{"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/crossattention","entry":"CrossAttention","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":85,"n_papers_ran":72,"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":88,"n_samples_ran":74,"n_samples_fingerprinted":5,"n_places":88,"n_places_pointer_only":43,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":74,"unverified":14},"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":"2608.19735","paper":"/paper/arxiv-2608-19735","title":"RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"SAP-samples/tabular-ai-recpfn","path":"src/architecture/recpfn.py","file_url":"https://github.com/SAP-samples/tabular-ai-recpfn/blob/HEAD/src/architecture/recpfn.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":"8153b54d2abfc622","mcp_get_code":{"code_sha256":"8153b54d2abfc622"}},{"arxiv_id":"2608.06025","paper":"/paper/arxiv-2608-06025","title":"Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"suchenjm/AutoThread","path":"python_algorithm/PINN.py","file_url":"https://github.com/suchenjm/AutoThread/blob/HEAD/python_algorithm/PINN.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"83d537ec97c49bd0","mcp_get_code":{"code_sha256":"83d537ec97c49bd0"}},{"arxiv_id":"2607.13164","paper":"/paper/arxiv-2607-13164","title":"Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"xiaruize0911/text2sign","path":"pipeline.py","file_url":"https://github.com/xiaruize0911/text2sign/blob/HEAD/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c3d09298e5fbcef2","mcp_get_code":{"code_sha256":"c3d09298e5fbcef2"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"071967d102ce1b68","mcp_get_code":{"code_sha256":"071967d102ce1b68"}},{"arxiv_id":"2606.05878","paper":"/paper/arxiv-2606-05878","title":"TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"EDF-Lab/ts-icl","path":"src/tsicl/model/network/ts_icl.py","file_url":"https://github.com/EDF-Lab/ts-icl/blob/HEAD/src/tsicl/model/network/ts_icl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"dbad070fabb35fcb","mcp_get_code":{"code_sha256":"dbad070fabb35fcb"}},{"arxiv_id":"2605.31266","paper":"/paper/arxiv-2605-31266","title":"Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"iCVTEAM/DSP","path":"models/dsp/layers.py","file_url":"https://github.com/iCVTEAM/DSP/blob/HEAD/models/dsp/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a820b721e43b1ab9","mcp_get_code":{"code_sha256":"a820b721e43b1ab9"}},{"arxiv_id":"2605.25127","paper":"/paper/arxiv-2605-25127","title":"PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ins-uni-bonn/PQDT","path":"pqdt/models/pq_transformer.py","file_url":"https://github.com/ins-uni-bonn/PQDT/blob/HEAD/pqdt/models/pq_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"607eff327c3cb5c5","mcp_get_code":{"code_sha256":"607eff327c3cb5c5"}},{"arxiv_id":"2603.23647","paper":"/paper/arxiv-2603-23647","title":"λSPLIT: SELF-SUPERVISED CONTENT-AWARE SPECTRAL UNMIXING FOR FLUORESCENCE MICROSCOPY","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"preetam22n/DeepTrans-HSU","path":"Trans_mod.py","file_url":"https://github.com/preetam22n/DeepTrans-HSU/blob/HEAD/Trans_mod.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"38e30b6b7893e8d0","mcp_get_code":{"code_sha256":"38e30b6b7893e8d0"}},{"arxiv_id":"2603.18493","paper":"/paper/arxiv-2603-18493","title":"FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"jinotter3/FILT3R","path":"src/dust3r/model.py","file_url":"https://github.com/jinotter3/FILT3R/blob/HEAD/src/dust3r/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"775287cd7a9a7949","mcp_get_code":{"code_sha256":"775287cd7a9a7949"}},{"arxiv_id":"2603.11950","paper":"/paper/arxiv-2603-11950","title":"Learning Transferable Sensor Models via Language-Informed Pretraining","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"yuc0805/SLIP","path":"modeling_slip.py","file_url":"https://github.com/yuc0805/SLIP/blob/HEAD/modeling_slip.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d936fd21ebf8cc5b","mcp_get_code":{"code_sha256":"d936fd21ebf8cc5b"}},{"arxiv_id":"2603.03312","paper":"/paper/arxiv-2603-03312","title":"Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"xmed-lab/SemKey","path":"model/semkey_parallel.py","file_url":"https://github.com/xmed-lab/SemKey/blob/HEAD/model/semkey_parallel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ad54fe671ae56e3","mcp_get_code":{"code_sha256":"8ad54fe671ae56e3"}},{"arxiv_id":"2601.19498","paper":"/paper/arxiv-2601-19498","title":"Cortex-Grounded Diffusion Models for Brain Image Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ai-med/Cor2Vox","path":"model/BrownianBridge/BrownianBridgeModel_c2v.py","file_url":"https://github.com/ai-med/Cor2Vox/blob/HEAD/model/BrownianBridge/BrownianBridgeModel_c2v.