BAAI (@BAAIBeijing) / X

BAAI

184 posts

BAAI

@BAAIBeijing

Beijing Academy of Artificial Intelligence. AI Science and Technology Innovation for Global Sustainable Development.

Beijing, China

Joined March 2020

Pinned
BAAI
@BAAIBeijing
Feb 2
🏆 Breaking: BAAI’s Emu3 Published in Nature! ⚡ Beijing Academy of Artificial Intelligence (BAAI) has marked an important step with its research on multimodal large models, published in @Nature. This is the first time a Chinese research institution has led a large model
00:00
7.8K
BAAI
@BAAIBeijing
Oct 30, 2025
🚀 Introducing Emu3.5 — a large-scale multimodal world model that natively predicts the next vision-language state. 🔥 Trained on over 10T interleaved vision-language tokens and enhanced with reinforcement learning, Emu3.5 achieves powerful multimodal reasoning and generation.
00:00
52K
BAAI
@BAAIBeijing
Sep 17, 2025
We're releasing InfoSeek, a dataset that trained a 3B model to rival Gemini/Sonnet 4.0 on deep research tasks. Here's how. 👇 -The First Open-source Dataset Purpose-built for Deep Research tasks -End-to-end Open Source: Dataset + Data Synthesis Framework -50,000+ High-Quality,
30K
BAAI
@BAAIBeijing
Oct 27, 2025
Pushing the boundaries of humanoids with THOR: Towards Human-level whOle-body Reaction. BAAI THOR is coming soon. #Robotics #AI #WholeBodyControl
00:00
95K
BAAI
@BAAIBeijing
Nov 19, 2022
Introducing AltDiffusion, a multilingual text-image generation model built on @StableDiffusion. Currently supports English, Chinese, Spanish, French, Japanese, Korean, Arabic, Russian and Italian: github.com/FlagAI-Open/Fl… @huggingface Model: huggingface.co/BAAI/AltDiffus…
BAAI
@BAAIBeijing
Jan 30, 2024
BAAI releases BGE-M3, a new member to BGE model series. M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec retrieval). 🔥
GitHub - FlagOpen/FlagEmbedding: Retrieval and Retrieval-augmented LLMs
From github.com
29K
BAAI
@BAAIBeijing
Nov 5, 2025
Real!!! BAAI THOR is here. Inspired by human reflexes, we’ve achieved robust whole-body reactions, enabling humanoids to handle intense interactions in the real world. It’s learned — not programmed. Watch it in action and read the full report 👇 📄 Paper:
00:00
12K
BAAI
@BAAIBeijing
Oct 31, 2025
🎃 This Halloween, Explore Multimodal Universe! 🚀 Explore, navigate, and interact across space and time — all with long-horizon consistency. Guess how many worlds Emu3.5 jumps through? 👀👀 #Emu3_5 #WorldModel #AI #Halloween2025
00:00
12K
BAAI
@BAAIBeijing
Apr 13, 2022
We have noticed the discussion on "A Roadmap of Big Model" and are verifying the issues raised. BAAI encourages academic innovation and exchanges, and holds a zero tolerance policy toward academic misconduct. We will keep you updated.
BAAI
@BAAIBeijing
Dec 21, 2023
Meet Emu2: BAAI's latest open-source multimodal AI model, advancing open and responsible AI research. Explore its capabilities in text and visual tasks with minimal guidance. 🔍 Project: baaivision.github.io/emu2/ 📄 Paper: arxiv.org/abs/2312.13286
9.6K
BAAI
@BAAIBeijing
Mar 3, 2023
Our team has also explored the direction of in-context visual learning for the first time, and developed the generalist vision model, Painter, taking a major step towards achieving the GPT-3 moment in computer vision. This work has been accepted by #CVPR2023. Congratulations!
4.7K
BAAI
@BAAIBeijing
May 31, 2023
Mark your calendars! Join us at the 5th BAAI Conference, a prominent annual international conference in the field of AI. 🗓️Date: June 9-10, 2023 📢Register here: 2023.baai.ac.cn Let's gather together and embark on this grand occasion! #2023BAAIConference
10K
BAAI
@BAAIBeijing
Sep 27, 2024
📢Meet Emu3: state-of-the-art multimodal models trained via next-token prediction. Emu3 beats leading task-specific models (e.g., SDXL, LLaVA 1.6, OpenSora) in both generation & perception—without diffusion or CLIP+LLM. 🔗 Project page: emu.baai.ac.cn/about
4K
BAAI
@BAAIBeijing
Dec 14, 2022
We released a Dreambooth @Gradio Web UI for our AltDiffusion-m9 model (a multilingual text-to-image generation model) on @huggingface Spaces.For details of AltDiffusion, see our previous post：x.com/BAAIBeijing/st… Try out the Naruto or Wukong model -> huggingface.co/spaces/BAAI/dr…
BAAI
@BAAIBeijing
Nov 19, 2022
Introducing AltDiffusion, a multilingual text-image generation model built on @StableDiffusion. Currently supports English, Chinese, Spanish, French, Japanese, Korean, Arabic, Russian and Italian: github.com/FlagAI-Open/Fl… @huggingface Model: huggingface.co/BAAI/AltDiffus…