Repositories list

• InfiniteVL

  Public
  InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models

  Python

  •

  Apache License 2.0

  •4•84•1•0•Updated Feb 2, 2026Feb 2, 2026

• VAD

  Public
  [ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

  end-to-endautonomous-driving

  Python

  •

  Apache License 2.0

  •141•1.2k•76•1•Updated Jan 31, 2026Jan 31, 2026

• VGT

  Public
  Visual Generation Tuning

  Python

  •

  MIT License

  •0•98•1•0•Updated Jan 27, 2026Jan 27, 2026

• MobileI2V

  Public
  [ArXiv 2025] MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices

  video-generationimage-to-videodiffusion-models+ 1video-diffusion-transformers

  Python

  •2•68•1•0•Updated Jan 5, 2026Jan 5, 2026

• GaussTR

  Public
  [CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

  Python

  •

  MIT License

  •11•207•1•0•Updated Jan 5, 2026Jan 5, 2026

• DiffusionDriveV2

  Public
  DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving

  Python

  •

  MIT License

  •20•233•9•2•Updated Dec 29, 2025Dec 29, 2025

• SuperCLIP

  Public
  Python

  •

  Apache License 2.0

  •6•121•5•0•Updated Dec 26, 2025Dec 26, 2025

• DiffusionVL

  Public
  [ArXiv 2025] DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

  Python

  •

  Apache License 2.0

  •5•131•3•0•Updated Dec 25, 2025Dec 25, 2025

• TBCM

  Public
  Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs

  Python

  •0•21•1•0•Updated Dec 16, 2025Dec 16, 2025

• LightningDiT

  Public
  [CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

  Python

  •

  MIT License

  •52•1.4k•18•1•Updated Dec 16, 2025Dec 16, 2025

• 4DLangVGGT

  Public
  Official implementation of “4D LangVGGT: 4D Language-Visual Geometry Grounded Transformer”

  Python

  •

  MIT License

  •2•79•3•0•Updated Dec 10, 2025Dec 10, 2025

• DiffusionDrive

  Public
  [CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

  Python

  •

  MIT License

  •121•1.3k•24•1•Updated Dec 8, 2025Dec 8, 2025

• EVA-X

  Public
  [npjDigitalMed (Nature Portfolio)] EVA-X: A foundation model for general chest X-ray analysis with self-supervised learning

  Python

  •14•94•6•0•Updated Dec 6, 2025Dec 6, 2025

• MolSight

  Public
  [AAAI 2026] MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning

  Python

  •

  Apache License 2.0

  •0•14•0•0•Updated Dec 5, 2025Dec 5, 2025

• LENS

  Public
  [AAAI 2026 Oral] LENS: Learning to Segment Anything with Unified Reinforced Reasoning

  Python

  •

  Apache License 2.0

  •6•106•15•0•Updated Dec 3, 2025Dec 3, 2025

• Turbo-VAED

  Public
  [AAAI 2026] Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

  Python

  •1•93•12•0•Updated Nov 30, 2025Nov 30, 2025

• RAD

  Public
  [NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

  Python

  •

  MIT License

  •3•183•6•0•Updated Nov 7, 2025Nov 7, 2025

• MaskAdapter

  Public
  [CVPR 2025] Official repository of the paper "Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation"

  segmentationclipzero-shot+ 6open-vocabularyopen-vocabulary-semantic-segmentationvision-language-modelsegment-anythingopen-vocabulary-segmentationzero-shot-segmentation

  Python

  •

  Apache License 2.0

  •4•123•2•0•Updated Oct 23, 2025Oct 23, 2025

• hustvl.github.io

  Public
  HTML

  •

  BSD 3-Clause "New" or "Revised" License

  •2•1•0•0•Updated Oct 11, 2025Oct 11, 2025

• TOGS

  Public
  [IEEE JBHI] The official code of "TOGS: Gaussian Splatting with Temporal Opacity Offset for Real-Time 4D DSA Rendering"

  Python

  •1•31•1•0•Updated Sep 10, 2025Sep 10, 2025

• simpleseg

  Public
  Python

  •0•8•3•0•Updated Sep 9, 2025Sep 9, 2025

• Snap-Snap

  Public
  The repository of "Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds"

  Python

  •2•40•5•0•Updated Sep 1, 2025Sep 1, 2025

• recogdrive

  Public
  ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

  Python

  •

  Apache License 2.0

  •48•7•0•0•Updated Aug 21, 2025Aug 21, 2025

• ViTMatte

  Public
  [Information Fusion (Vol.103, Mar. '24)] Boosting Image Matting with Pretrained Plain Vision Transformers

  Python

  •

  MIT License

  •45•506•19•3•Updated Aug 13, 2025Aug 13, 2025

• Dynamic-2DGS

  Public
  [ACM MM 2025] Dynamic 2D Gaussians: Geometrically Accurate Radiance Fields for Dynamic Objects

  3d-vision4d-reconstructiondynamic-reconstruction+ 3gaussian-splatting3d-gaussian-splatting4d-gaussian-splatting

  Python

  •

  Apache License 2.0

  •6•170•3•0•Updated Aug 6, 2025Aug 6, 2025

• .github

  Public
  0•0•0•0•Updated Jul 4, 2025Jul 4, 2025

• GroundingSuite

  Public
  [ICCV 2025] GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

  Python

  •1•73•2•0•Updated Jun 26, 2025Jun 26, 2025

• PersonViT

  Public
  PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification

  Python

  •

  Apache License 2.0

  •7•41•2•0•Updated Jun 11, 2025Jun 11, 2025

• MIM4D

  Public
  [IJCV 2025] MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning

  Python

  •

  Apache License 2.0

  •1•76•2•0•Updated May 30, 2025May 30, 2025

• PixelHacker

  Public
  PixelHacker: Image Inpainting with Structural and Semantic Consistency

  Python

  •

  Apache License 2.0

  •20•473•14•1•Updated May 20, 2025May 20, 2025