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"d4fae2e24ad5c07e","mcp_get_code":{"code_sha256":"d4fae2e24ad5c07e"}},{"arxiv_id":"2601.17271","paper":"/paper/arxiv-2601-17271","title":"Cross360: 360°Monocular Depth Estimation via Cross Projections Across Scales","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"huangkun101230/Cross360","path":"Networks/network.py","file_url":"https://github.com/huangkun101230/Cross360/blob/HEAD/Networks/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"544581ee39313b81","mcp_get_code":{"code_sha256":"544581ee39313b81"}},{"arxiv_id":"2512.22550","paper":"/paper/arxiv-2512-22550","title":"TIMEPERCEIVER: An Encoder-Decoder Framework for Generalized Time-Series Forecasting","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"efficient-learning-lab/TimePerceiver","path":"models/TimePerceiver.py","file_url":"https://github.com/efficient-learning-lab/TimePerceiver/blob/HEAD/models/TimePerceiver.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba95d81f47fd8823","mcp_get_code":{"code_sha256":"ba95d81f47fd8823"}},{"arxiv_id":"2510.12764","paper":"/paper/arxiv-2510-12764","title":"AnyUp: Universal Feature Upsampling","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"wimmerth/anyup","path":"anyup/model.py","file_url":"https://github.com/wimmerth/anyup/blob/HEAD/anyup/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"05254353888b6fff","mcp_get_code":{"code_sha256":"05254353888b6fff"}},{"arxiv_id":"2510.06691","paper":"/paper/arxiv-2510-06691","title":"Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformer","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Giovanni-Sforza/MaskPoint-AMPT","path":"models/MaskPoint.py","file_url":"https://github.com/Giovanni-Sforza/MaskPoint-AMPT/blob/HEAD/models/MaskPoint.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"eecd5279cc0854b7","mcp_get_code":{"code_sha256":"eecd5279cc0854b7"}},{"arxiv_id":"2510.04577","paper":"/paper/arxiv-2510-04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"wjc2830/Siren","path":"src/siren/model.py","file_url":"https://github.com/wjc2830/Siren/blob/HEAD/src/siren/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cda35aded4b4d4c8","mcp_get_code":{"code_sha256":"cda35aded4b4d4c8"}},{"arxiv_id":"2508.08252","paper":"/paper/arxiv-2508-08252","title":"ReferSplat: Referring Segmentation in 3D Gaussian Splatting","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"heshuting555/ReferSplat","path":"scene/cross_attention.py","file_url":"https://github.com/heshuting555/ReferSplat/blob/HEAD/scene/cross_attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a116fcfa48d9680f","mcp_get_code":{"code_sha256":"a116fcfa48d9680f"}},{"arxiv_id":"2508.03256","paper":"/paper/arxiv-2508-03256","title":"Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"dailenson/DiffBrush","path":"models/unet.py","file_url":"https://github.com/dailenson/DiffBrush/blob/HEAD/models/unet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aaf73d2a3d84cc5b","mcp_get_code":{"code_sha256":"aaf73d2a3d84cc5b"}},{"arxiv_id":"2506.22463","paper":"/paper/modulated-diffusion-accelerating-generative","title":"Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization","date":"2025-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeizhiGao/MoDiff","path":"qdiff/quant_model.py","file_url":"https://github.com/WeizhiGao/MoDiff/blob/HEAD/qdiff/quant_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"edbc6b070aba0b51","mcp_get_code":{"code_sha256":"edbc6b070aba0b51"}},{"arxiv_id":"2505.24103","paper":"/paper/weakly-supervised-affordance-grounding-guided","title":"Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"woyut/wsag-plsp","path":"codes/models/decoder_affordance.py","file_url":"https://github.com/woyut/wsag-plsp/blob/HEAD/codes/models/decoder_affordance.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"02f1b10113bdeb6d","mcp_get_code":{"code_sha256":"02f1b10113bdeb6d"}},{"arxiv_id":"2505.23734","paper":"/paper/zpressor-bottleneck-aware-compression-for","title":"ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziplab/ZPressor","path":"zpressor/zpressor.py","file_url":"https://github.com/ziplab/ZPressor/blob/HEAD/zpressor/zpressor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"154432c6c478da51","mcp_get_code":{"code_sha256":"154432c6c478da51"}},{"arxiv_id":"2505.02625","paper":"/paper/llama-omni2-llm-based-real-time-spoken","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","date":"2025-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rainbowluocs/openomni","path":"openomni/model/speech_generator_ar/speech_generator.py","file_url":"https://github.com/rainbowluocs/openomni/blob/HEAD/openomni/model/speech_generator_ar/speech_generator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d5a46d215b2b4700","mcp_get_code":{"code_sha256":"d5a46d215b2b4700"}},{"arxiv_id":"2504.20860","paper":null,"title":"arXiv:2504.20860","date":null,"month_inferred_from_arxiv_id":"2025-04","title_source":null,"repo":"mainaksingha01/FedMVP","path":"model/FedMVP.py","file_url":"https://github.com/mainaksingha01/FedMVP/blob/HEAD/model/FedMVP.