I am Huajie Tan (谭桦杰), a third-year M.S. student at the School of Computer Science, Peking University, advised by Prof. Shanghang Zhang. Previously, I received my dual-degree B.Eng. from Tianjin University (College of Intelligence and Computing & College of Microelectronics) and was honored with the Outstanding Graduate Award.
My research focuses on embodied AI and multi-modal foundation models. I am currently an intern at the Beijing Academy of Artificial Intelligence (BAAI), exploring pathways toward general-purpose robotic intelligence and real-world deployment of embodied systems. I am also open to collaborative opportunities and research partnerships, feel free to email me: tanhuajie@stu.pku.edu.cn.
Meanwhile, I am now seeking entrepreneurship opportunities. I have received multiple top-tier offers from leading industry labs, e.g., Huawei Top Minds (华为天少), Tencent QingYun (腾讯青云), JD Tech Genius Team (京东TGT), BAAI Star (智源智星) and Xiaomi Top Talent (小米顶尖计划). If you have a better fit or would like to connect, please also feel free to reach out.
🔥 News
- 2026.01: 🔥 Released RoboBrain 2.5, our more powerful embodied foundation model (first author, project lead).
- 2026.01: 🎯 Released our new research paper Action-Sketcher (first author, project lead).
- 2025.12: 🎯 Released our new research paper Robo-Dopamine (first author, project lead).
- 2025.10: 🔥 Released LLaVA-OneVision-1.5, a fully open framework for democratized MLLM training.
- 2025.10: 🔥 Released more advanced RoboOS-NeXT (first author, project lead).
- 2025.09: 🎉 Reason-RFT accepted to NeurIPS 2025. See you in San Diego, USA!
- 2025.06: 🎉 Released RoboBrain 2.0 and RoboOS in BAAI Conference 2025 (first author, project lead).
- 2025.04: 🌍 RoboBrain 1.0 selected for CVPR 2025’s official Embodied AI Trends Commentary.
- 2025.02: 🎉 RoboBrain 1.0 accepted to CVPR 2025.
📝 Publications
RoboBrain 2.5: Depth in Sight, Time in Mind.
BAAI RoboBrain Team
Co-First Author, Project Lead, Technical Report 2026
RoboBrain 2.0: See Better. Think Harder. Do Smarter.
BAAI RoboBrain Team
Co-First Author, Core Contributor, Technical Report 2025
Project | Paper | Code 
LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
LLaVA-OneVision Community Contributors
Core Contributor, Technical Report 2025
Paper | Code 
Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
Huajie Tan*, Yuheng Ji*, Xiaoshuai Hao*, Xiansheng Chen, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang
Co-First Author, NeurIPS 2025
Project | Paper | Code 
RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete
Yuheng Ji*, Huajie Tan*, Jiayu Shi*, Xiaoshuai Hao*, Yuan Zhang, Hengyuan Zhang, Pengwei Wang, Mengdi Zhao, Yao Mu, Pengju An, Xinda Xue, Qinghang Su, Huaihai Lyu, Xiaolong Zheng, Jiaming Liu, Zhongyuan Wang, Shanghang Zhang
Co-First Author, CVPR 2025
Project | Paper | Code 
Huajie Tan*, Cheng Chi*, Xiansheng Chen*, Yuheng Ji*, Zhongxia Zhao, Xiaoshuai Hao, Yaoxu Lyu, Mingyu Cao, Junkai Zhao, Huaihai Lyu, Enshen Zhou, Ning Chen, Yankai Fu, Cheng Peng, Wei Guo, Dong Liang, Zhuo Chen, Mengsi Lyu, Chenrui He, Yulong Ao, Yonghua Lin, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang
Co-First Author, Project Lead, ArXiv 2025
Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation
Huajie Tan*, Sixiang Chen*, Yijie Xu*, Zixiao Wang, Yuheng Ji, Cheng Chi, Yaoxu Lyu, Zhongxia Zhao, Xiansheng Chen, Peterson Co, Shaoxuan Xie, Guocai Yao, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang
Co-First Author, Project Lead, ArXiv 2025
Project | Paper | Code 
Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation
Huajie Tan*, Peterson Co*, Yijie Xu*, Shanyu Rong, Yuheng Ji, Cheng Chi, Xiansheng Chen, Qiongyu Zhang, Zhongxia Zhao, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang
Co-First Author, Project Lead, ArXiv 2026
📖 Educations
- 2023.09 - 2026.06, Master, School of Computer Science, Peking University, Beijing.
- 2019.09 - 2023.06, Undergraduate, College of Intelligence and Computing & School of Microelectronics, Tianjin University, Tianjin.
💻 Internships
- 2024.12 - now, Beijing Academy of Artificial Intelligence (BAAI), Beijing.
- 2024.05 - 2024.11, DeepGlint, Beijing.
👥 Services
- Served as reviewer for CVPR, ICCV, NeurIPS, ICRA
- Active open-source contributor to huggingface/transformers, huggingface/smolagents
- Teaching Assistant, Fundamentals of Artificial Intelligence (Instructor: Prof. Shanghang Zhang)