BAAI-Vision

All

22 repositories

URSA
Public
[ICLR 2026] 🐻 Uniform Discrete Diffusion with Metric Path for Video Generation
image-generation video-generation discrete-diffusion diffusion-forcing
Python
•
Apache License 2.0
•2•103•0•0•Updated Feb 6, 2026Feb 6, 2026
Uni3D
Public
[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI
3d-representation-learning vision-transformers foundation-models
Python
•
MIT License
•43•643•22•1•Updated Jan 12, 2026Jan 12, 2026
Emu
Public
Emu Series: Generative Multimodal Models from BAAI
foundation-models in-context-learning multimodal-pretraining instruct-tuning multimodal-generalist generative-pretraining-in-multimodality
Python
•
Apache License 2.0
•84•1.8k•46•0•Updated Jan 12, 2026Jan 12, 2026
Emu3
Public
Next-Token Prediction is All You Need
Python
•
Apache License 2.0
•93•2.3k•66•0•Updated Jan 12, 2026Jan 12, 2026
Emu3.5
Public
Native Multimodal Models are World Learners
Python
•
Apache License 2.0
•57•1.5k•30•0•Updated Dec 30, 2025Dec 30, 2025
NOVA
Public
[ICLR 2025] Autoregressive Video Generation without Vector Quantization
image-generation video-generation diffusion-models autoregressive-models
Python
•
Apache License 2.0
•21•626•0•0•Updated Oct 29, 2025Oct 29, 2025
UniVLA
Public
[ICLR 2026] Unified Vision-Language-Action Model
Python
•20•276•1•1•Updated Oct 15, 2025Oct 15, 2025
MTVCraft
Public
MTVCraft: An Open Veo3-style Audio-Video Generation Demo
Python
•
Apache License 2.0
•12•98•5•0•Updated Oct 8, 2025Oct 8, 2025
CoS
Public
[NeurIPS 2025] Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
Python
•
Apache License 2.0
•0•17•0•0•Updated Oct 6, 2025Oct 6, 2025
EVE
Public
EVE Series: Encoder-Free Vision-Language Models from BAAI
clip vlm instruction-following large-language-models llm mllm multimodal-large-language-models vision-language-models encoder-free-vlm
Python
•
MIT License
•13•368•2•0•Updated Jul 24, 2025Jul 24, 2025
See3D
Public
[CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
Python
•18•708•22•0•Updated Apr 16, 2025Apr 16, 2025
JudgeLM
Public
[ICLR 2025 Spotlight] An open-sourced LLM judge for evaluating LLM-generated answers.
Python
•
Apache License 2.0
•28•416•10•1•Updated Feb 11, 2025Feb 11, 2025
DIVA
Public
[ICLR 2025] Diffusion Feedback Helps CLIP See Better
clip diffusion visual-perception
Python
•
MIT License
•15•299•5•0•Updated Jan 23, 2025Jan 23, 2025
tokenize-anything
Public
[ECCV 2024] Tokenize Anything via Prompting
representation-learning multimodal foundation-models promptable
Jupyter Notebook
•
Apache License 2.0
•25•603•12•0•Updated Dec 11, 2024Dec 11, 2024
Painter
Public
Painter & SegGPT Series: Vision Foundation Models from BAAI
in-context-learning cvpr2023 generalist-model in-context-visual-learning generalist-painter seggpt segmentation-foundation-model
Python
•
MIT License
•180•2.6k•55•4•Updated Dec 6, 2024Dec 6, 2024
DenseFusion
Public
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
vlm image-descriptions visual-perception mllm multimodal-large-language-models vision-language-models
Python
•1•159•4•0•Updated Dec 6, 2024Dec 6, 2024
EVA
Public
EVA Series: Visual Representation Fantasies from BAAI
representation-learning vision-transformer foundation-models
Python
•
MIT License
•189•2.6k•77•1•Updated Aug 1, 2024Aug 1, 2024
CapsFusion
Public
[CVPR 2024] CapsFusion: Rethinking Image-Text Data at Scale
Python
•5•213•8•0•Updated Feb 27, 2024Feb 27, 2024
GeoDream
Public
GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation
3d 3d-generation text-to-3d 3d-aigc
Python
•
Apache License 2.0
•10•497•4•0•Updated Jan 22, 2024Jan 22, 2024
emu2
Public
JavaScript
•0•4•0•0•Updated Dec 21, 2023Dec 21, 2023
vid2vid-zero
Public
Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
Python
•23•357•8•0•Updated Jul 4, 2023Jul 4, 2023
MUSE-Pytorch
Public
An in-context conditioning version of MUSE with pre-trained checkpoints.
Python
•
MIT License
•4•116•5•0•Updated Jun 4, 2023Jun 4, 2023