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 1.3k 45

  2. Emu3 Emu3 Public

    Next-Token Prediction is All You Need

    Python 2.3k 89

  3. Emu Emu Public

    Emu Series: Generative Multimodal Models from BAAI

    Python 1.8k 86

  4. EVA EVA Public

    EVA Series: Visual Representation Fantasies from BAAI

    Python 2.6k 188

  5. Painter Painter Public

    Painter & SegGPT Series: Vision Foundation Models from BAAI

    Python 2.6k 182

  6. See3D See3D Public

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

    Python 705 18

Repositories

Showing 10 of 22 repositories
  • Emu3 Public

    Next-Token Prediction is All You Need

    baaivision/Emu3’s past year of commit activity
    Python 2,252 Apache-2.0 89 65 0 Updated Nov 19, 2025
  • Emu3.5 Public

    Native Multimodal Models are World Learners

    baaivision/Emu3.5’s past year of commit activity
    Python 1,289 Apache-2.0 45 25 0 Updated Nov 19, 2025
  • URSA Public

    🐻 Uniform Discrete Diffusion with Metric Path for Video Generation

    baaivision/URSA’s past year of commit activity
    Python 77 Apache-2.0 2 0 0 Updated Nov 18, 2025
  • NOVA Public

    [ICLR 2025] Autoregressive Video Generation without Vector Quantization

    baaivision/NOVA’s past year of commit activity
    Python 601 Apache-2.0 19 0 0 Updated Oct 29, 2025
  • UniVLA Public

    Unified Vision-Language-Action Model

    baaivision/UniVLA’s past year of commit activity
    Python 243 17 4 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 83 Apache-2.0 10 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 15 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 359 MIT 11 0 0 Updated Jul 24, 2025
  • See3D Public

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

    baaivision/See3D’s past year of commit activity
    Python 705 18 22 0 Updated Apr 16, 2025
  • JudgeLM Public

    [ICLR 2025 Spotlight] An open-sourced LLM judge for evaluating LLM-generated answers.

    baaivision/JudgeLM’s past year of commit activity
    Python 406 Apache-2.0 26 10 1 Updated Feb 11, 2025