{"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/transformerblock","entry":"TransformerBlock","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":73,"n_papers_ran":35,"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":89,"n_samples_ran":47,"n_samples_fingerprinted":6,"n_places":89,"n_places_pointer_only":50,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":47,"unverified":42},"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":"2608.03715","paper":"/paper/arxiv-2608-03715","title":"Amortized Interventional Forecasting for Multivariate CIR Processes","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"sa-and/cir-activa","path":"models.py","file_url":"https://github.com/sa-and/cir-activa/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":"5f42d8d95774866a","mcp_get_code":{"code_sha256":"5f42d8d95774866a"}},{"arxiv_id":"2608.01839","paper":"/paper/arxiv-2608-01839","title":"tFUSOperator: Operator Learning for Transcranial Focused Ultrasound Digital Twins","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"CMME-Lab/tFUSOperator","path":"models/model.py","file_url":"https://github.com/CMME-Lab/tFUSOperator/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd3ab8b08108ae49","mcp_get_code":{"code_sha256":"fd3ab8b08108ae49"}},{"arxiv_id":"2607.26504","paper":"/paper/arxiv-2607-26504","title":"From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"SeunggeunKimkr/genuine-any-order","path":"LatentMDM/model/latent_mdm.py","file_url":"https://github.com/SeunggeunKimkr/genuine-any-order/blob/HEAD/LatentMDM/model/latent_mdm.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":"92e841bff119fbfb","mcp_get_code":{"code_sha256":"92e841bff119fbfb"}},{"arxiv_id":"2606.15104","paper":"/paper/arxiv-2606-15104","title":"Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Shaoyun2023/TEDFusion","path":"model/TEDFusion_model.py","file_url":"https://github.com/Shaoyun2023/TEDFusion/blob/HEAD/model/TEDFusion_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3bec9331e88709b1","mcp_get_code":{"code_sha256":"3bec9331e88709b1"}},{"arxiv_id":"2605.14937","paper":"/paper/arxiv-2605-14937","title":"Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"angelvillar96/PlaySlot","path":"src/models/Predictors/DynamicsModels.py","file_url":"https://github.com/angelvillar96/PlaySlot/blob/HEAD/src/models/Predictors/DynamicsModels.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39f80a1d11dadcea","mcp_get_code":{"code_sha256":"39f80a1d11dadcea"}},{"arxiv_id":"2604.22826","paper":"/paper/arxiv-2604-22826","title":"Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"simd-ai/shape","path":"shape_foundation/models/gaot_backbone.py","file_url":"https://github.com/simd-ai/shape/blob/HEAD/shape_foundation/models/gaot_backbone.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":"59d28bdee2ad39aa","mcp_get_code":{"code_sha256":"59d28bdee2ad39aa"}},{"arxiv_id":"2603.22315","paper":"/paper/arxiv-2603-22315","title":"Emergency Preemption Without Online Exploration: A Decision Transformer Approach","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"AnthonySu/decision-transformer-traffic","path":"src/models/madt.py","file_url":"https://github.com/AnthonySu/decision-transformer-traffic/blob/HEAD/src/models/madt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5bbbfdbefbaf524d","mcp_get_code":{"code_sha256":"5bbbfdbefbaf524d"}},{"arxiv_id":"2602.11139","paper":"/paper/arxiv-2602-11139","title":"TabICLv2: A better, faster, scalable, and open tabular foundation model","date":"2026-02-11","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"soda-inria/nanotabicl","path":"model.py","file_url":"https://github.com/soda-inria/nanotabicl/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"17ca29b6edfb0303","mcp_get_code":{"code_sha256":"17ca29b6edfb0303"}},{"arxiv_id":"2602.05667","paper":"/paper/arxiv-2602-05667","title":"Accelerating Benchmarking of Functional Connectivity Modeling via Structure-aware Core-set Selection","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"lzhan94swu/SCLCS","path":"model.py","file_url":"https://github.com/lzhan94swu/SCLCS/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2cc3cf6df8f2cd0a","mcp_get_code":{"code_sha256":"2cc3cf6df8f2cd0a"}},{"arxiv_id":"2602.00596","paper":"/paper/arxiv-2602-00596","title":"Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"shenyangHuang/TGB","path":"modules/sthn.py","file_url":"https://github.com/shenyangHuang/TGB/blob/HEAD/modules/sthn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0c8de46adf7473e","mcp_get_code":{"code_sha256":"c0c8de46adf7473e"}},{"arxiv_id":"2601.20072","paper":"/paper/arxiv-2601-20072","title":"Semi-Supervised