I am a Ph.D. student in Computer Science at UC San Diego, advised by Professor Jingbo Shang. My research is about pushing LLMs to solve hard problems in code, such as competitive programming and open-ended optimization. I work on benchmarking, agents, and using LLMs to generate problems and data for training better models. I am also an ICPC World Finals 22nd Place finisher and a Codeforces International Grandmaster. I spent summer 2026 as a Quantitative Research Intern at Jump Trading, and will join Citadel Securities as a Quantitative Research Intern in summer 2027.
Publications
AutoCode-RL: Reinforcement Learning for Code with Verifiable Synthetic Data
Kaiyuan Liu, Zhiming Wang, Zeyu Shen, Yulun Wu, Yeyuan Chen, Shang Zhou, et al.
Under review at ICLR 2027
OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation
Shang Zhou, Wenhao Chai, Kaiyuan Liu, Huanzhi Mao, Qiuyang Mang, Jingbo Shang
Under review at ICLR 2027
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
Runyuan He*, Qiuyang Mang*, Shang Zhou, Kaiyuan Liu, Hanchen Li, et al.
NeurIPS 2026 (Spotlight)
FrontierCS: Evolving Challenges for Evolving Intelligence
Qiuyang Mang*, Wenhao Chai*, Zhifei Li*, Huanzhi Mao*, Shang Zhou*, et al.
ICML 2026
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A Merrill*, Alexander Glenn Shaw*, Nicholas Carlini, et al. (incl. Shang Zhou)
ICLR 2026
AutoCode: LLMs as Problem Setters for Competitive Programming
Shang Zhou*, Zihan Zheng*, Kaiyuan Liu*, Zeyu Shen*, Zerui Cheng*, et al.
ICLR 2026
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
Zihan Zheng*, Zerui Cheng*, Zeyu Shen*, Shang Zhou*, Kaiyuan Liu*, Hansen He*, et al.
NeurIPS 2025 ยท MIT Technology Review
Scaling LLM Inference Efficiently with Optimized Sample Compute Allocation
Kexun Zhang*, Shang Zhou*, Danqing Wang, William Yang Wang, Lei Li
NAACL 2025
Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs
Shang Zhou*, Feng Yao*, Chengyu Dong, Zihan Wang, Jingbo Shang
Findings of ACL 2024