{"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/finallayer","entry":"FinalLayer","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":29,"n_papers_ran":28,"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":30,"n_samples_ran":29,"n_samples_fingerprinted":4,"n_places":30,"n_places_pointer_only":12,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":29,"unverified":1},"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","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7a122209a9457bd0","mcp_get_code":{"code_sha256":"7a122209a9457bd0"}},{"arxiv_id":"2607.26860","paper":"/paper/arxiv-2607-26860","title":"Amortized Moment Matching for Visual Generation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"poppuppy/amfd","path":"models/amfd_loss.py","file_url":"https://github.com/poppuppy/amfd/blob/HEAD/models/amfd_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"05012eadd72a8228","mcp_get_code":{"code_sha256":"05012eadd72a8228"}},{"arxiv_id":"2607.12753","paper":"/paper/arxiv-2607-12753","title":"RFMSR: Residual Flow Matching for Image Super-Resolution","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Faze-Hsw/RFMSR","path":"models/rfmsr.py","file_url":"https://github.com/Faze-Hsw/RFMSR/blob/HEAD/models/rfmsr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"79c5559a6eacf08d","mcp_get_code":{"code_sha256":"79c5559a6eacf08d"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"14abdaa97f983a0c","mcp_get_code":{"code_sha256":"14abdaa97f983a0c"}},{"arxiv_id":"2605.18055","paper":"/paper/arxiv-2605-18055","title":"FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"darkflash03/FLAG","path":"models/graph_dit_repa.py","file_url":"https://github.com/darkflash03/FLAG/blob/HEAD/models/graph_dit_repa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"99e2d26fbcf322cd","mcp_get_code":{"code_sha256":"99e2d26fbcf322cd"}},{"arxiv_id":"2605.11622","paper":"/paper/arxiv-2605-11622","title":"RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq Prediction","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"YXSong000/RNA-FM","path":"src/model_RNAFM.py","file_url":"https://github.com/YXSong000/RNA-FM/blob/HEAD/src/model_RNAFM.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4770614d2e972930","mcp_get_code":{"code_sha256":"4770614d2e972930"}},{"arxiv_id":"2605.07193","paper":"/paper/arxiv-2605-07193","title":"Coupling Models for One-Step Discrete Generation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"pengzhangzhi/Coupling-Models","path":"mnist_guidance/coupling_model/transformer_flow.py","file_url":"https://github.com/pengzhangzhi/Coupling-Models/blob/HEAD/mnist_guidance/coupling_model/transformer_flow.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97e7ff49c36f3550","mcp_get_code":{"code_sha256":"97e7ff49c36f3550"}},{"arxiv_id":"2603.20700","paper":"/paper/arxiv-2603-20700","title":"mmWave-Diffusion:A Novel Framework for Respiration Sensing Using Observation-Anchored Conditional Diffusion Model","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"goodluckyongw/mmWave-Diffusion","path":"network.py","file_url":"https://github.com/goodluckyongw/mmWave-Diffusion/blob/HEAD/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28b45f22cc03a722","mcp_get_code":{"code_sha256":"28b45f22cc03a722"}},{"arxiv_id":"2603.14366","paper":"/paper/arxiv-2603-14366","title":"Representation Alignment for Just Image Transformers is not Easier than You Think","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"kaist-cvml/PixelREPA","path":"model_pixelREPA.py","file_url":"https://github.com/kaist-cvml/PixelREPA/blob/HEAD/model_pixelREPA.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"85504c53809c9e71","mcp_get_code":{"code_sha256":"85504c53809c9e71"}},{"arxiv_id":"2602.03858","paper":"/paper/arxiv-2602-03858","title":"PENGUIN: General Vital Sign Reconstruction from PPG with Flow Matching State Space Model","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Neurogica/PENGUIN","path":"src/models/PENGUIN.py","file_url":"https://github.com/Neurogica/PENGUIN/blob/HEAD/src/models/PENGUIN.