{"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/attnblock","entry":"AttnBlock","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":22,"n_papers_ran":13,"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":22,"n_samples_ran":13,"n_samples_fingerprinted":2,"n_places":22,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":13,"unverified":9},"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":"2602.01760","paper":"/paper/arxiv-2602-01760","title":"MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"zhayanping/MagicFuse","path":"network.py","file_url":"https://github.com/zhayanping/MagicFuse/blob/HEAD/network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d879f3a6d4f4c07","mcp_get_code":{"code_sha256":"9d879f3a6d4f4c07"}},{"arxiv_id":"2510.19618","paper":"/paper/arxiv-2510-19618","title":"Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"jeffreychou777/GenComm","path":"opencood/models/gencomm_modules/cond_diff.py","file_url":"https://github.com/jeffreychou777/GenComm/blob/HEAD/opencood/models/gencomm_modules/cond_diff.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d4886c3d9b64d574","mcp_get_code":{"code_sha256":"d4886c3d9b64d574"}},{"arxiv_id":"2507.02358","paper":"/paper/hita-holistic-tokenizer-for-autoregressive","title":"Hita: Holistic Tokenizer for Autoregressive Image Generation","date":"2025-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CVMI-Lab/Hita","path":"hita/tokenizer/tokenizer_image/vq_model.py","file_url":"https://github.com/CVMI-Lab/Hita/blob/HEAD/hita/tokenizer/tokenizer_image/vq_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7cbb211518a363dd","mcp_get_code":{"code_sha256":"7cbb211518a363dd"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ae77b73557079f18","mcp_get_code":{"code_sha256":"ae77b73557079f18"}},{"arxiv_id":"2505.17685","paper":"/paper/futuresightdrive-thinking-visually-with","title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MIV-XJTU/FSDrive","path":"MoVQGAN/movqgan/models/vqgan.py","file_url":"https://github.com/MIV-XJTU/FSDrive/blob/HEAD/MoVQGAN/movqgan/models/vqgan.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c22fcb7b2c1bd3b","mcp_get_code":{"code_sha256":"5c22fcb7b2c1bd3b"}},{"arxiv_id":"2505.17022","paper":"/paper/got-r1-unleashing-reasoning-capability-of","title":"GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gogoduan/got-r1","path":"src/models/vq_model.py","file_url":"https://github.com/gogoduan/got-r1/blob/HEAD/src/models/vq_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93ec039f4b98caf7","mcp_get_code":{"code_sha256":"93ec039f4b98caf7"}},{"arxiv_id":"2504.02160","paper":"/paper/less-to-more-generalization-unlocking-more","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/UNO","path":"uno/flux/pipeline.py","file_url":"https://github.com/bytedance/UNO/blob/HEAD/uno/flux/pipeline.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":"237044dc7eab755f","mcp_get_code":{"code_sha256":"237044dc7eab755f"}},{"arxiv_id":"2405.17398","paper":"/paper/vista-a-generalizable-driving-world-model","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendrivelab/vista","path":"vwm/models/diffusion.py","file_url":"https://github.com/opendrivelab/vista/blob/HEAD/vwm/models/diffusion.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":"65943cc8c6a0822c","mcp_get_code":{"code_sha256":"65943cc8c6a0822c"}},{"arxiv_id":"2404.00815","paper":"/paper/towards-realistic-scene-generation-with-lidar","title":"Towards Realistic Scene Generation with LiDAR Diffusion Models","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hancyran/lidar-diffusion","path":"lidm/modules/diffusion/model_lidm.py","file_url":"https://github.com/hancyran/lidar-diffusion/blob/HEAD/lidm/modules/diffusion/model_lidm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d1c55266c7801e2b","mcp_get_code":{"code_sha256":"d1c55266c7801e2b"}},{"arxiv_id":"2403.19527","paper":"/paper/instance-adaptive-and-geometric-aware","title":"Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leeiieeo/ag-pose","path":"model/Net_modules.py","file_url":"https://github.com/leeiieeo/ag-pose/blob/HEAD/model/Net_modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4db14c22fe42c8b3","mcp_get_code":{"code_sha256":"4db14c22fe42c8b3"}},{"arxiv_id":"2403.10897","paper":"/paper/rethinking-multi-view-representation-learning","title":"Rethinking Multi-view Representation Learning via Distilled Disentangling","date":"2024-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Guanzhou-Ke/MRDD","path":"src/models/mrdd.py","file_url":"https://github.com/Guanzhou-Ke/MRDD/blob/HEAD/src/models/mrdd.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a6490b3d3c9759c","mcp_get_code":{"code_sha256":"3a6490b3d3c9759c"}},{"arxiv_id":"2311.05152","paper":"/paper/cross-modal-prompts-adapting-large-pre","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoyi-duan/dg-sct","path":"DG-SCT/AVVP/nets/grouping.py","file_url":"https://github.com/haoyi-duan/dg-sct/blob/HEAD/DG-SCT/AVVP/nets/grouping.