Scholar
Yuzhen Huang
Google Scholar ID: XZK8cewAAAAJ
Hong Kong University of Science and Technology, SJTU
Citations & Impact
Citations
1,019
H-index
5
i10-index
4
Publications
7
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild (COLM 2025)
- SimpleRL: 7B Model and 8K Examples: Emerging Reasoning with Reinforcement Learning is Both Effective and Efficient (Notion)
- Predictive Data Selection: The Data That Predicts Is the Data That Teaches (ICML 2025)
- B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners (ICLR 2025)
- Compression Represents Intelligence Linearly (COLM 2024)
- C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models (NeurIPS 2023)
Research Experience
- Currently pursuing a PhD in the Department of Computer Science and Engineering at The Hong Kong University of Science and Technology, focusing on large language models' reasoning capabilities and multimodal understanding.
Education
- Received a bachelor's degree in Computer Science from Shanghai Jiao Tong University in 2023. Currently a second-year PhD student in the Department of Computer Science and Engineering at The Hong Kong University of Science and Technology, advised by Prof. Junxian He.
Background
- Research Interests: Large language models, particularly in advancing their reasoning capabilities and multimodal understanding. Research directions include enhancing reasoning and planning abilities through self-improvement and RL techniques; developing reliable evaluation methods for language models; improving the architecture and training methods of multimodal models to strengthen their understanding across multiple modalities.
Miscellany
- Open to collaboration