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"172f846498770187","mcp_get_code":{"code_sha256":"172f846498770187"}},{"arxiv_id":"2503.06965","paper":"/paper/secap-self-calibrating-and-adaptive-prompts","title":"SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks","date":"2025-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangshining681/SeCap-AGPReID","path":"fastreid/modeling/backbones/vision_transformer_multiview_SeCap.py","file_url":"https://github.com/wangshining681/SeCap-AGPReID/blob/HEAD/fastreid/modeling/backbones/vision_transformer_multiview_SeCap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"4ea2e6c979e1783b","mcp_get_code":{"code_sha256":"4ea2e6c979e1783b"}},{"arxiv_id":"2412.12146","paper":"/paper/generative-modeling-and-data-augmentation-for","title":"Generative Modeling and Data Augmentation for Power System Production Simulation","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Becklishious/NeurIPS2024","path":"TS-Diffusion/Models/interpretable_diffusion/gaussian_diffusion.py","file_url":"https://github.com/Becklishious/NeurIPS2024/blob/HEAD/TS-Diffusion/Models/interpretable_diffusion/gaussian_diffusion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"70413232706855f0","mcp_get_code":{"code_sha256":"70413232706855f0"}},{"arxiv_id":"2412.06028","paper":"/paper/flexdit-dynamic-token-density-control-for","title":"FlexDiT: Dynamic Token Density Control for Diffusion Transformer","date":"2024-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"changsn/FlexDiT","path":"models.py","file_url":"https://github.com/changsn/FlexDiT/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba088b40a6c22823","mcp_get_code":{"code_sha256":"ba088b40a6c22823"}},{"arxiv_id":"2410.15364","paper":"/paper/scene-graph-generation-with-role-playing","title":"Scene Graph Generation with Role-Playing Large Language Models","date":"2024-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guikunchen/sdsgg","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/roi_relation_predictors.py","file_url":"https://github.com/guikunchen/sdsgg/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/roi_relation_predictors.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c3b3f92371d4c055","mcp_get_code":{"code_sha256":"c3b3f92371d4c055"}},{"arxiv_id":"2407.16448","paper":"/paper/monowad-weather-adaptive-diffusion-model-for","title":"MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VisualAIKHU/MonoWAD","path":"visualDet3D/networks/detectors/MonoWAD.py","file_url":"https://github.com/VisualAIKHU/MonoWAD/blob/HEAD/visualDet3D/networks/detectors/MonoWAD.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"056357c296407ea2","mcp_get_code":{"code_sha256":"056357c296407ea2"}},{"arxiv_id":"2407.15837","paper":"/paper/towards-latent-masked-image-modeling-for-self","title":"Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning","date":"2024-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yibingwei-1/LatentMIM","path":"models_lmim.py","file_url":"https://github.com/yibingwei-1/LatentMIM/blob/HEAD/models_lmim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0aa2506ff4669ad9","mcp_get_code":{"code_sha256":"0aa2506ff4669ad9"}},{"arxiv_id":"2407.04619","paper":"/paper/countgd-multi-modal-open-world-counting","title":"CountGD: Multi-Modal Open-World Counting","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niki-amini-naieni/countx","path":"models_counting_network.py","file_url":"https://github.com/niki-amini-naieni/countx/blob/HEAD/models_counting_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4cb253256cb32632","mcp_get_code":{"code_sha256":"4cb253256cb32632"}},{"arxiv_id":"2406.16860","paper":"/paper/cambrian-1-a-fully-open-vision-centric","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambrian-mllm/cambrian","path":"cambrian/model/vision_sampler.py","file_url":"https://github.com/cambrian-mllm/cambrian/blob/HEAD/cambrian/model/vision_sampler.