Repositories list

• aim-uofa.github.io

  Public
  code for aim-uofa.github.io

  JavaScript

  •44 forks•1010 stars•00 issues•00 pull requests•Updated Jun 16, 2026Jun 16, 2026

• COSINE

  Public
  [ICCV'25] Unified Open-World Segmentation with Multi-Modal Prompts

  Python

  •

  Other

  •22 forks•1616 stars•00 issues•00 pull requests•Updated Jun 16, 2026Jun 16, 2026

• STAIR

  Public
  Python

  •11 fork•1818 stars•00 issues•00 pull requests•Updated Jun 13, 2026Jun 13, 2026

• StaMo

  Public
  Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

  roboticsdiffusion-modelsembodied-ai

  roboticsdiffusion-modelsembodied-ai

  Python

  •00 forks•4040 stars•11 issue•00 pull requests•Updated Jun 10, 2026Jun 10, 2026

• ReasonMatch

  Public
  [CVPR2026] Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching

  spatial-reasoningspatial-intelligence

  spatial-reasoningspatial-intelligence

  Python

  •

  Apache License 2.0

  •11 fork•1919 stars•11 issue•00 pull requests•Updated Jun 4, 2026Jun 4, 2026

• GSI-Bench

  Public
  [CVPR2026] Exploring Spatial Intelligence from a Generative Perspective

  spatial-intelligence

  spatial-intelligence

  Python

  •

  Other

  •11 fork•3030 stars•22 issues•00 pull requests•Updated Jun 3, 2026Jun 3, 2026

• TVRBench

  Public
  TVRBench: Target Viewpoint Reproduction Benchmark for Active Spatial Intelligence

  Python

  •

  Apache License 2.0

  •00 forks•2525 stars•00 issues•00 pull requests•Updated Jun 2, 2026Jun 2, 2026

• MARBLE

  Public
  Multi-Aspect Reward Balance for Diffusion RL

  00 forks•3939 stars•11 issue•00 pull requests•Updated May 8, 2026May 8, 2026

• AGILE

  Public
  00 forks•4848 stars•11 issue•00 pull requests•Updated May 6, 2026May 6, 2026

• Active-o3

  Public
  [ICML2026] ACTIVE-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO

  rlactive-visionactive-perception+ 4

  rlactive-visionactive-perceptiono3mllmsgrpothinking-with-image

  11 fork•8383 stars•33 issues•00 pull requests•Updated Apr 30, 2026Apr 30, 2026

• CARVE

  Public
  [CVPR2026] Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation

  BSD 2-Clause "Simplified" License

  •00 forks•1212 stars•00 issues•00 pull requests•Updated Apr 23, 2026Apr 23, 2026

• MMControl

  Public
  00 forks•88 stars•00 issues•00 pull requests•Updated Apr 22, 2026Apr 22, 2026

• OmniJigsaw

  Public
  HTML

  •11 fork•3535 stars•22 issues•00 pull requests•Updated Apr 10, 2026Apr 10, 2026

• EvoTokenDLM

  Public
  [ACL'26] EvoToken-DLM (Beyond Hard Masks: Progressive Token Evolution for Diffusion Language)

  Python

  •22 forks•4848 stars•11 issue•00 pull requests•Updated Apr 7, 2026Apr 7, 2026

• dLLM-MidTruth

  Public
  [ICLR'26] Official PyTorch implementation of "Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models".

  Python

  •

  Apache License 2.0

  •33 forks•6666 stars•22 issues•00 pull requests•Updated Mar 5, 2026Mar 5, 2026

• AutoStory

  Public
  [IJCV'24] AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort

  Jupyter Notebook

  •

  Other

  •55 forks•149149 stars•44 issues•00 pull requests•Updated Mar 5, 2026Mar 5, 2026

• GenDeF

  Public
  Python

  •00 forks•3939 stars•00 issues•00 pull requests•Updated Mar 5, 2026Mar 5, 2026

• PM-Loss

  Public
  [3DV 2026] Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

  Python

  •

  MIT License

  •88 forks•161161 stars•00 issues•00 pull requests•Updated Dec 9, 2025Dec 9, 2025

• Omni-R1

  Public
  [NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

  rlomnimodalmllms+ 2

  rlomnimodalmllmsgrponeurips-2025

  Python

  •66 forks•126126 stars•66 issues•00 pull requests•Updated Dec 3, 2025Dec 3, 2025

• Matcher

  Public
  [ICLR'24 & IJCV‘25] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

  sammatchergeneralist-model+ 2

  sammatchergeneralist-modeldinov2in-context-segmentation

  Python

  •

  Other

  •4343 forks•571571 stars•2323 issues•00 pull requests•Updated Dec 3, 2025Dec 3, 2025

• Diception

  Public
  [NeurIPS 2025 Spotlight] A Generalist Diffusion Model for Vision Perception

  generative-modelsegmentationmulti-task-learning+ 3

  generative-modelsegmentationmulti-task-learningdiffusion-modelnormal-estimationdepth-estimaiton

  Python

  •1414 forks•319319 stars•22 issues•00 pull requests•Updated Sep 21, 2025Sep 21, 2025

• FreeCustom

  Public
  [CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

  Python

  •

  BSD 2-Clause "Simplified" License

  •55 forks•177177 stars•33 issues•00 pull requests•Updated Sep 1, 2025Sep 1, 2025

• Tinker

  Public
  One-shot and Few-shot 3D Editing without Per-Scene Optimization

  1111 forks•175175 stars•33 issues•00 pull requests•Updated Aug 21, 2025Aug 21, 2025

• GVM

  Public
  [SIGGRAPH2025] Generative Video Matting

  generative-modelvideo-matting

  generative-modelvideo-matting

  Python

  •44 forks•9292 stars•55 issues•00 pull requests•Updated Aug 12, 2025Aug 12, 2025

• SegAgent

  Public
  [CVPR2025] SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

  agentsegment-anythingvlms+ 1

  agentsegment-anythingvlmsmllms

  Python

  •

  MIT License

  •44 forks•107107 stars•44 issues•00 pull requests•Updated Aug 8, 2025Aug 8, 2025

• SurfaceSplat

  Public
  SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting

  BSD 2-Clause "Simplified" License

  •00 forks•6060 stars•22 issues•00 pull requests•Updated Jul 21, 2025Jul 21, 2025

• DiverGen

  Public
  DiverGen (CVPR 2024) & BSGAL (ICML 2024)

  active-learninginstance-segmentationlvis+ 2

  active-learninginstance-segmentationlvisgenerative-data-augmentationlong-tailed-segmentation

  Python

  •

  BSD 2-Clause "Simplified" License

  •22 forks•5353 stars•00 issues•00 pull requests•Updated Jul 6, 2025Jul 6, 2025

• SegPrompt

  Public
  Official Implementation of ICCV 2023 Paper - SegPrompt: Boosting Open-World Segmentation via Category-level Prompt Learning

  Python

  •

  BSD 2-Clause "Simplified" License

  •11 fork•112112 stars•11 issue•00 pull requests•Updated May 28, 2025May 28, 2025

• ConvNova

  Public
  Python

  •11 fork•1313 stars•55 issues•00 pull requests•Updated Apr 23, 2025Apr 23, 2025

• PerturboLLaVA

  Public
  Python

  •00 forks•1717 stars•22 issues•00 pull requests•Updated Apr 20, 2025Apr 20, 2025