Masked Autoencoders: Unlocking Vision Transformer Potential with Limited Data","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"atik666/ssmae","path":"ssmae.py","file_url":"https://github.com/atik666/ssmae/blob/HEAD/ssmae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"439300399e4bce24","mcp_get_code":{"code_sha256":"439300399e4bce24"}},{"arxiv_id":"2601.12252","paper":"/paper/arxiv-2601-12252","title":"Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Trymore-lab/PerceptAlign","path":"perceptalign/models/perceptalign.py","file_url":"https://github.com/Trymore-lab/PerceptAlign/blob/HEAD/perceptalign/models/perceptalign.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6d63f165bbbdc39f","mcp_get_code":{"code_sha256":"6d63f165bbbdc39f"}},{"arxiv_id":"2601.03955","paper":"/paper/arxiv-2601-03955","title":"ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Kwai-Kolors/ResTok","path":"modeling/restok.py","file_url":"https://github.com/Kwai-Kolors/ResTok/blob/HEAD/modeling/restok.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":"031fee67ad484ab8","mcp_get_code":{"code_sha256":"031fee67ad484ab8"}},{"arxiv_id":"2510.09343","paper":"/paper/arxiv-2510-09343","title":"Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Zihang-Chen/HM-TIR","path":"models/restormer_arch.py","file_url":"https://github.com/Zihang-Chen/HM-TIR/blob/HEAD/models/restormer_arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"543f89fa45313251","mcp_get_code":{"code_sha256":"543f89fa45313251"}},{"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":"569eaf68130b8046","mcp_get_code":{"code_sha256":"569eaf68130b8046"}},{"arxiv_id":"2509.25727","paper":"/paper/arxiv-2509-25727","title":"Boundary-to-Region Supervision for Offline Safe Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"HuikangSu/B2R","path":"model/B2R.py","file_url":"https://github.com/HuikangSu/B2R/blob/HEAD/model/B2R.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":"5f51ec4895241525","mcp_get_code":{"code_sha256":"5f51ec4895241525"}},{"arxiv_id":"2509.15891","paper":"/paper/arxiv-2509-15891","title":"Global Regulation and Excitation via Attention Tuning for Stereo Matching","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"JarvisLee0423/GREAT-Stereo","path":"models/great_stereo/transformers.py","file_url":"https://github.com/JarvisLee0423/GREAT-Stereo/blob/HEAD/models/great_stereo/transformers.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":"91825e9c5c198d4d","mcp_get_code":{"code_sha256":"91825e9c5c198d4d"}},{"arxiv_id":"2507.16251","paper":"/paper/holitracer-holistic-vectorization-of","title":"HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery","date":"2025-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vvangfaye/HoliTracer","path":"holitracer/vector/models/base.py","file_url":"https://github.com/vvangfaye/HoliTracer/blob/HEAD/holitracer/vector/models/base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"786b3229be60ffc1","mcp_get_code":{"code_sha256":"786b3229be60ffc1"}},{"arxiv_id":"2506.10351","paper":"/paper/physiowave-a-multi-scale-wavelet-transformer","title":"PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation","date":"2025-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ForeverBlue816/PhysioWave","path":"model.py","file_url":"https://github.com/ForeverBlue816/PhysioWave/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8560d21a0d260387","mcp_get_code":{"code_sha256":"8560d21a0d260387"}},{"arxiv_id":"2506.08292","paper":"/paper/from-debate-to-equilibrium-belief-driven","title":"From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/econ","path":"src/modules/agents/belief_policy_network.py","file_url":"https://github.com/tmlr-group/econ/blob/HEAD/src/modules/agents/belief_policy_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c9580d1c98d9c426","mcp_get_code":{"code_sha256":"c9580d1c98d9c426"}},{"arxiv_id":"2505.16298","paper":"/paper/flow-matching-based-sequential-recommender","title":"Flow Matching based Sequential Recommender Model","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FengLiu-1/FMRec","path":"src/fmrec.py","file_url":"https://github.com/FengLiu-1/FMRec/blob/HEAD/src/fmrec.