Haozhe Wang
Scholar

Haozhe Wang

Google Scholar ID: V96YGIMAAAAJ
PhD student, Hong Kong University of Science and Technology
large language modelsreinforcement learning
Citations & Impact
All-time
Citations
265
 
H-index
10
 
i10-index
10
 
Publications
20
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • Multiple papers accepted at top conferences, such as two first-authored papers, Pixel-Reasoner and VL-Rethinker, accepted at NeurIPS 2025 (24.5%), with VL-Rethinker getting a spotlight (3%). Also released several research tools or frameworks like REER, Hierarchical-Reasoner, VerlTool, AlphaMed, etc.
Research Experience
  • Prior to joining HKUST, worked as a Research Engineer at Alibaba, under the guidance of Dr. Chao Du. These experiences allowed deepening expertise in AI and machine learning while contributing to impactful industry projects.
Education
  • PhD student at the Hong Kong University of Science and Technology (HKUST), advised by Prof. Fangzhen Lin; in close collaboration with Prof. Wenhu Chen at the University of Waterloo and Ge Zhang at ByteDance Seed. Recipient of the Hong Kong PhD Fellowship Scheme (HKPFS), with only 300 awardees across Hong Kong each year. Recognized as one of the Outstanding Graduates of Shanghai (top 1% province-wide) when studying at ShanghaiTech, and awarded the prestigious National Scholarship (top 0.2% nation-wide) at Wuhan University in 2017.
Background
  • Research interests include Large Language Models (LLMs) and Vision-Language Models (VLMs), Reasoning, RL, and agents. Recent work focuses on developing RL-based approaches to enhance VLM and LLM reasoning.
Miscellany
  • Actively seeking research collaboration and opportunities in VLMs, RL, and agents, preferably remote.
Co-authors
0 total
Co-authors: 0 (list not available)