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7f1838302ff8b2bc","mcp_get_code":{"code_sha256":"7f1838302ff8b2bc"}},{"arxiv_id":"2405.17829","paper":"/paper/ldmol-text-conditioned-molecule-diffusion","title":"LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinhojsk515/ldmol","path":"models.py","file_url":"https://github.com/jinhojsk515/ldmol/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"97fc89954c17d8f4","mcp_get_code":{"code_sha256":"97fc89954c17d8f4"}},{"arxiv_id":"2405.11913","paper":"/paper/diff-bgm-a-diffusion-model-for-video","title":"Diff-BGM: A Diffusion Model for Video Background Music Generation","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sizhelee/Diff-BGM","path":"diffbgm/stable_diffusion/model/unet.py","file_url":"https://github.com/sizhelee/Diff-BGM/blob/HEAD/diffbgm/stable_diffusion/model/unet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ecb181d8f481c786","mcp_get_code":{"code_sha256":"ecb181d8f481c786"}},{"arxiv_id":"2405.04009","paper":"/paper/structured-click-control-in-transformer-based","title":"Structured Click Control in Transformer-based Interactive Segmentation","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hahamyt/scc","path":"isegm/model/modeling/gatlayers.py","file_url":"https://github.com/hahamyt/scc/blob/HEAD/isegm/model/modeling/gatlayers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"df5cfe9ca081ba57","mcp_get_code":{"code_sha256":"df5cfe9ca081ba57"}},{"arxiv_id":"2404.11474","paper":"/paper/towards-highly-realistic-artistic-style","title":"Towards Highly Realistic Artistic Style Transfer via Stable Diffusion with Step-aware and Layer-aware Prompt","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jamie-Cheung/LSAST","path":"cldm/cldm.py","file_url":"https://github.com/Jamie-Cheung/LSAST/blob/HEAD/cldm/cldm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"edd0dbdde64951f7","mcp_get_code":{"code_sha256":"edd0dbdde64951f7"}},{"arxiv_id":"2404.10939","paper":"/paper/more-room-for-language-investigating-the","title":"More Room for Language: Investigating the Effect of Retrieval on Language Models","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ltgoslo/more-room-for-language","path":"pretraining/model.py","file_url":"https://github.com/ltgoslo/more-room-for-language/blob/HEAD/pretraining/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"bb2cd17b7a096164","mcp_get_code":{"code_sha256":"bb2cd17b7a096164"}},{"arxiv_id":"2404.10242","paper":"/paper/masked-autoencoders-for-microscopy-are","title":"Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"recursionpharma/maes_microscopy","path":"mae_modules.py","file_url":"https://github.com/recursionpharma/maes_microscopy/blob/HEAD/mae_modules.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"80cfc8ee2b854473","mcp_get_code":{"code_sha256":"80cfc8ee2b854473"}},{"arxiv_id":"2404.01740","paper":"/paper/weakly-supervised-audio-separation-via-bi","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/bimodalaudioseparation","path":"models/cond_unet_attn.py","file_url":"https://github.com/microsoft/bimodalaudioseparation/blob/HEAD/models/cond_unet_attn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"837dd2dcaeaaded4","mcp_get_code":{"code_sha256":"837dd2dcaeaaded4"}},{"arxiv_id":"2404.01340","paper":"/paper/from-similarity-to-superiority-channel","title":"From Similarity to Superiority: Channel Clustering for Time Series Forecasting","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graph-and-geometric-learning/timeseriesccm","path":"models/layers.py","file_url":"https://github.com/graph-and-geometric-learning/timeseriesccm/blob/HEAD/models/layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfa6cff859120675","mcp_get_code":{"code_sha256":"cfa6cff859120675"}},{"arxiv_id":"2404.00292","paper":"/paper/lake-red-camouflaged-images-generation-by","title":"LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion","date":"2024-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PanchengZhao/LAKE-RED","path":"ldm/ldm/models/diffusion/ddpm.py","file_url":"https://github.com/PanchengZhao/LAKE-RED/blob/HEAD/ldm/ldm/models/diffusion/ddpm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ff2c454a70dac1f9","mcp_get_code":{"code_sha256":"ff2c454a70dac1f9"}},{"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/pt_EquiAV.py","file_url":"https://github.com/jongsuk1/equiav/blob/HEAD/models/pt_EquiAV.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4d9aba462915ffd","mcp_get_code":{"code_sha256":"d4d9aba462915ffd"}},{"arxiv_id":"2403.07874","paper":"/paper/beyond-text-frozen-large-language-models-in","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zh460045050/V2L-Tokenizer","path":"models/models_v2l.py","file_url":"https://github.com/zh460045050/V2L-Tokenizer/blob/HEAD/models/models_v2l.