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"68095f4e08371ab1","mcp_get_code":{"code_sha256":"68095f4e08371ab1"}},{"arxiv_id":"2303.17056","paper":"/paper/audio-visual-grouping-network-for-sound","title":"Audio-Visual Grouping Network for Sound Localization from Mixtures","date":"2023-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stonemo/avgn","path":"model.py","file_url":"https://github.com/stonemo/avgn/blob/HEAD/model.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":"60da1158138a6b50","mcp_get_code":{"code_sha256":"60da1158138a6b50"}},{"arxiv_id":"2210.10864","paper":"/paper/cluster-and-aggregate-face-recognition-with","title":"Cluster and Aggregate: Face Recognition with Large Probe Set","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mk-minchul/caface","path":"caface/nets/transformer/cluster_transformer.py","file_url":"https://github.com/mk-minchul/caface/blob/HEAD/caface/nets/transformer/cluster_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7ef7a4e5e9d4847","mcp_get_code":{"code_sha256":"e7ef7a4e5e9d4847"}},{"arxiv_id":"2209.00588","paper":"/paper/transformers-are-sample-efficient-world","title":"Transformers are Sample-Efficient World Models","date":"2022-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eloialonso/iris","path":"src/models/world_model.py","file_url":"https://github.com/eloialonso/iris/blob/HEAD/src/models/world_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":"9d1f4ad302b969e4","mcp_get_code":{"code_sha256":"9d1f4ad302b969e4"}},{"arxiv_id":"2205.09853","paper":"/paper/masked-conditional-video-diffusion-for","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","date":"2022-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"voletiv/mcvd-pytorch","path":"models/unet.py","file_url":"https://github.com/voletiv/mcvd-pytorch/blob/HEAD/models/unet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"608ce50c0a254bf3","mcp_get_code":{"code_sha256":"608ce50c0a254bf3"}},{"arxiv_id":"2203.09516","paper":"/paper/autosdf-shape-priors-for-3d-completion","title":"AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation","date":"2022-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yccyenchicheng/AutoSDF","path":"models/networks/pvqvae_networks/auto_encoder.py","file_url":"https://github.com/yccyenchicheng/AutoSDF/blob/HEAD/models/networks/pvqvae_networks/auto_encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ee868f3e1b5e8b8b","mcp_get_code":{"code_sha256":"ee868f3e1b5e8b8b"}},{"arxiv_id":"2202.04298","paper":"/paper/image-difference-captioning-with-pre-training","title":"Image Difference Captioning with Pre-training and Contrastive Learning","date":"2022-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaolinli/IDC","path":"bird/modules_pretrain_bird.py","file_url":"https://github.com/yaolinli/IDC/blob/HEAD/bird/modules_pretrain_bird.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0536f292ece1ae96","mcp_get_code":{"code_sha256":"0536f292ece1ae96"}},{"arxiv_id":"2107.11298","paper":"/paper/surfacenet-adversarial-svbrdf-estimation-from","title":"SurfaceNet: Adversarial SVBRDF Estimation from a Single Image","date":"2021-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"perceivelab/trf-sg2im","path":"modules/blocks.py","file_url":"https://github.com/perceivelab/trf-sg2im/blob/HEAD/modules/blocks.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":"bf6e2d1e65621c97","mcp_get_code":{"code_sha256":"bf6e2d1e65621c97"}},{"arxiv_id":"2107.00630","paper":"/paper/variational-diffusion-models","title":"Variational Diffusion Models","date":"2021-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/vdm","path":"model_vdm.py","file_url":"https://github.com/google-research/vdm/blob/HEAD/model_vdm.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":"561db3edf2a73d49","mcp_get_code":{"code_sha256":"561db3edf2a73d49"}},{"arxiv_id":"2102.12122","paper":"/paper/pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/vision-longformer","path":"src/models/msvit.py","file_url":"https://github.com/microsoft/vision-longformer/blob/HEAD/src/models/msvit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2de4320db751601f","mcp_get_code":{"code_sha256":"2de4320db751601f"}},{"arxiv_id":"2006.11239","paper":"/paper/denoising-diffusion-probabilistic-models","title":"Denoising Diffusion Probabilistic Models","date":"2020-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiyixuxu/denoising-diffusion-flax","path":"denoising_diffusion_flax/unet.py","file_url":"https://github.com/yiyixuxu/denoising-diffusion-flax/blob/HEAD/denoising_diffusion_flax/unet.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":"1a4610fe4183ab35","mcp_get_code":{"code_sha256":"1a4610fe4183ab35"}}]}