Skip to content
@baaivision

BAAI-Vision

Foundation model fanatics from BAAI.

Pinned Loading

  1. Emu3.5 Emu3.5 Public

    Native Multimodal Models are World Learners

    Python 1.4k 54

  2. Emu3 Emu3 Public

    Next-Token Prediction is All You Need

    Python 2.3k 90

  3. Emu Emu Public

    Emu Series: Generative Multimodal Models from BAAI

    Python 1.8k 84

  4. EVA EVA Public

    EVA Series: Visual Representation Fantasies from BAAI

    Python 2.6k 189

  5. Painter Painter Public

    Painter & SegGPT Series: Vision Foundation Models from BAAI

    Python 2.6k 181

  6. See3D See3D Public

    [CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

    Python 706 18

Repositories

Showing 10 of 22 repositories
  • URSA Public

    [ICLR 2026] 🐻 Uniform Discrete Diffusion with Metric Path for Video Generation

    baaivision/URSA’s past year of commit activity
    Python 94 Apache-2.0 2 1 0 Updated Jan 15, 2026
  • Uni3D Public

    [ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI

    baaivision/Uni3D’s past year of commit activity
    Python 640 MIT 43 22 1 Updated Jan 12, 2026
  • Emu Public

    Emu Series: Generative Multimodal Models from BAAI

    baaivision/Emu’s past year of commit activity
    Python 1,764 Apache-2.0 84 46 0 Updated Jan 12, 2026
  • Emu3 Public

    Next-Token Prediction is All You Need

    baaivision/Emu3’s past year of commit activity
    Python 2,302 Apache-2.0 90 66 0 Updated Jan 12, 2026
  • Emu3.5 Public

    Native Multimodal Models are World Learners

    baaivision/Emu3.5’s past year of commit activity
    Python 1,436 Apache-2.0 54 29 0 Updated Dec 30, 2025
  • NOVA Public

    [ICLR 2025] Autoregressive Video Generation without Vector Quantization

    baaivision/NOVA’s past year of commit activity
    Python 624 Apache-2.0 21 0 0 Updated Oct 29, 2025
  • UniVLA Public

    [ICLR 2026] Unified Vision-Language-Action Model

    baaivision/UniVLA’s past year of commit activity
    Python 271 20 2 1 Updated Oct 15, 2025
  • MTVCraft Public

    MTVCraft: An Open Veo3-style Audio-Video Generation Demo

    baaivision/MTVCraft’s past year of commit activity
    Python 98 Apache-2.0 12 4 0 Updated Oct 8, 2025
  • CoS Public

    [NeurIPS 2025] Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards

    baaivision/CoS’s past year of commit activity
    Python 17 Apache-2.0 0 0 0 Updated Oct 6, 2025
  • EVE Public

    EVE Series: Encoder-Free Vision-Language Models from BAAI

    baaivision/EVE’s past year of commit activity
    Python 366 MIT 13 2 0 Updated Jul 24, 2025