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"43b458c02b16d6b9","mcp_get_code":{"code_sha256":"43b458c02b16d6b9"}},{"arxiv_id":"2403.07187","paper":"/paper/ups-towards-foundation-models-for-pde-solving","title":"UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjunhongshen/unifiedpdesolvers","path":"embedder.py","file_url":"https://github.com/sjunhongshen/unifiedpdesolvers/blob/HEAD/embedder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad5b233df0fa6774","mcp_get_code":{"code_sha256":"ad5b233df0fa6774"}},{"arxiv_id":"2403.06951","paper":"/paper/deadiff-an-efficient-stylization-diffusion","title":"DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Tianhao-Qi/DEADiff_code","path":"ldm/modules/new_attention.py","file_url":"https://github.com/Tianhao-Qi/DEADiff_code/blob/HEAD/ldm/modules/new_attention.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":"e602decd5226f079","mcp_get_code":{"code_sha256":"e602decd5226f079"}},{"arxiv_id":"2403.06225","paper":"/paper/most-motion-style-transformer-between-diverse","title":"MoST: Motion Style Transformer between Diverse Action Contents","date":"2024-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Boeun-Kim/MoST","path":"model/networks.py","file_url":"https://github.com/Boeun-Kim/MoST/blob/HEAD/model/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a6a8c5cc76b3eb9","mcp_get_code":{"code_sha256":"1a6a8c5cc76b3eb9"}},{"arxiv_id":"2403.00131","paper":"/paper/units-building-a-unified-time-series-model","title":"UniTS: A Unified Multi-Task Time Series Model","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mims-harvard/UniTS","path":"models/UniTS.py","file_url":"https://github.com/mims-harvard/UniTS/blob/HEAD/models/UniTS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef2961b050617953","mcp_get_code":{"code_sha256":"ef2961b050617953"}},{"arxiv_id":"2402.19387","paper":"/paper/sed-semantic-aware-discriminator-for-image","title":"SeD: Semantic-Aware Discriminator for Image Super-Resolution","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lbc12345/sed","path":"models/sed.py","file_url":"https://github.com/lbc12345/sed/blob/HEAD/models/sed.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b46f5f90925902c0","mcp_get_code":{"code_sha256":"b46f5f90925902c0"}},{"arxiv_id":"2402.12138","paper":"/paper/perceiving-longer-sequences-with-bi","title":"Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mrkshllr/bixt","path":"timm/models/bixt.py","file_url":"https://github.com/mrkshllr/bixt/blob/HEAD/timm/models/bixt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"406496ff28d67b77","mcp_get_code":{"code_sha256":"406496ff28d67b77"}},{"arxiv_id":"2402.08393","paper":"/paper/nfgtransformer-equivariant-representation","title":"NfgTransformer: Equivariant Representation Learning for Normal-form Games","date":null,"month_inferred_from_arxiv_id":"2024-02","title_source":"archive","repo":"google-deepmind/nfg_transformer","path":"nfg_transformer/network.py","file_url":"https://github.com/google-deepmind/nfg_transformer/blob/HEAD/nfg_transformer/network.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":"32711727edad3841","mcp_get_code":{"code_sha256":"32711727edad3841"}},{"arxiv_id":"2402.05408","paper":"/paper/migc-multi-instance-generation-controller-for","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"limuloo/migc","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c14fdb4777f76063","mcp_get_code":{"code_sha256":"c14fdb4777f76063"}},{"arxiv_id":"2312.06647","paper":"/paper/4m-massively-multimodal-masked-modeling-1","title":"4M: Massively Multimodal Masked Modeling","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-4m","path":"fourm/models/fm.py","file_url":"https://github.com/apple/ml-4m/blob/HEAD/fourm/models/fm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"92c05b09aa8b432d","mcp_get_code":{"code_sha256":"92c05b09aa8b432d"}},{"arxiv_id":"2311.04640","paper":"/paper/object-centric-learning-with-slot-mixture","title":"Object-Centric Learning with Slot Mixture Module","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"airi-institute/smm","path":"modules/smm.py","file_url":"https://github.com/airi-institute/smm/blob/HEAD/modules/smm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ca05fae56d0a5950","mcp_get_code":{"code_sha256":"ca05fae56d0a5950"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba24c9bdfa918f05","mcp_get_code":{"code_sha256":"ba24c9bdfa918f05"}},{"arxiv_id":"2310.12474","paper":"/paper/enhancing-high-resolution-3d-generation","title":"Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fudan-zvg/pgc-3d","path":"ldm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/fudan-zvg/pgc-3d/blob/HEAD/ldm/modules/diffusionmodules/openaimodel