Scholar
Bo Liu (Benjamin Liu)
Google Scholar ID: ta7ReHYAAAAJ
PhD student, National University of Singapore | Prev DeepSeek, Peking University
Citations & Impact
Citations
2,292
H-index
12
i10-index
12
Publications
18
Co-authors
28
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published papers include 'Natural Language Reinforcement Learning' (ICLR 2025 Workshop SSI-FM) and 'DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search' (ICLR 2025); released models such as DeepSeek-Prover-V1.5, DeepSeek-Prover, DeepSeek-V2, DeepSeek-VL, and DeepSeek-LLM; open-source project TorchOpt accepted as a PyTorch Ecosystem project.
Research Experience
- Worked as a Research Scientist Intern at Meta FAIR with Jason Weston on scalable self-improvement with self-play for LLMs; collaborated with Prof. Natasha Jaques from the University of Washington; Student Researcher at DeepSeek on foundation models; Research Assistant working closely with Prof. Jun Wang and Prof. Yaodong Yang.
Education
- Ph.D. student at the National University of Singapore, Department of Computer Science, advised by Prof. Wee Sun Lee and Prof. David Hsu; B.S. in Machine Intelligence and B.A. in Economics from Peking University, advised by Prof. Zongqing Lu.
Background
- Research interests: Reinforcement Learning, Reasoning, and Machine Learning Systems with applications in complex, real-world environments. Aiming to build an autonomous decision-making system that can act intelligently in any unknown environment.
Miscellany
- Enjoys playing soccer in his free time and is open to collaborating on exploring the potential of reinforcement learning across various fields.