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c2faa101f85c2e6f","mcp_get_code":{"code_sha256":"c2faa101f85c2e6f"}},{"arxiv_id":"2505.12630","paper":"/paper/degradation-aware-feature-perturbation-for","title":"Degradation-Aware Feature Perturbation for All-in-One Image Restoration","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TxpHome/DFPIR","path":"net/model.py","file_url":"https://github.com/TxpHome/DFPIR/blob/HEAD/net/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cde7278418c4fe09","mcp_get_code":{"code_sha256":"cde7278418c4fe09"}},{"arxiv_id":"2505.02707","paper":"/paper/voila-voice-language-foundation-models-for","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","date":"2025-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maitrix-org/Voila","path":"model.py","file_url":"https://github.com/maitrix-org/Voila/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"262a73a1c64553d2","mcp_get_code":{"code_sha256":"262a73a1c64553d2"}},{"arxiv_id":"2504.08222","paper":"/paper/f-3-set-towards-analyzing-fast-frequent-and","title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","date":"2025-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"f3set/f3set","path":"model/impl/actionformer.py","file_url":"https://github.com/f3set/f3set/blob/HEAD/model/impl/actionformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"881363cfc3127e8f","mcp_get_code":{"code_sha256":"881363cfc3127e8f"}},{"arxiv_id":"2504.07963","paper":"/paper/pixelflow-pixel-space-generative-models-with","title":"PixelFlow: Pixel-Space Generative Models with Flow","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shoufachen/pixelflow","path":"pixelflow/model.py","file_url":"https://github.com/shoufachen/pixelflow/blob/HEAD/pixelflow/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"768992dc577749dc","mcp_get_code":{"code_sha256":"768992dc577749dc"}},{"arxiv_id":"2503.20174","paper":"/paper/devil-is-in-the-uniformity-exploring-diverse","title":"Devil is in the Uniformity: Exploring Diverse Learners within Transformer for Image Restoration","date":"2025-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshyZhou/HINT","path":"basicsr/models/archs/HINT_arch.py","file_url":"https://github.com/joshyZhou/HINT/blob/HEAD/basicsr/models/archs/HINT_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"888eb051383154ce","mcp_get_code":{"code_sha256":"888eb051383154ce"}},{"arxiv_id":"2503.10696","paper":"/paper/neighboring-autoregressive-modeling-for","title":"Neighboring Autoregressive Modeling for Efficient Visual Generation","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thisisbillhe/nar","path":"NAR-images/autoregressive/models/gpt.py","file_url":"https://github.com/thisisbillhe/nar/blob/HEAD/NAR-images/autoregressive/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0421358adba1260b","mcp_get_code":{"code_sha256":"0421358adba1260b"}},{"arxiv_id":"2502.19854","paper":"/paper/one-model-for-all-low-level-task-interaction","title":"One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AWCXV/GIFNet","path":"GIFNet_model.py","file_url":"https://github.com/AWCXV/GIFNet/blob/HEAD/GIFNet_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12e49ea3bbb33533","mcp_get_code":{"code_sha256":"12e49ea3bbb33533"}},{"arxiv_id":"2501.00880","paper":"/paper/improving-autoregressive-visual-generation","title":"Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction","date":"2025-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjtuplayer/IAR","path":"autoregressive/models/gpt.py","file_url":"https://github.com/sjtuplayer/IAR/blob/HEAD/autoregressive/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f03b5731f02b2a1e","mcp_get_code":{"code_sha256":"f03b5731f02b2a1e"}},{"arxiv_id":"2410.08261","paper":"/paper/meissonic-revitalizing-masked-generative","title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"viiika/Meissonic","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"8d6351d29b4f55c6","mcp_get_code":{"code_sha256":"8d6351d29b4f55c6"}},{"arxiv_id":"2410.05711","paper":"/paper/diffusion-auto-regressive-transformer-for","title":"Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyue-cheng/timemae","path":"model/TimeMAE.py","file_url":"https://github.com/mingyue-cheng/timemae/blob/HEAD/model/TimeMAE.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d60276a4b2f78c8d","mcp_get_code":{"code_sha256":"d60276a4b2f78c8d"}},{"arxiv_id":"2410.02705","paper":"/paper/controlar-controllable-image-generation-with","title":"ControlAR: Controllable Image Generation with Autoregressive Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/controlar","path":"autoregressive/models/gpt.py","file_url":"https://github.com/hustvl/controlar/blob/HEAD/autoregressive/models/gpt.