Scholar
Hanbin Wang
Google Scholar ID: FMHqC7gAAAAJ
Peking University
Citations & Impact
Citations
344
H-index
5
i10-index
4
Publications
9
Co-authors
7
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Preprint: 'Group Pattern Selection Optimization: Let LRMs Pick the Right Pattern for Reasoning'
- Preprint: 'Ui-tars-2 technical report: Advancing gui agent with multi-turn reinforcement learning'
- Preprint: 'From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones'
- Preprint: 'Code-vision: Evaluating multimodal llms logic understanding and code generation capabilities'
- Preprint: 'Process Reinforcement through Implicit Rewards'
- Publication (ACL 2025): 'CODEMENV: Benchmarking Large Language Models on Code Migration'
- Publication (ACL 2025): 'KnowCoder-X: Boosting Multilingual Information Extraction via Code'
- Publication (ICLR 2025): 'Advancing LLM Reasoning Generalists with Preference Trees' (Equal contribution)
- Publication (NAACL 2025): 'Enhancing the Code Debugging Ability of LLMs via Communicative Agent Based Data Refinement' (Equal contribution)
- Publication (TOIS 2024): 'Building A Coding Assistant via the Retrieval-Augmented Language Model' (Equal contribution)
- Publication (ACL 2024): 'INTERVENOR: Prompt the Coding Ability of Large Language Models with the Interactive Chain of Repairing'
Research Experience
- 2025.07 – Present: ByteDance Seed, Beijing
- 2024.07 – 2024.09: Shanghai AI Laboratory, Beijing
- 2023.10 – 2024.07: TsinghuaNLP & ModelBest Inc (面壁智能), Beijing
- 2022.08 – 2024.07: NEUIR Lab, Shenyang
- 2023.03 – 2023.06: The Knowledge Computing Lab, Peking University, Beijing