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"93dcd06df2fc1896","mcp_get_code":{"code_sha256":"93dcd06df2fc1896"}},{"arxiv_id":"2309.13524","paper":"/paper/global-correlated-3d-decoupling-transformer-1","title":"Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction","date":"2023-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"river-zhang/gta","path":"lib/net/Transformer.py","file_url":"https://github.com/river-zhang/gta/blob/HEAD/lib/net/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c770dc5d61e03875","mcp_get_code":{"code_sha256":"c770dc5d61e03875"}},{"arxiv_id":"2308.05095","paper":"/paper/layoutllm-t2i-eliciting-layout-guidance-from","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"layoutllm-t2i/layoutllm-t2i","path":"GLIGEN/ldm/modules/diffusionmodules/gligen_combine_layout.py","file_url":"https://github.com/layoutllm-t2i/layoutllm-t2i/blob/HEAD/GLIGEN/ldm/modules/diffusionmodules/gligen_combine_layout.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62dab2e5d80c65f2","mcp_get_code":{"code_sha256":"62dab2e5d80c65f2"}},{"arxiv_id":"2307.01952","paper":"/paper/sdxl-improving-latent-diffusion-models-for","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","date":"2023-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stability-ai/generative-models","path":"sgm/modules/diffusionmodules/openaimodel.py","file_url":"https://github.com/stability-ai/generative-models/blob/HEAD/sgm/modules/diffusionmodules/openaimodel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"75e42984360b91c5","mcp_get_code":{"code_sha256":"75e42984360b91c5"}},{"arxiv_id":"2307.01097","paper":"/paper/mvdiffusion-enabling-holistic-multi-view-1","title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion","date":"2023-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Tangshitao/MVDiffusion","path":"src/models/pano/MVGenModel.py","file_url":"https://github.com/Tangshitao/MVDiffusion/blob/HEAD/src/models/pano/MVGenModel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"105b547188750534","mcp_get_code":{"code_sha256":"105b547188750534"}},{"arxiv_id":"2305.18259","paper":"/paper/glyphcontrol-glyph-conditional-control-for-1","title":"GlyphControl: Glyph Conditional Control for Visual Text Generation","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aigtext/glyphcontrol-release","path":"cldm/cldm.py","file_url":"https://github.com/aigtext/glyphcontrol-release/blob/HEAD/cldm/cldm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8f64e619c23619c5","mcp_get_code":{"code_sha256":"8f64e619c23619c5"}},{"arxiv_id":"2305.16283","paper":"/paper/commonscenes-generating-commonsense-3d-indoor","title":"CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ymxlzgy/commonscenes","path":"model/networks/diffusion_networks/sg_diff.py","file_url":"https://github.com/ymxlzgy/commonscenes/blob/HEAD/model/networks/diffusion_networks/sg_diff.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"feb6629ec7db268f","mcp_get_code":{"code_sha256":"feb6629ec7db268f"}},{"arxiv_id":"2304.03869","paper":"/paper/harnessing-the-spatial-temporal-attention-of","title":"Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis","date":"2023-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsb-nlp-chang/diffusion-spacetime-attn","path":"attention_optimization/stable-diffusion/ldm/modules/attention.py","file_url":"https://github.com/ucsb-nlp-chang/diffusion-spacetime-attn/blob/HEAD/attention_optimization/stable-diffusion/ldm/modules/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dbb6a642cadd75ab","mcp_get_code":{"code_sha256":"dbb6a642cadd75ab"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"563ed599da513e37","mcp_get_code":{"code_sha256":"563ed599da513e37"}},{"arxiv_id":"2304.02012","paper":"/paper/egc-image-generation-and-classification-via-a","title":"EGC: Image Generation and Classification via a Diffusion Energy-Based Model","date":"2023-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GuoQiushan/EGC","path":"guided_diffusion/unet.py","file_url":"https://github.com/GuoQiushan/EGC/blob/HEAD/guided_diffusion/unet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"351f5f1606153b33","mcp_get_code":{"code_sha256":"351f5f1606153b33"}},{"arxiv_id":"2303.14412","paper":"/paper/freestyle-layout-to-image-synthesis","title":"Freestyle Layout-to-Image Synthesis","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"essunny310/FreestyleNet","path":"ldm/modules/attention_FLIS.py","file_url":"https://github.com/essunny310/FreestyleNet/blob/HEAD/ldm/modules/attention_FLIS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e38161420ae652c","mcp_get_code":{"code_sha256":"3e38161420ae652c"}},{"arxiv_id":"2303.12670","paper":"/paper/correlational-image-modeling-for-self","title":"Correlational Image Modeling for Self-Supervised Visual Pre-Training","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weivision/correlational-image-modeling","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2e7d0ca574d0d946","mcp_get_code":{"code_sha256":"2e7d0ca574d0d946"}},{"arxiv_id":"2303.06840","paper":"/paper/ddfm-denoising-diffusion-model-for-multi","title":"DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaozixiang1228/if-film","path":"net/Film.py","file_url":"https://github.com/zhaozixiang1228/if-film/blob/HEAD/net/Film.