HNHacker News
TopNewBestAskShowJobs

BAAIBeijing

48 karma · joined December 2, 2023

BAAI officially open-sourced RoboBrain-X0, a cross-embodiment foundation model capable of driving multiple real-world robots to perform complex tasks under zero-shot generalization and few-shot fine-tuning conditions. Building upon the multimodal foundation capabilities of RoboBrain and the RoboBrain 2.0 dataset, RoboBrain-X0 further integrates real robotic action data. By jointly modeling vision, language, and actions, it achieves cross-embodiment generalization and adaptation, providing end-to-end capabilities from perception to execution.

RoboBrain-X0 is now fully open-sourced, including pretrained models, datasets, and technical documentation, and is fully integrated with the BAAI RoboBrain 2.0 toolchain. This solution aims to provide a solid starting point for developers to build their own embodied intelligence applications that operate reliably in the real world. •RoboBrain-X0 GitHub: https://github.com/FlagOpen/RoboBrain-X0 •RoboBrain-X0 Multi-Chip Version (FlagRelease):https://huggingface.co/FlagRelease/RoboBrain-X0-FlagOS •RoboBrain-X0 Dataset:https://huggingface.co/datasets/BAAI/RoboBrain-X-Dataset •RoboBrain 2.0 Technical Documentation:https://arxiv.org/abs/2507.02029

submissionscomments

Show HN: FLM- Audio, our 7B spoken dialog chatbot with native full-duplexity

2 pts·BAAIBeijing·
0

InfoSeek: The First Open-Source Framework for Deep Research Data Synthesis

2 pts·BAAIBeijing·
1

BGE-Reasoner: An open-source framework for reasoning-intensive retrieval

github.com·1 pts·BAAIBeijing·
1

Next-Token Prediction Is All Your Need:Emu3 Beats SDXL, LLaVA-1.6, and OpenSora

1 pts·BAAIBeijing·
0

Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model

153 pts·BAAIBeijing·
27

Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model

3 pts·BAAIBeijing·
0

Show HN: A High-Quality Chinese Internet Language Dataset for AI

1 pts·BAAIBeijing·
2