Hao Cheng

Researcher, Microsoft Research

Joined

September 2019

Names

Hao Cheng (Preferred)

Emails

****@uw.edu (Confirmed)

****@gmail.com (Confirmed)

****@microsoft.com (Confirmed)

Personal Links

Career & Education History

Researcher

Microsoft Research (microsoft.com)

2020 – Present

PhD student

University of Washington, Seattle (uw.edu)

2014 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Mari Ostendorf

2014 – 2019

Expertise

deep learning

Present

question answering

Present

conversational AI

Present

natural language processing

Present

Publications

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Xiao Yu, Baolin Peng, Ruize Xu, Michel Galley, Hao Cheng, Suman Nath, Jianfeng Gao, Zhou Yu
- ICLR 2026 Workshop World Models
- Readers: Everyone
Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Xiao Yu, Baolin Peng, Ruize Xu, Michel Galley, Hao Cheng, Suman Nath, Jianfeng Gao, Zhou Yu
- Submitted to ICLR 2026
- Readers: Everyone
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Xiao Yu, Baolin Peng, Michel Galley, Hao Cheng, Qianhui Wu, Janardhan Kulkarni, Suman Nath, Zhou Yu, Jianfeng Gao
- ICLR 2026 Poster
- Readers: Everyone
Coupling Attention and Memory: A Dynamic Memory Module for Efficient Adapation with Pretrained LLMs
Shenyu Zhang, Hao Cheng, Jianfeng Liu, Xiaodong Liu, Yuefeng Zhan, Yongrui Chen, Hao Sun, Weiwei Deng, Feng Sun, Guilin Qi, Jianfeng Gao, Qi Zhang
- Submitted to ICLR 2026
- Readers: Everyone
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
Xiangru Tang, Tianrui Qin, Yanjun Shao, Ziyang Zhou, Jiapeng Chen, Tianhao Peng, Tingting Du, Peng Xia, Fang Wu, He Zhu, Jiaheng Liu, Xingyao Wang, Sirui Hong, Chenglin Wu, Hao Cheng, Chi Wang, Wangchunshu Zhou
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Training Large Reasoning Models Efficiently via Progressive Thought Encoding
Zeliang Zhang, Xiaodong Liu, Hao Cheng, Hao Sun, Chenliang Xu, Jianfeng Gao
- ICLR 2026 Poster
- Readers: Everyone
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
Liliang Ren, Congcong Chen, Haoran Xu, Young Jin Kim, Adam Atkinson, Zheng Zhan, Jiankai Sun, Baolin Peng, Liyuan Liu, Shuohang Wang, Hao Cheng, Jianfeng Gao, Weizhu Chen, yelong shen
- ES-FoMo III
- Readers: Everyone
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Yiping Wang, Qing Yang, Zhiyuan Zeng, Liliang Ren, Liyuan Liu, Baolin Peng, Hao Cheng, Xuehai He, Kuan Wang, Jianfeng Gao, Weizhu Chen, Shuohang Wang, Simon Shaolei Du, yelong shen
- NeurIPS 2025 poster
- Readers: Everyone
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
Liliang Ren, Congcong Chen, Haoran Xu, Young Jin Kim, Adam Atkinson, Zheng Zhan, Jiankai Sun, Baolin Peng, Liyuan Liu, Shuohang Wang, Hao Cheng, Jianfeng Gao, Weizhu Chen, yelong shen
- NeurIPS 2025 poster
- Readers: Everyone
SAS: Simulated Attention Score
Chuanyang Zheng, Jiankai Sun, Yihang Gao, Yuehao Wang, Peihao Wang, Jing Xiong, Liliang Ren, Hao Cheng, Janardhan Kulkarni, yelong shen, Zhangyang Wang, Mac Schwager, Anderson Schneider, Xiaodong Liu, Jianfeng Gao
- NeurIPS 2025 poster
- Readers: Everyone

View all 146 publications

Co-Authors

View all 269 co-authors