Skip to content
Change the repository type filter

All

    Repositories list

    • PAP

      Public
      Panoramic Affordance Prediction (PAP)
      01900Updated Mar 10, 2026Mar 10, 2026
    • MTI

      Public
      Official implementation of "Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention"
      Python
      03710Updated Mar 9, 2026Mar 9, 2026
    • UniCalli

      Public
      Official implementation of UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy
      Python
      1719220Updated Feb 26, 2026Feb 26, 2026
    • TiViBench

      Public
      [CVPR 2026] TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
      Python
      16520Updated Feb 21, 2026Feb 21, 2026
    • LatentMorph: Morphing Latent Reasoning into Image Generation
      Python
      03710Updated Feb 3, 2026Feb 3, 2026
    • Official Implementation of Paper [DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation]
      Python
      27310Updated Dec 29, 2025Dec 29, 2025
    • A4-Agent

      Public
      A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning
      Python
      03500Updated Dec 17, 2025Dec 17, 2025
    • DA-2

      Public
      Official implementation of DA²: Depth Anything in Any Direction
      Python
      Apache License 2.0
      2025230Updated Dec 9, 2025Dec 9, 2025
    • Lotus-2

      Public
      Official implementation of Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
      Python
      Apache License 2.0
      1323940Updated Dec 8, 2025Dec 8, 2025
    • Lotus

      Public
      Official implementation of Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
      Python
      Apache License 2.0
      45785180Updated Nov 28, 2025Nov 28, 2025
    • Python
      1118800Updated Nov 13, 2025Nov 13, 2025
    • STANCE

      Public
      STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding
      Python
      Apache License 2.0
      11200Updated Oct 28, 2025Oct 28, 2025
    • PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
      Python
      MIT License
      32710Updated Oct 20, 2025Oct 20, 2025
    • Official PyTorch/Diffusers implementation of "RectifiedHR: Enable Efficient High Resolution Image Generation via Energy Rectification"
      Python
      03000Updated Oct 11, 2025Oct 11, 2025
    • ScalingAR

      Public
      Go with Your Gut: Scaling Confidence for Autoregressive Image Generation
      Python
      MIT License
      11900Updated Oct 1, 2025Oct 1, 2025
    • ComfyMind

      Public
      ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback
      Python
      MIT License
      412170Updated Sep 20, 2025Sep 20, 2025
    • MTMamba

      Public
      Python
      64811Updated Jul 30, 2025Jul 30, 2025
    • FractFlow

      Public
      Python
      52510Updated Jul 28, 2025Jul 28, 2025
    • Official implementation of GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs.
      Python
      77240Updated Jul 7, 2025Jul 7, 2025
    • Kiss3DGen

      Public
      [CVPR 2025] Official implementation of "Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation"
      Python
      MIT License
      2529330Updated May 24, 2025May 24, 2025
    • Scale-BEV

      Public
      Python
      05400Updated May 1, 2025May 1, 2025
    • TASC

      Public
      Python
      12710Updated Apr 28, 2025Apr 28, 2025
    • OmniBooth

      Public
      Python
      MIT License
      413300Updated Mar 25, 2025Mar 25, 2025
    • Official implementation of “LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images”
      Python
      MIT License
      47440Updated Mar 21, 2025Mar 21, 2025
    • Official implementation of "Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion" [CVPR2025]
      Python
      Apache License 2.0
      15420Updated Mar 13, 2025Mar 13, 2025
    • Python
      1814700Updated Mar 6, 2025Mar 6, 2025
    • Official implementation of DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation
      Python
      Apache License 2.0
      1312010Updated Jan 23, 2025Jan 23, 2025
    • SyntheOcc

      Public
      Python
      MIT License
      410310Updated Nov 21, 2024Nov 21, 2024
    • [SIGGRAPH 2025] Official implementation of 'Motion Inversion For Video Customization'
      Python
      915360Updated Oct 22, 2024Oct 22, 2024
    • Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics (ECCV2024)
      Python
      Apache License 2.0
      1713360Updated Aug 26, 2024Aug 26, 2024