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":"7baa685224160fe5","mcp_get_code":{"code_sha256":"7baa685224160fe5"}},{"arxiv_id":"2408.14080","paper":"/paper/sonics-synthetic-or-not-identifying","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","date":"2024-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awsaf49/sonics","path":"sonics/models/spectttra.py","file_url":"https://github.com/awsaf49/sonics/blob/HEAD/sonics/models/spectttra.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1a607e9c32d2884d","mcp_get_code":{"code_sha256":"1a607e9c32d2884d"}},{"arxiv_id":"2407.13987","paper":"/paper/realviformer-investigating-attention-for-real","title":"RealViformer: Investigating Attention for Real-World Video Super-Resolution","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yuehan717/RealViformer","path":"archs/realviformer_arch.py","file_url":"https://github.com/Yuehan717/RealViformer/blob/HEAD/archs/realviformer_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e91c5e9a654fd7dc","mcp_get_code":{"code_sha256":"e91c5e9a654fd7dc"}},{"arxiv_id":"2407.10172","paper":"/paper/restoring-images-in-adverse-weather","title":"Restoring Images in Adverse Weather Conditions via Histogram Transformer","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunshangquan/Histoformer","path":"basicsr/models/archs/histoformer_arch.py","file_url":"https://github.com/sunshangquan/Histoformer/blob/HEAD/basicsr/models/archs/histoformer_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b3103e147e16c1a5","mcp_get_code":{"code_sha256":"b3103e147e16c1a5"}},{"arxiv_id":"2407.04621","paper":"/paper/onerestore-a-universal-restoration-framework","title":"OneRestore: A Universal Restoration Framework for Composite Degradation","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gy65896/onerestore","path":"model/OneRestore.py","file_url":"https://github.com/gy65896/onerestore/blob/HEAD/model/OneRestore.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"392dd9ba5b5f2e7a","mcp_get_code":{"code_sha256":"392dd9ba5b5f2e7a"}},{"arxiv_id":"2406.04329","paper":"/paper/simplified-and-generalized-masked-diffusion","title":"Simplified and Generalized Masked Diffusion for Discrete Data","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/md4","path":"md4/models/diffusion/md4.py","file_url":"https://github.com/google-deepmind/md4/blob/HEAD/md4/models/diffusion/md4.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":"7a351fb6b29e26ac","mcp_get_code":{"code_sha256":"7a351fb6b29e26ac"}},{"arxiv_id":"2405.13911","paper":"/paper/topa-extend-large-language-models-for-video","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhg-wei/topa","path":"llama/model.py","file_url":"https://github.com/dhg-wei/topa/blob/HEAD/llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"36f60efcf15f5bc6","mcp_get_code":{"code_sha256":"36f60efcf15f5bc6"}},{"arxiv_id":"2405.03943","paper":"/paper/predictive-modeling-with-temporal-graphical","title":"Predictive Modeling with Temporal Graphical Representation on Electronic Health Records","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"The-Real-JerryChen/TRANS","path":"models/Seqmodels.py","file_url":"https://github.com/The-Real-JerryChen/TRANS/blob/HEAD/models/Seqmodels.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"65bdef9d91c144b9","mcp_get_code":{"code_sha256":"65bdef9d91c144b9"}},{"arxiv_id":"2404.05001","paper":"/paper/dual-scale-transformer-for-large-scale-single","title":"Dual-Scale Transformer for Large-Scale Single-Pixel Imaging","date":"2024-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gang-Qu/HATNet-SPI","path":"model/network.py","file_url":"https://github.com/Gang-Qu/HATNet-SPI/blob/HEAD/model/network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f0be4135088932a4","mcp_get_code":{"code_sha256":"f0be4135088932a4"}},{"arxiv_id":"2404.01547","paper":"/paper/bidirectional-multi-scale-implicit-neural","title":"Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cschenxiang/NeRD-Rain","path":"model.py","file_url":"https://github.com/cschenxiang/NeRD-Rain/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0f3a63ce67469c7","mcp_get_code":{"code_sha256":"e0f3a63ce67469c7"}},{"arxiv_id":"2404.00288","paper":null,"title":"arXiv:2404.00288","date":null,"month_inferred_from_arxiv_id":"2024-04","title_source":null,"repo":"joshyZhou/FPro","path":"basicsr/models/archs/FPro_arch.py","file_url":"https://github.com/joshyZhou/FPro/blob/HEAD/basicsr/models/archs/FPro_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e2bd9540b0c5ff0","mcp_get_code":{"code_sha256":"2e2bd9540b0c5ff0"}},{"arxiv_id":"2403.18548","paper":"/paper/a-semi-supervised-nighttime-dehazing-baseline","title":"A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xiaofeng-life/SFSNiD","path":"methods/MyNightDehazing/SFSNiD.py","file_url":"https://github.com/Xiaofeng-life/SFSNiD/blob/HEAD/methods/MyNightDehazing/SFSNiD.