Scholar
Wei Fu
Google Scholar ID: RwcQRrQAAAAJ
IIIS, Tsinghua University
Citations & Impact
Citations
430
H-index
9
i10-index
8
Publications
15
Co-authors
9
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published several papers including 'Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL', 'AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning', 'ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation'. Some works have been accepted by top conferences like ICML and ICLR.
Research Experience
- Developing the AReaL project, which has accumulated 2.5k GitHub stars. Also involved in projects such as ASearcher and ReaLHF.
Education
- PhD in Computer Science at Tsinghua University (expected graduation: June 2026), advised by Professor Yi Wu; BEng degree from the Department of Electrical Engineering, 2021.
Background
- Research interests: the intersection of reinforcement learning (RL) and distributed systems. Currently focusing on developing AReaL — the fastest and easiest way to scale up agentic RL training for LLM/VLMs. Describes himself more as a programmer than a researcher.
Miscellany
- Enjoys coding, cooking, listening to pop music, and working out at the gym.
