Hao Sun

Researcher, Google DeepMind

Joined

September 2017

Names

Hao Sun (Preferred)

Emails

****@gmail.com (Confirmed)

****@ie.cuhk.edu.hk (Confirmed)

****@cam.ac.uk (Confirmed)

****@google.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Google DeepMind (google.com)

2025 – Present

PhD student

University of Cambridge (cam.ac.uk)

2021 – 2025

Advisors, Relations & Conflicts

No relations added

Expertise

Large Language Models

2023 – Present

Reinforcement Learning

2018 – Present

Publications

Improving Interactive In-Context Learning from Natural Language Feedback
Martin Klissarov, Jonathan Cook, Diego Antognini, Hao Sun, Jingling Li, Natasha Jaques, Claudiu Cristian Musat, Edward Grefenstette
- OpenReview Archive Direct Upload
- Readers: Everyone
Advancing LLM Reasoning with Natural Language and Numerical Feedback
Xiaoying Zhang, Hao Sun, Yipeng Zhang, Kaituo Feng, Chaochao Lu, Chao Yang, Helen M. Meng
- Submitted to ICLR 2026
- Readers: Everyone
Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes
Kasia Kobalczyk, Claudio Fanconi, Hao Sun, Mihaela van der Schaar
- MoFA Oral
- Readers: Everyone
OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of LLMs
Hao Sun, Yunyi Shen, Mihaela van der Schaar
- Submitted to NeurIPS 2025 Position Paper Track
- Readers: Everyone
Understanding the Sources of Uncertainty for Large Language and Multimodal Models
Ziran Yang, Shibo Hao, Hao Sun, Lai Jiang, Qiyue Gao, Yian Ma, Zhiting Hu
- QUESTION Poster
- Readers: Everyone
Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment
Yunyi Shen, Hao Sun, Jean-Francois Ton
- ICML 2025 poster
- Readers: Everyone
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
Thomas Pouplin, Kasia Kobalczyk, Hao Sun, Mihaela van der Schaar
- ICML 2025 spotlightposter
- Readers: Everyone
LLMs for Generalizable Language-Conditioned Policy Learning under Minimal Data Requirements
Thomas Pouplin, Kasia Kobalczyk, Hao Sun, Mihaela van der Schaar
- Submitted to ICLR 2025
- Readers: Everyone
Retrieval Augmented Thought Process for Private Data Handling in Healthcare
Thomas Pouplin, Hao Sun, Samuel Holt, Mihaela van der Schaar
- Submitted to ICLR 2025
- Readers: Everyone
Rethinking Reward Modeling in Preference-based Large Language Model Alignment
Hao Sun, Yunyi Shen, Jean-Francois Ton
- ICLR 2025 Oral
- Readers: Everyone

View all 37 publications

Co-Authors

View all 77 co-authors