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5a7a00261e5bfad2","mcp_get_code":{"code_sha256":"5a7a00261e5bfad2"}},{"arxiv_id":"2402.13040","paper":"/paper/text-guided-molecule-generation-with","title":"Text-Guided Molecule Generation with Diffusion Language Model","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Deno-V/tgm-dlm","path":"improved-diffusion/improved_diffusion/transformer_model.py","file_url":"https://github.com/Deno-V/tgm-dlm/blob/HEAD/improved-diffusion/improved_diffusion/transformer_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"85f117cd2c476a03","mcp_get_code":{"code_sha256":"85f117cd2c476a03"}},{"arxiv_id":"2402.09450","paper":"/paper/guiding-masked-representation-learning-to","title":"Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bakqui/st-mem","path":"models/st_mem.py","file_url":"https://github.com/bakqui/st-mem/blob/HEAD/models/st_mem.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8bb3bf9e7e9a8e01","mcp_get_code":{"code_sha256":"8bb3bf9e7e9a8e01"}},{"arxiv_id":"2312.12275","paper":"/paper/emergence-of-in-context-reinforcement","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"corl-team/ad-eps","path":"dark_room/ad_darkroom.py","file_url":"https://github.com/corl-team/ad-eps/blob/HEAD/dark_room/ad_darkroom.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0797809d36877895","mcp_get_code":{"code_sha256":"0797809d36877895"}},{"arxiv_id":"2311.04434","paper":null,"title":"arXiv:2311.04434","date":null,"month_inferred_from_arxiv_id":"2023-11","title_source":null,"repo":"spatialdatasciencegroup/HST","path":"utils/bandLayers.py","file_url":"https://github.com/spatialdatasciencegroup/HST/blob/HEAD/utils/bandLayers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1886bc45e56b3f1a","mcp_get_code":{"code_sha256":"1886bc45e56b3f1a"}},{"arxiv_id":"2310.15747","paper":"/paper/large-language-models-are-temporal-and-causal","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlvlab/Flipped-VQA","path":"llama/model.py","file_url":"https://github.com/mlvlab/Flipped-VQA/blob/HEAD/llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ed5543f646686967","mcp_get_code":{"code_sha256":"ed5543f646686967"}},{"arxiv_id":"2310.04148","paper":"/paper/self-supervised-neuron-segmentation-with","title":"Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning","date":"2023-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ydchen0806/dbMiM","path":"dbmim/models.py","file_url":"https://github.com/ydchen0806/dbMiM/blob/HEAD/dbmim/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8c788e1c3eb20c1","mcp_get_code":{"code_sha256":"a8c788e1c3eb20c1"}},{"arxiv_id":"2308.14036","paper":"/paper/mb-taylorformer-multi-branch-efficient","title":"MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing","date":"2023-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FVL2020/ICCV-2023-MB-TaylorFormer","path":"basicsr/models/archs/MB_TaylorFormer.py","file_url":"https://github.com/FVL2020/ICCV-2023-MB-TaylorFormer/blob/HEAD/basicsr/models/archs/MB_TaylorFormer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"60ff91d683606241","mcp_get_code":{"code_sha256":"60ff91d683606241"}},{"arxiv_id":"2307.09288","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"glb400/Toy-RecLM","path":"model.py","file_url":"https://github.com/glb400/Toy-RecLM/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61aae005c3076a9b","mcp_get_code":{"code_sha256":"61aae005c3076a9b"}},{"arxiv_id":"2303.11950","paper":"/paper/learning-a-sparse-transformer-network-for","title":"Learning A Sparse Transformer Network for Effective Image Deraining","date":"2023-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cschenxiang/drsformer","path":"basicsr/models/archs/DRSformer_arch.py","file_url":"https://github.com/cschenxiang/drsformer/blob/HEAD/basicsr/models/archs/DRSformer_arch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"724b7c5be1319bc9","mcp_get_code":{"code_sha256":"724b7c5be1319bc9"}},{"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/mmif-cddfuse","path":"net.py","file_url":"https://github.com/zhaozixiang1228/mmif-cddfuse/blob/HEAD/net.