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"code_sha256_prefix":"0d2f91efc3774a83","mcp_get_code":{"code_sha256":"0d2f91efc3774a83"}},{"arxiv_id":"2602.02722","paper":"/paper/arxiv-2602-02722","title":"Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"DanHrmti/HECRL","path":"agents/diffuser/subgoal_diffuser.py","file_url":"https://github.com/DanHrmti/HECRL/blob/HEAD/agents/diffuser/subgoal_diffuser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eff3741649fc49e6","mcp_get_code":{"code_sha256":"eff3741649fc49e6"}},{"arxiv_id":"2602.02722","paper":"/paper/arxiv-2602-02722","title":"Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"carl-qi/EC-Diffuser","path":"diffuser/diffuser/models/transformer_modules.py","file_url":"https://github.com/carl-qi/EC-Diffuser/blob/HEAD/diffuser/diffuser/models/transformer_modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7534870f9202f83","mcp_get_code":{"code_sha256":"f7534870f9202f83"}},{"arxiv_id":"2602.02493","paper":"/paper/arxiv-2602-02493","title":"PixelGen: Improving Pixel Diffusion with Perceptual Supervision","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Zehong-Ma/PixelGen","path":"src/models/transformer/JiT.py","file_url":"https://github.com/Zehong-Ma/PixelGen/blob/HEAD/src/models/transformer/JiT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fc4b1cddc56752ce","mcp_get_code":{"code_sha256":"fc4b1cddc56752ce"}},{"arxiv_id":"2601.07773","paper":"/paper/arxiv-2601-07773","title":"Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"csslc/Self-Transcendence","path":"models/sit_selftrans_model.py","file_url":"https://github.com/csslc/Self-Transcendence/blob/HEAD/models/sit_selftrans_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce261fdb436234fb","mcp_get_code":{"code_sha256":"ce261fdb436234fb"}},{"arxiv_id":"2506.19935","paper":"/paper/any-order-gpt-as-masked-diffusion-model","title":"Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture","date":"2025-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scxue/AO-GPT-MDM","path":"model_AOGPT_AdaLN6_NoRep_cond_128_trunc_qknorm.py","file_url":"https://github.com/scxue/AO-GPT-MDM/blob/HEAD/model_AOGPT_AdaLN6_NoRep_cond_128_trunc_qknorm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3bdc88f4e362aea","mcp_get_code":{"code_sha256":"f3bdc88f4e362aea"}},{"arxiv_id":"2505.11196","paper":"/paper/2505-11196","title":"DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling","date":"2025-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shallowdream204/dico","path":"dico_models.py","file_url":"https://github.com/shallowdream204/dico/blob/HEAD/dico_models.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":"abeb88030013a7f9","mcp_get_code":{"code_sha256":"abeb88030013a7f9"}},{"arxiv_id":"2505.07812","paper":"/paper/continuous-visual-autoregressive-generation","title":"Continuous Visual Autoregressive Generation via Score Maximization","date":"2025-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shaochenze/ear","path":"models/ear.py","file_url":"https://github.com/shaochenze/ear/blob/HEAD/models/ear.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69746d7a74acca85","mcp_get_code":{"code_sha256":"69746d7a74acca85"}},{"arxiv_id":"2504.11295","paper":"/paper/autoregressive-distillation-of-diffusion","title":"Autoregressive Distillation of Diffusion Transformers","date":"2025-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alsdudrla10/ARD","path":"models_ARD.py","file_url":"https://github.com/alsdudrla10/ARD/blob/HEAD/models_ARD.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":"9e95dfea74d4d587","mcp_get_code":{"code_sha256":"9e95dfea74d4d587"}},{"arxiv_id":"2503.06132","paper":"/paper/usp-unified-self-supervised-pretraining-for","title":"USP: Unified Self-Supervised Pretraining for Image Generation and Understanding","date":"2025-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AMAP-ML/USP","path":"generation/SiT/models.py","file_url":"https://github.com/AMAP-ML/USP/blob/HEAD/generation/SiT/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f722666b1c98510c","mcp_get_code":{"code_sha256":"f722666b1c98510c"}},{"arxiv_id":"2503.03965","paper":"/paper/all-atom-diffusion-transformers-unified","title":"All-atom Diffusion Transformers: Unified generative modelling