series","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mobile-sensing-and-ubicomp-laboratory/normwear","path":"modules/layers.py","file_url":"https://github.com/mobile-sensing-and-ubicomp-laboratory/normwear/blob/HEAD/modules/layers.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":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"2403.04692","paper":"/paper/pixart-s-weak-to-strong-training-of-diffusion","title":"PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2402.14654","paper":"/paper/multi-hmr-multi-person-whole-body-human-mesh","title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/multi-hmr","path":"multi_hmr_anny/pos_embed.py","file_url":"https://github.com/naver/multi-hmr/blob/HEAD/multi_hmr_anny/pos_embed.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2402.11458","paper":"/paper/key-patch-proposer-key-patches-contain-rich","title":"Key Patch Proposer: Key Patches Contain Rich Information","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CA-TT-AC/key-patch-proposer","path":"util/pos_embed.py","file_url":"https://github.com/CA-TT-AC/key-patch-proposer/blob/HEAD/util/pos_embed.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2402.04252","paper":"/paper/eva-clip-18b-scaling-clip-to-18-billion","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baaivision/EVA","path":"EVA-01/eva/modeling_mae_pretrain.py","file_url":"https://github.com/baaivision/EVA/blob/HEAD/EVA-01/eva/modeling_mae_pretrain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2401.02031","paper":"/paper/spy-watermark-robust-invisible-watermarking","title":"Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rfww/spy-watermark","path":"models/pos_embed.py","file_url":"https://github.com/rfww/spy-watermark/blob/HEAD/models/pos_embed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"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/leap/core/embeddings.py","file_url":"https://github.com/wrchen530/leapvo/blob/HEAD/main/leap/core/embeddings.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2401.08639","paper":"/paper/one-step-diffusion-distillation-via-deep-1","title":"One-Step Diffusion Distillation via Deep Equilibrium Models","date":"2023-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"locuslab/get","path":"models/get.py","file_url":"https://github.com/locuslab/get/blob/HEAD/models/get.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2312.02139","paper":"/paper/diffit-diffusion-vision-transformers-for","title":"DiffiT: Diffusion Vision Transformers for Image Generation","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nvlabs/diffit","path":"diffit/diffit.py","file_url":"https://github.com/nvlabs/diffit/blob/HEAD/diffit/diffit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"aa58f30251e59c74","mcp_get_code":{"code_sha256":"aa58f30251e59c74"}},{"arxiv_id":"2311.17597","paper":"/paper/continual-self-supervised-learning-towards","title":"Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeerwen/medcoss","path":"model/Unimodel.py","file_url":"https://github.com/yeerwen/medcoss/blob/HEAD/model/Unimodel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2311.00566","paper":"/paper/croma-remote-sensing-representations-with-1","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","date":"2023-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"antofuller/croma","path":"pretrain_croma.py","file_url":"https://github.com/antofuller/croma/blob/HEAD/pretrain_croma.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2fae31fd41fc4c69","mcp_get_code":{"code_sha256":"2fae31fd41fc4c69"}},{"arxiv_id":"2310.00426","paper":"/paper/pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","date":"2023-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2309.15729","paper":"/paper/mindgpt-interpreting-what-you-see-with-non","title":"MindGPT: Interpreting What You See with Non-invasive Brain Recordings","date":"2023-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jxuanc/mindgpt","path":"modules/pos_embed.py","file_url":"https://github.com/jxuanc/mindgpt/blob/HEAD/modules/pos_embed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2309.10667","paper":"/paper/learning-tri-modal-embeddings-for-zero-shot","title":"Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping","date":"2023-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mvrl/geoclap","path":"geoclap/models/SATMAE.py","file_url":"https://github.com/mvrl/geoclap/blob/HEAD/geoclap/models/SATMAE.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2308.00566","paper":"/paper/predicting-masked-tokens-in-stochastic","title":"Stochastic positional embeddings improve masked image modeling","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amirbar/stop","path":"src/deit.py","file_url":"https://github.com/amirbar/stop/blob/HEAD/src/deit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2307.09361","paper":"/paper/moca-self-supervised-representation-learning","title":"MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/moca","path":"util/model_utils.py","file_url":"https://github.com/valeoai/moca/blob/HEAD/util/model_utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"2305.02968","paper":"/paper/masked-trajectory-models-for-prediction","title":"Masked Trajectory Models for Prediction, Representation, and Control","date":"2023-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/mtm","path":"research/mtm/models/mtm_model.py","file_url":"https://github.com/facebookresearch/mtm/blob/HEAD/research/mtm/models/mtm_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"efa8e5ed19b69df0","mcp_get_code":{"code_sha256":"efa8e5ed19b69df0"}},{"arxiv_id":"2304.03283","paper":"/paper/diffusion-models-as-masked-autoencoders","title":"Diffusion Models as Masked Autoencoders","date":"2023-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kimdanni/DiffMAE","path":"models_cross.py","file_url":"https://github.com/kimdanni/DiffMAE/blob/HEAD/models_cross.