Repositories list

• Causal-Forcing

  Public
  [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & C…

  diffusiondistillationvideo-generation+ 14

  diffusiondistillationvideo-generationworld-modelsdiffusion-modelsconsistency-modelstext-to-videoautoregressive-modelsgenerative-aiworld-model+ 7

  Python

  •

  Apache License 2.0

  •5757 forks•988988 stars•3333 issues•00 pull requests•Updated Oct 3, 2026Oct 3, 2026

• TurboDiffusion

  Public
  TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

  rcmdistillationvideo-generation+ 7

  rcmdistillationvideo-generationmlsystemdiffusion-modelsinference-accelerationai-infraconsistency-modelsageattentionsparse-linear-attention

  Python

  •

  Apache License 2.0

  •277277 forks•3.9k3.9k stars•7272 issues•77 pull requests•Updated Aug 27, 2026Aug 27, 2026

• TetraJet-v2-NVFP4Training

  Public
  [ICML 2026 Spotlight] Official implementation of TetraJet-v2: Accurate NVFP4 Training for LLMs, with fully-NVFP4 linear layer with unbiased backprop, and algori…

  Python

  •

  Apache License 2.0

  •00 forks•1818 stars•00 issues•00 pull requests•Updated Jul 3, 2026Jul 3, 2026

• PACT

  Public
  [ICML 2026 Spotlight] Official implementation of "PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation".

  Python

  •

  Apache License 2.0

  •11 fork•1414 stars•00 issues•00 pull requests•Updated Jun 16, 2026Jun 16, 2026

• DiT-Extrapolation

  Public
  Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

  generative-modelropediffusion+ 9

  generative-modelropediffusionextrapolationditvideo-generationposition-embeddingdiffusion-modelslong-video-generationdiffusion-transformer+ 2

  Python

  •

  Apache License 2.0

  •7676 forks•829829 stars•2424 issues•00 pull requests•Updated Jun 6, 2026Jun 6, 2026

• TetraJet-MXFP4Training

  Public
  Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training

  Python

  •

  Apache License 2.0

  •33 forks•4141 stars•00 issues•00 pull requests•Updated May 4, 2026May 4, 2026

• tianshou

  Public
  An elegant PyTorch deep reinforcement learning library.

  pytorchdqnpolicy-gradient+ 16

  pytorchdqnpolicy-gradientrlcqlatariddpgimitation-learningsacdrl+ 9

  Python

  •

  MIT License

  •1.3k1.3k forks•11k11k stars•131131 issues•1010 pull requests•Updated Apr 3, 2026Apr 3, 2026

• Auto-MIA

  Public
  Python

  •00 forks•33 stars•00 issues•00 pull requests•Updated Mar 24, 2026Mar 24, 2026

• RGBT-Clothing

  Public
  Python

  •00 forks•33 stars•00 issues•00 pull requests•Updated Mar 24, 2026Mar 24, 2026

• embodied-data-toolkit

  Public
  A toolkit for processing raw embodied data into standardized formats and converting between embodied dataset schemas.

  data-processingembodied-aiformat-converter-tool

  data-processingembodied-aiformat-converter-tool

  Python

  •33 forks•2020 stars•00 issues•00 pull requests•Updated Mar 16, 2026Mar 16, 2026

• SLA

  Public
  SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

  transformervideo-generationmlsys+ 7

  transformervideo-generationmlsysinference-accelerationai-infralinear-attentionsparse-attentiondiffusion-transformertrain-accelerationsparse-linear-attention

  Python

  •

  Apache License 2.0

  •2323 forks•551551 stars•99 issues•00 pull requests•Updated Feb 24, 2026Feb 24, 2026

• RDT2

  Public
  Official code of RDT 2

  Python

  •

  Apache License 2.0

  •5858 forks•805805 stars•1717 issues•22 pull requests•Updated Feb 7, 2026Feb 7, 2026

• i-DODE

  Public
  Official code for "Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs" (ICML 2023)

  Python

  •

  Apache License 2.0

  •11 fork•1919 stars•11 issue•00 pull requests•Updated Jan 27, 2026Jan 27, 2026

• RoboticsDiffusionTransformer

  Public
  RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

  Python

  •

  MIT License

  •168168 forks•1.8k1.8k stars•3838 issues•33 pull requests•Updated Jan 21, 2026Jan 21, 2026