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7fbefc76d724c861","mcp_get_code":{"code_sha256":"7fbefc76d724c861"}},{"arxiv_id":"2302.14348","paper":"/paper/im2hands-learning-attentive-implicit","title":"Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes","date":"2023-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jyunlee/im2hands","path":"artihand/nasa/models/core_ref_occ.py","file_url":"https://github.com/jyunlee/im2hands/blob/HEAD/artihand/nasa/models/core_ref_occ.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e8908a6667142a43","mcp_get_code":{"code_sha256":"e8908a6667142a43"}},{"arxiv_id":"2302.07351","paper":"/paper/constrained-decision-transformer-for-offline","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","date":"2023-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuzuxin/osrl","path":"osrl/algorithms/cdt.py","file_url":"https://github.com/liuzuxin/osrl/blob/HEAD/osrl/algorithms/cdt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c0e123b568ecbec0","mcp_get_code":{"code_sha256":"c0e123b568ecbec0"}},{"arxiv_id":"2207.08132","paper":"/paper/e-nerv-expedite-neural-video-representation","title":"E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context","date":"2022-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kyleleey/E-NeRV","path":"model/E_NeRV.py","file_url":"https://github.com/kyleleey/E-NeRV/blob/HEAD/model/E_NeRV.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"718295a430fc6897","mcp_get_code":{"code_sha256":"718295a430fc6897"}},{"arxiv_id":"2207.05342","paper":"/paper/video-graph-transformer-for-video-question","title":"Video Graph Transformer for Video Question Answering","date":"2022-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/VGT","path":"model/vqa_model.py","file_url":"https://github.com/sail-sg/VGT/blob/HEAD/model/vqa_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b294b4902336fb78","mcp_get_code":{"code_sha256":"b294b4902336fb78"}},{"arxiv_id":"2205.14209","paper":"/paper/stargraph-a-coarse-to-fine-representation","title":"StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph","date":"2022-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hzli-ucas/stargraph","path":"model.py","file_url":"https://github.com/hzli-ucas/stargraph/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"479ae90c7dfc70a7","mcp_get_code":{"code_sha256":"479ae90c7dfc70a7"}},{"arxiv_id":"2203.15556","paper":"/paper/training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karpathy/llama2.c","path":"model.py","file_url":"https://github.com/karpathy/llama2.c/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46b07f9445b01dce","mcp_get_code":{"code_sha256":"46b07f9445b01dce"}},{"arxiv_id":"2202.11921","paper":"/paper/auto-scaling-vision-transformers-without-1","title":"Auto-scaling Vision Transformers without Training","date":"2022-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-group/asvit","path":"lib/models/cell_infers/transformer.py","file_url":"https://github.com/vita-group/asvit/blob/HEAD/lib/models/cell_infers/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96404f2862cd1474","mcp_get_code":{"code_sha256":"96404f2862cd1474"}},{"arxiv_id":"2109.02974","paper":"/paper/fuseformer-fusing-fine-grained-information-in","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","date":"2021-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruiliu-ai/FuseFormer","path":"model/fuseformer.py","file_url":"https://github.com/ruiliu-ai/FuseFormer/blob/HEAD/model/fuseformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"afa615aa2f60ae16","mcp_get_code":{"code_sha256":"afa615aa2f60ae16"}},{"arxiv_id":"2106.13924","paper":"/paper/self-attentive-ensemble-transformer","title":"Self-Attentive Ensemble Transformer: Representing Ensemble Interactions in Neural Networks for Earth System Models","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uantwerpm4s/pp_eupp","path":"Transformer.py","file_url":"https://github.com/uantwerpm4s/pp_eupp/blob/HEAD/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b8f30b82390a6db8","mcp_get_code":{"code_sha256":"b8f30b82390a6db8"}},{"arxiv_id":"2106.01345","paper":"/paper/decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"corl-team/CORL","path":"algorithms/offline/dt.py","file_url":"https://github.com/corl-team/CORL/blob/HEAD/algorithms/offline/dt.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":"d879368facd3289e","mcp_get_code":{"code_sha256":"d879368facd3289e"}},{"arxiv_id":"2106.01345","paper":"/paper/decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzmtsvv/rl_task","path":"decision_transformer/model.