Scholar
Fengshuo Bai
Google Scholar ID: rzt0quQAAAAJ
Shanghai Jiao Tong University
Citations & Impact
Citations
187
H-index
7
i10-index
5
Publications
17
Co-authors
7
list available
Contact
Publications
Resume (English only)
Academic Achievements
- 1. Paper 'STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization' accepted to NeurIPS 2025.
- 2. Paper 'DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation' accepted to NeurIPS 2025 and selected as Spotlight.
- 3. Paper 'ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models' accepted to NeurIPS 2025 Workshop on Regulatable ML (RegML).
- 4. Paper 'AdaptFlow: Adaptive Workflow Optimization via Meta-Learning' accepted to EMNLP 2025.
- 5. Released survey paper 'A Survey on Vision-Language-Action Models: An Action Tokenization Perspective'.
- 6. Paper 'Roadmap on Incentive Compatibility for AI Alignment and Governance in Sociotechnical Systems' accepted to AGI 2025 and selected as Oral.
- 7. Released paper 'Retrieval Dexterity: Efficient Object Retrieval in Clutters with Dexterous Hand'.
- 8. Paper 'Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs' accepted to ICLR 2025.
- 9. Paper 'GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation' accepted to NAACL 2025.
- 10. Paper 'β-DQN: Improving Deep Q-Learning By Evolving the Behavior' accepted to ICML 2025 and selected as Oral.
Research Experience
- Involved in multiple research projects, including publishing papers at top conferences such as NeurIPS and EMNLP.
Education
- Ph.D. Student at the Department of Computer Science and Engineering, Shanghai Jiao Tong University, co-advised by Prof. Yaodong Yang and Prof. Ying Wen; selected into Wen-Tsun Wu AI Honorary Doctoral Class in 2023, advised by Prof. Cewu Lu.
Background
- Currently a Ph.D. Student at the Department of Computer Science and Engineering, Shanghai Jiao Tong University, and a member of PAIR-Lab. Research interests include Dexterous Manipulation, Preference-based RL, and AI Alignment.