• MLA-Trust

  Public
  A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness, controllability, safety and privacy dimensions through 34 interactive task…

  agentbenchmarkprivacy+ 6

  agentbenchmarkprivacytoolboxsafetymulti-modalcontrollabilitytrustworthy-aitruthfulness

  Python

  •

  MIT License

  •44 forks•6464 stars•33 issues•00 pull requests•Updated Jan 9, 2026Jan 9, 2026

• Motus

  Public
  Official code of Motus: A Unified Latent Action World Model

  roboticsdiffusion-modelvideo-generation+ 4

  roboticsdiffusion-modelvideo-generationrobotic-manipulationworld-modelunidiffuservision-language-action-model

  Python

  •

  Apache License 2.0

  •7777 forks•1.3k1.3k stars•3434 issues•11 pull request•Updated Jan 5, 2026Jan 5, 2026

• vidar-robotwin

  Public
  robotwin evaluation code for vidar.

  Python

  •

  MIT License

  •00 forks•66 stars•11 issue•00 pull requests•Updated Dec 22, 2025Dec 22, 2025

• vidar

  Public
  Official repo for vidar and vidarc: video foundation model for robotics.

  Python

  •11 fork•4444 stars•22 issues•00 pull requests•Updated Dec 22, 2025Dec 22, 2025

• UniCardio

  Public
  Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer

  Python

  •

  MIT License

  •66 forks•6464 stars•22 issues•00 pull requests•Updated Oct 9, 2025Oct 9, 2025

• FrameBridge

  Public
  FrameBridge: Improving Image-to-Video Generation with Bridge Models

  Python

  •00 forks•33 stars•00 issues•00 pull requests•Updated Oct 2, 2025Oct 2, 2025

• DiffusionBridge

  Public
  Official codebase for "Diffusion Bridge Implicit Models" (ICLR 2025) and "Consistency Diffusion Bridge Models" (NeurIPS 2024)

  Python

  •1010 forks•125125 stars•66 issues•00 pull requests•Updated Sep 9, 2025Sep 9, 2025

• SparseDM

  Public
  Python

  •11 fork•22 stars•00 issues•00 pull requests•Updated Aug 24, 2025Aug 24, 2025

• EmbodiedActiveDefense

  Public
  Official implementation for "Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments" (T…

  Python

  •

  MIT License

  •00 forks•99 stars•00 issues•00 pull requests•Updated Jul 26, 2025Jul 26, 2025

• Adaptive-Sparse-Trainer

  Public
  Official implementation for "Pruning Large Language Models with Semi-Structural Adaptive Sparse Training" (AAAI 2025)

  Python

  •

  Apache License 2.0

  •33 forks•2020 stars•00 issues•00 pull requests•Updated Jul 1, 2025Jul 1, 2025

• MMTrustEval

  Public
  A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)

  benchmarkprivacytoolbox+ 9

  benchmarkprivacytoolboxsafetymulti-modalfairnessrobustnessclaudegpt-4trustworthy-ai+ 2

  Python

  •

  Creative Commons Attribution Share Alike 4.0 International

  •1212 forks•178178 stars•11 issue•00 pull requests•Updated Jun 27, 2025Jun 27, 2025

• DDO

  Public
  Python

  •

  Other

  •00 forks•00 stars•00 issues•00 pull requests•Updated Jun 16, 2025Jun 16, 2025

• GFT

  Public
  Python

  •

  MIT License

  •11 fork•5353 stars•55 issues•00 pull requests•Updated Jun 13, 2025Jun 13, 2025

• STAIR

  Public
  Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"

  Python

  •

  MIT License

  •77 forks•9090 stars•33 issues•00 pull requests•Updated Feb 26, 2025Feb 26, 2025

• EffWRN-paddle

  Public
  Python

  •

  MIT License

  •00 forks•00 stars•00 issues•00 pull requests•Updated Feb 24, 2025Feb 24, 2025

• CCA

  Public
  Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"

  Python

  •

  MIT License

  •11 fork•3737 stars•33 issues•00 pull requests•Updated Feb 11, 2025Feb 11, 2025