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"553a596819206f47","mcp_get_code":{"code_sha256":"553a596819206f47"}},{"arxiv_id":"2301.05225","paper":"/paper/domain-expansion-of-image-generators","title":"Domain Expansion of Image Generators","date":"2023-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lllyasviel/controlnet","path":"cldm/cldm.py","file_url":"https://github.com/lllyasviel/controlnet/blob/HEAD/cldm/cldm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"87dcf207c5c9187c","mcp_get_code":{"code_sha256":"87dcf207c5c9187c"}},{"arxiv_id":"2301.01296","paper":"/paper/tinymim-an-empirical-study-of-distilling-mim","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","date":"2023-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oliverrensu/d-igpt","path":"DiGPT_torch/models_digpt.py","file_url":"https://github.com/oliverrensu/d-igpt/blob/HEAD/DiGPT_torch/models_digpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce2a200723aec3f8","mcp_get_code":{"code_sha256":"ce2a200723aec3f8"}},{"arxiv_id":"2212.05032","paper":"/paper/training-free-structured-diffusion-guidance","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","date":"2022-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weixi-feng/structured-diffusion-guidance","path":"structured_stable_diffusion/modules/attention.py","file_url":"https://github.com/weixi-feng/structured-diffusion-guidance/blob/HEAD/structured_stable_diffusion/modules/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3efa08f77f40bfd5","mcp_get_code":{"code_sha256":"3efa08f77f40bfd5"}},{"arxiv_id":"2211.05556","paper":"/paper/generating-astronomical-spectra-from","title":"Generating astronomical spectra from photometry with conditional diffusion models","date":null,"month_inferred_from_arxiv_id":"2022-11","title_source":"archive","repo":"larsdoorenbos/generate-spectra","path":"generative/unet.py","file_url":"https://github.com/larsdoorenbos/generate-spectra/blob/HEAD/generative/unet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7eb48a00e07ad73f","mcp_get_code":{"code_sha256":"7eb48a00e07ad73f"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"863ed6dfef2b047a","mcp_get_code":{"code_sha256":"863ed6dfef2b047a"}},{"arxiv_id":"2208.03792","paper":"/paper/domain-randomization-enhanced-depth","title":"Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects","date":"2022-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-EPIC/DREDS","path":"CatePoseEstimation/networks/SwinDRNet.py","file_url":"https://github.com/PKU-EPIC/DREDS/blob/HEAD/CatePoseEstimation/networks/SwinDRNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"10375f1d1a2e05b2","mcp_get_code":{"code_sha256":"10375f1d1a2e05b2"}},{"arxiv_id":"2208.01626","paper":"/paper/prompt-to-prompt-image-editing-with-cross","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","date":"2022-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenwu98/cycle-diffusion","path":"model/lib/stable_diffusion/ldm/modules/attention.py","file_url":"https://github.com/chenwu98/cycle-diffusion/blob/HEAD/model/lib/stable_diffusion/ldm/modules/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"eb721f1e5050ad01","mcp_get_code":{"code_sha256":"eb721f1e5050ad01"}},{"arxiv_id":"2204.02311","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/CoCa-pytorch","path":"coca_pytorch/coca_pytorch.py","file_url":"https://github.com/lucidrains/CoCa-pytorch/blob/HEAD/coca_pytorch/coca_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e79daee4d06c337","mcp_get_code":{"code_sha256":"3e79daee4d06c337"}},{"arxiv_id":"2201.04850","paper":"/paper/bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/bridgeformer/bridge_former_training_block.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/bridgeformer/bridge_former_training_block.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"697a1de2168a5a59","mcp_get_code":{"code_sha256":"697a1de2168a5a59"}},{"arxiv_id":"2201.04850","paper":"/paper/bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tencentarc/mcq","path":"model/video_bridge_former.py","file_url":"https://github.com/tencentarc/mcq/blob/HEAD/model/video_bridge_former.