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/decision_transformer/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12cc4b7038955563","mcp_get_code":{"code_sha256":"12cc4b7038955563"}},{"arxiv_id":"2106.01345","paper":"/paper/decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yun-kwak/decision-transformer-jax","path":"dt_jax/gpt.py","file_url":"https://github.com/yun-kwak/decision-transformer-jax/blob/HEAD/dt_jax/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b48d1222dabdd2c","mcp_get_code":{"code_sha256":"9b48d1222dabdd2c"}},{"arxiv_id":"2105.15203","paper":"/paper/segformer-simple-and-efficient-design-for","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","date":"2021-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"macdonaldezra/minesegsat","path":"mine_seg_sat/models/segformer.py","file_url":"https://github.com/macdonaldezra/minesegsat/blob/HEAD/mine_seg_sat/models/segformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89979e961601b054","mcp_get_code":{"code_sha256":"89979e961601b054"}},{"arxiv_id":"2103.06495","paper":"/paper/read-like-humans-autonomous-bidirectional-and","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","date":"2021-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"topdu/openocr","path":"openrec/modeling/decoders/abinet_decoder.py","file_url":"https://github.com/topdu/openocr/blob/HEAD/openrec/modeling/decoders/abinet_decoder.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":"27366919489ba9ab","mcp_get_code":{"code_sha256":"27366919489ba9ab"}},{"arxiv_id":"2102.02808","paper":"/paper/multi-stage-progressive-image-restoration","title":"Multi-Stage Progressive Image Restoration","date":"2021-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taowangzj/llformer","path":"model/LLFormer.py","file_url":"https://github.com/taowangzj/llformer/blob/HEAD/model/LLFormer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2d417e1b35e33481","mcp_get_code":{"code_sha256":"2d417e1b35e33481"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Burf/VisionTransformer-Tensorflow2","path":"vit/vit.py","file_url":"https://github.com/Burf/VisionTransformer-Tensorflow2/blob/HEAD/vit/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"608cb341e62af9a7","mcp_get_code":{"code_sha256":"608cb341e62af9a7"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mdmhriday/vision-transformers","path":"models/vit.py","file_url":"https://github.com/mdmhriday/vision-transformers/blob/HEAD/models/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"136aaa7dc1143322","mcp_get_code":{"code_sha256":"136aaa7dc1143322"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nima1999nikkhah/ViT-Hybrid","path":"ViT-Hybrid.py","file_url":"https://github.com/nima1999nikkhah/ViT-Hybrid/blob/HEAD/ViT-Hybrid.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"472347df45454b8a","mcp_get_code":{"code_sha256":"472347df45454b8a"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"04RR/SOTA-Vision","path":"ViT.py","file_url":"https://github.com/04RR/SOTA-Vision/blob/HEAD/ViT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"625ba3d0632ccbe7","mcp_get_code":{"code_sha256":"625ba3d0632ccbe7"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uzi0espil/research-papers-implementation","path":"Vision Transformer/models.py","file_url":"https://github.com/uzi0espil/research-papers-implementation/blob/HEAD/Vision%20Transformer/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"621c33d160c8772b","mcp_get_code":{"code_sha256":"621c33d160c8772b"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ugenteraan/Masked-AutoEncoder-PyTorch","path":"models/mae.py","file_url":"https://github.com/Ugenteraan/Masked-AutoEncoder-PyTorch/blob/HEAD/models/mae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ca9596fc7f3f63a7","mcp_get_code":{"code_sha256":"ca9596fc7f3f63a7"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamalkraj/ALBERT-TF2.0","path":"albert.py","file_url":"https://github.com/kamalkraj/ALBERT-TF2.0/blob/HEAD/albert.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":"64da3191abb9f8c9","mcp_get_code":{"code_sha256":"64da3191abb9f8c9"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanchenyou/transformer-study","path":"transformer_bert_from_scratch_5.py","file_url":"https://github.com/fanchenyou/transformer-study/blob/HEAD/transformer_bert_from_scratch_5.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7e19140b483ea0b1","mcp_get_code":{"code_sha256":"7e19140b483ea0b1"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codertimo/BERT-pytorch","path":"bert_pytorch/model/bert.py","file_url":"https://github.com/codertimo/BERT-pytorch/blob/HEAD/bert_pytorch/model/bert.