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6a53acdcb72e78dd","mcp_get_code":{"code_sha256":"6a53acdcb72e78dd"}},{"arxiv_id":"2303.15564","paper":"/paper/mask-and-restore-blind-backdoor-defense-at","title":"Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder","date":"2023-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsun/bdmae","path":"mae/pos_embed.py","file_url":"https://github.com/tsun/bdmae/blob/HEAD/mae/pos_embed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2303.10834","paper":"/paper/object-centric-slot-diffusion-1","title":"Object-Centric Slot Diffusion","date":"2023-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jindongjiang/latent-slot-diffusion","path":"src/models/utils.py","file_url":"https://github.com/jindongjiang/latent-slot-diffusion/blob/HEAD/src/models/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2301.13155","paper":"/paper/advancing-radiograph-representation-learning","title":"Advancing Radiograph Representation Learning with Masked Record Modeling","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rl4m/mrm-pytorch","path":"model_mrm.py","file_url":"https://github.com/rl4m/mrm-pytorch/blob/HEAD/model_mrm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddbefd1ad8482d18","mcp_get_code":{"code_sha256":"ddbefd1ad8482d18"}},{"arxiv_id":"2212.10368","paper":"/paper/masked-event-modeling-self-supervised","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tum-vision/mem","path":"mem/modeling_mae.py","file_url":"https://github.com/tum-vision/mem/blob/HEAD/mem/modeling_mae.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":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2212.09748","paper":"/paper/scalable-diffusion-models-with-transformers","title":"Scalable Diffusion Models with Transformers","date":"2022-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/dig","path":"models_dig.py","file_url":"https://github.com/hustvl/dig/blob/HEAD/models_dig.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5947aba1d10885f","mcp_get_code":{"code_sha256":"e5947aba1d10885f"}},{"arxiv_id":"2210.10716","paper":"/paper/croco-self-supervised-pre-training-for-3d","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/croco","path":"models/croco.py","file_url":"https://github.com/naver/croco/blob/HEAD/models/croco.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"2204.09435","paper":"/paper/hephaestus-a-large-scale-multitask-dataset","title":"Hephaestus: A large scale multitask dataset towards InSAR understanding","date":"2022-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"orion-ai-lab/hephaestus","path":"self_supervised/mae/mae_model.py","file_url":"https://github.com/orion-ai-lab/hephaestus/blob/HEAD/self_supervised/mae/mae_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"da34f99c07cf5566","mcp_get_code":{"code_sha256":"da34f99c07cf5566"}},{"arxiv_id":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"0jason000/mae_vit","path":"src/mae_vit.py","file_url":"https://github.com/0jason000/mae_vit/blob/HEAD/src/mae_vit.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":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nasa-impact/hls-foundation-os","path":"geospatial_fm/geospatial_fm.py","file_url":"https://github.com/nasa-impact/hls-foundation-os/blob/HEAD/geospatial_fm/geospatial_fm.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":"f6ed4fbd11e09648","mcp_get_code":{"code_sha256":"f6ed4fbd11e09648"}},{"arxiv_id":"2105.12723","paper":"/paper/aggregating-nested-transformers","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","date":"2021-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freder-chen/vitp","path":"util/pos_embed.py","file_url":"https://github.com/freder-chen/vitp/blob/HEAD/util/pos_embed.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":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"1807.10221","paper":"/paper/unified-perceptual-parsing-for-scene","title":"Unified Perceptual Parsing for Scene Understanding","date":"2018-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ESA-PhiLab/PhilEO-MajorTOM","path":"model/phileo_vit.py","file_url":"https://github.com/ESA-PhiLab/PhilEO-MajorTOM/blob/HEAD/model/phileo_vit.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":"4bdd36eab04c3f62","mcp_get_code":{"code_sha256":"4bdd36eab04c3f62"}},{"arxiv_id":"Zhou_Towards_Effective_Foundation_Model_Adaptation_for_Extreme_Cross-Domain_Few-Shot_Learning_ICCV_2025_paper","paper":null,"title":"arXiv:Zhou_Towards_Effective_Foundation_Model_Adaptation_for_Extreme_Cross-Domain_Few-Shot_Learning_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"NWPUZhoufei/FMA","path":"MAE_decoder.py","file_url":"https://github.com/NWPUZhoufei/FMA/blob/HEAD/MAE_decoder.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":"5c8ea92d43ead77d","mcp_get_code":{"code_sha256":"5c8ea92d43ead77d"}},{"arxiv_id":"Fang_Unleashing_Vanilla_Vision_Transformer_with_Masked_Image_Modeling_for_Object_ICCV_2023_paper","paper":null,"title":"arXiv:Fang_Unleashing_Vanilla_Vision_Transformer_with_Masked_Image_Modeling_for_Object_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hustvl/MIMDet","path":"utils/pos_embed.py","file_url":"https://github.com/hustvl/MIMDet/blob/HEAD/utils/pos_embed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12035a2f77d8016c","mcp_get_code":{"code_sha256":"12035a2f77d8016c"}}]}