Scholar
Hao Sun
Google Scholar ID: 7ZNoHJkAAAAJ
Google DeepMind
Citations & Impact
Citations
1,303
H-index
20
i10-index
30
Publications
20
Co-authors
24
list available
Publications
Resume (English only)
Academic Achievements
- May 2025: Paper 'Multi-Objective and Personalized Alignment with PCA' accepted by ACL findings; two papers on prompt optimization accepted by ACL as main and findings
- May 2025: Papers 'Active Reward Modeling' and a spotlight paper on LLM for RL accepted by ICML
- February 2025: Part IV of Reward Model Paper 'Multi-Objective and Personalized Alignment with PCA' online
- February 2025: Part III of Reward Model Paper 'Infrastructure for Reproducible Reward Model Research' online
- February 2025: Part II of Reward Model Paper 'Active Reward Modeling' online
- January 2025: Part I of Reward Model Paper 'Foundation, Theory, and Alternatives' accepted by ICLR as an oral presentation
Research Experience
- Research Scientist at Google DeepMind
- July 2025: Attended ACL 2025 and ran a tutorial on Inverse RL Meets LLM Alignment in Vienna
- July 2025: Invited talk on RL in the Era of LLMs at Intuit AI research
- June 2025: Invited talk on RL in the Era of LLMs at Jump Trading London
- March 2025: Guest lecture on Inverse RL Meets LLMs at the UCLA Reinforcement Learning course
- February 2025: Attended AAAI 2025 and ran a tutorial on Inverse RL Meets LLMs in Philadelphia
Background
- Research interests include reinforcement learning and large language model alignment. Completed a PhD at the University of Cambridge and currently works as a Research Scientist at Google DeepMind.
Miscellany
- Based in London, UK, active on Twitter, Github, and Google Scholar