of molecules and materials","date":"2025-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/all-atom-diffusion-transformer","path":"src/models/denoisers/dit.py","file_url":"https://github.com/facebookresearch/all-atom-diffusion-transformer/blob/HEAD/src/models/denoisers/dit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"9e3ed34320e0b553","mcp_get_code":{"code_sha256":"9e3ed34320e0b553"}},{"arxiv_id":"2501.15598","paper":"/paper/diffusion-generative-modeling-for-spatially","title":"Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images","date":"2025-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SichenZhu/Stem","path":"Stem/models.py","file_url":"https://github.com/SichenZhu/Stem/blob/HEAD/Stem/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1e595016d632ec56","mcp_get_code":{"code_sha256":"1e595016d632ec56"}},{"arxiv_id":"2412.03603","paper":"/paper/hunyuanvideo-a-systematic-framework-for-large","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","date":"2024-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tencent/hunyuanvideo","path":"hyvideo/modules/models.py","file_url":"https://github.com/tencent/hunyuanvideo/blob/HEAD/hyvideo/modules/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"db1fce6ba128923c","mcp_get_code":{"code_sha256":"db1fce6ba128923c"}},{"arxiv_id":"2410.23788","paper":"/paper/edt-an-efficient-diffusion-transformer","title":"EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinwangchen/edt","path":"models_edt.py","file_url":"https://github.com/xinwangchen/edt/blob/HEAD/models_edt.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":"413ff2ca1aeb13c7","mcp_get_code":{"code_sha256":"413ff2ca1aeb13c7"}},{"arxiv_id":"2410.10356","paper":"/paper/fasterdit-towards-faster-diffusion","title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/LightningDiT","path":"models/lightningdit.py","file_url":"https://github.com/hustvl/LightningDiT/blob/HEAD/models/lightningdit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"044b0ed1c2fd2514","mcp_get_code":{"code_sha256":"044b0ed1c2fd2514"}},{"arxiv_id":"2406.11838","paper":"/paper/autoregressive-image-generation-without","title":"Autoregressive Image Generation without Vector Quantization","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lth14/mar","path":"models/diffloss.py","file_url":"https://github.com/lth14/mar/blob/HEAD/models/diffloss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89c137ff7c13fc84","mcp_get_code":{"code_sha256":"89c137ff7c13fc84"}},{"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":"790db4e566777808","mcp_get_code":{"code_sha256":"790db4e566777808"}},{"arxiv_id":"2402.01516","paper":"/paper/cross-view-masked-diffusion-transformers-for","title":"Cross-view Masked Diffusion Transformers for Person Image Synthesis","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trungpx/xmdpt","path":"masked_diffusion/models.py","file_url":"https://github.com/trungpx/xmdpt/blob/HEAD/masked_diffusion/models.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":"01200a9e5704de4e","mcp_get_code":{"code_sha256":"01200a9e5704de4e"}},{"arxiv_id":"2305.13311","paper":"/paper/vdt-an-empirical-study-on-video-diffusion","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rerv/vdt","path":"models.py","file_url":"https://github.com/rerv/vdt/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8e42700c31523a9c","mcp_get_code":{"code_sha256":"8e42700c31523a9c"}},{"arxiv_id":"2303.14389","paper":"/paper/masked-diffusion-transformer-is-a-strong","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/MDT","path":"masked_diffusion/models.py","file_url":"https://github.com/sail-sg/MDT/blob/HEAD/masked_diffusion/models.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":"b6005b513a46b17e","mcp_get_code":{"code_sha256":"b6005b513a46b17e"}},{"arxiv_id":"1512.03385","paper":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wondonghyeon/protest-detection-violence-estimation","path":"util.py","file_url":"https://github.com/wondonghyeon/protest-detection-violence-estimation/blob/HEAD/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5edb2e8bee3de5a1","mcp_get_code":{"code_sha256":"5edb2e8bee3de5a1"}}]}