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":"81af9c02ca090c06","mcp_get_code":{"code_sha256":"81af9c02ca090c06"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eagle705/bert","path":"model/bert.py","file_url":"https://github.com/eagle705/bert/blob/HEAD/model/bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"daa550ff0552c158","mcp_get_code":{"code_sha256":"daa550ff0552c158"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linlei1214/SITS-BERT","path":"code/model/bert.py","file_url":"https://github.com/linlei1214/SITS-BERT/blob/HEAD/code/model/bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b28507fe7a827ac","mcp_get_code":{"code_sha256":"9b28507fe7a827ac"}},{"arxiv_id":"1807.03819","paper":"/paper/universal-transformers","title":"Universal Transformers","date":"2018-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sidney1505/arc_maml_transformer","path":"keras_transformer/transformer.py","file_url":"https://github.com/sidney1505/arc_maml_transformer/blob/HEAD/keras_transformer/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bfa58c8b92ee3953","mcp_get_code":{"code_sha256":"bfa58c8b92ee3953"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WenYanger/General-Transformer-Pytorch","path":"Transformer.py","file_url":"https://github.com/WenYanger/General-Transformer-Pytorch/blob/HEAD/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1a2fa936d6b70229","mcp_get_code":{"code_sha256":"1a2fa936d6b70229"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Wolfie8935/Implementation-of-Attention-is-all-you-need","path":"transformer_from_scratch.py","file_url":"https://github.com/Wolfie8935/Implementation-of-Attention-is-all-you-need/blob/HEAD/transformer_from_scratch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb24958475ff8e8a","mcp_get_code":{"code_sha256":"eb24958475ff8e8a"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jelifysh/Transformers","path":"transformers.py","file_url":"https://github.com/jelifysh/Transformers/blob/HEAD/transformers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a41be559b566c0ca","mcp_get_code":{"code_sha256":"a41be559b566c0ca"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"The-AI-Summer/self_attention","path":"self_attention_cv/transformer_vanilla/transformer_block.py","file_url":"https://github.com/The-AI-Summer/self_attention/blob/HEAD/self_attention_cv/transformer_vanilla/transformer_block.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"82fc4978c3cb86ab","mcp_get_code":{"code_sha256":"82fc4978c3cb86ab"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Rami97rgb/French-to-English-Translator","path":"model.py","file_url":"https://github.com/Rami97rgb/French-to-English-Translator/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ea0e0ad81a3931c","mcp_get_code":{"code_sha256":"9ea0e0ad81a3931c"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlinc1905/dsilt-tsa","path":"time_series_classification/models.py","file_url":"https://github.com/nlinc1905/dsilt-tsa/blob/HEAD/time_series_classification/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4f1eaa4055e49eac","mcp_get_code":{"code_sha256":"4f1eaa4055e49eac"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShivamRajSharma/Transformer-Architectures-From-Scratch","path":"TRANSFORMERS.py","file_url":"https://github.com/ShivamRajSharma/Transformer-Architectures-From-Scratch/blob/HEAD/TRANSFORMERS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97b94fa2b1b16f5b","mcp_get_code":{"code_sha256":"97b94fa2b1b16f5b"}},{"arxiv_id":"ijcai2024_0231","paper":null,"title":"arXiv:ijcai2024_0231","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"2837790380/SD-CEM","path":"model/SDCEM.py","file_url":"https://github.com/2837790380/SD-CEM/blob/HEAD/model/SDCEM.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7a7203de53c6f2b","mcp_get_code":{"code_sha256":"a7a7203de53c6f2b"}},{"arxiv_id":"Zhou_PanoLlama_Generating_Endless_and_Coherent_Panoramas_with_Next-Token-Prediction_LLMs_ICCV_2025_paper","paper":null,"title":"arXiv:Zhou_PanoLlama_Generating_Endless_and_Coherent_Panoramas_with_Next-Token-Prediction_LLMs_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"0606zt/PanoLlama","path":"token_generator/gpt.py","file_url":"https://github.com/0606zt/PanoLlama/blob/HEAD/token_generator/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b99cafb688aeae10","mcp_get_code":{"code_sha256":"b99cafb688aeae10"}}]}