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fe726d5b3aa825e3","mcp_get_code":{"code_sha256":"fe726d5b3aa825e3"}},{"arxiv_id":"2112.04426","paper":"/paper/improving-language-models-by-retrieving-from","title":"Improving language models by retrieving from trillions of tokens","date":"2021-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"labmlai/annotated_deep_learning_paper_implementations","path":"labml_nn/transformers/retro/model.py","file_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/HEAD/labml_nn/transformers/retro/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c3e56d6f2af858c1","mcp_get_code":{"code_sha256":"c3e56d6f2af858c1"}},{"arxiv_id":"2109.01134","paper":"/paper/learning-to-prompt-for-vision-language-models","title":"Learning to Prompt for Vision-Language Models","date":"2021-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hhenryd/tap","path":"trainers/TAP.py","file_url":"https://github.com/hhenryd/tap/blob/HEAD/trainers/TAP.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa2102c5842a8045","mcp_get_code":{"code_sha256":"aa2102c5842a8045"}},{"arxiv_id":"2107.14795","paper":"/paper/perceiver-io-a-general-architecture-for","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","date":"2021-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"esceptico/perceiver-io","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf3adb72e7c5e13d","mcp_get_code":{"code_sha256":"cf3adb72e7c5e13d"}},{"arxiv_id":"2103.14899","paper":"/paper/2103-14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","date":"2021-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rishikksh20/CrossViT-pytorch","path":"crossvit.py","file_url":"https://github.com/rishikksh20/CrossViT-pytorch/blob/HEAD/crossvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8abca80f7f8a5dda","mcp_get_code":{"code_sha256":"8abca80f7f8a5dda"}},{"arxiv_id":"2103.14899","paper":"/paper/2103-14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","date":"2021-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/CrossViT","path":"models/crossvit.py","file_url":"https://github.com/IBM/CrossViT/blob/HEAD/models/crossvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9811d06fb8557fa5","mcp_get_code":{"code_sha256":"9811d06fb8557fa5"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kietngt00/hmdb51-recognition","path":"model/attention.py","file_url":"https://github.com/kietngt00/hmdb51-recognition/blob/HEAD/model/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"122a2bb1f3342e5c","mcp_get_code":{"code_sha256":"122a2bb1f3342e5c"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/perceiver/cross_attention.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/perceiver/cross_attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ce5db0a13e19e003","mcp_get_code":{"code_sha256":"ce5db0a13e19e003"}},{"arxiv_id":"2006.15020","paper":"/paper/pre-training-via-paraphrasing","title":"Pre-training via Paraphrasing","date":"2020-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/marge-pytorch","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fb7817bba2fe0a0b","mcp_get_code":{"code_sha256":"fb7817bba2fe0a0b"}},{"arxiv_id":"Lu_FedHCA2_Towards_Hetero-Client_Federated_Multi-Task_Learning_CVPR_2024_paper","paper":null,"title":"arXiv:Lu_FedHCA2_Towards_Hetero-Client_Federated_Multi-Task_Learning_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"innovator-zero/FedHCA2","path":"models/hyperweight.py","file_url":"https://github.com/innovator-zero/FedHCA2/blob/HEAD/models/hyperweight.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bbea3081c4b97ef","mcp_get_code":{"code_sha256":"0bbea3081c4b97ef"}},{"arxiv_id":"Koo_PartGlot_Learning_Shape_Part_Segmentation_From_Language_Reference_Games_CVPR_2022_paper","paper":null,"title":"arXiv:Koo_PartGlot_Learning_Shape_Part_Segmentation_From_Language_Reference_Games_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"63days/PartGlot","path":"partglot/models/pn_agnostic.py","file_url":"https://github.com/63days/PartGlot/blob/HEAD/partglot/models/pn_agnostic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"69f36807fe0a43bd","mcp_get_code":{"code_sha256":"69f36807fe0a43bd"}},{"arxiv_id":"2024.acl-long.332","paper":null,"title":"arXiv:2024.acl-long.332","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"BUAAw-ML/SKP","path":"lavis/models/adapt_module/amortized_encdec.py","file_url":"https://github.com/BUAAw-ML/SKP/blob/HEAD/lavis/models/adapt_module/amortized_encdec.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"aa1cf692d15daa47","mcp_get_code":{"code_sha256":"aa1cf692d15daa47"}}]}