I am Ziheng Cheng, a second-year PhD student in Department of IEOR, UC Berkeley and fortunately supervised by Xin Guo. Prior to that, I got my B.S. degree in School of Mathematical Sciences, Peking University, supervised by Cheng Zhang. I was also very fortunate to have worked with Song Mei, Kun Yuan, Tengyu Ma. My research interests span broadly in statistics, optimization and machine learning, including multi-agent RL, language models and diffusion models, distributed optimization, sampling and variational inference. If you are interested in my research, please feel free to contact me.

News

• Sep, 2025 Our paper “Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning” accepted at ICML 2026!
• Jan, 2026 Join Bytedance Seed at San Jose as an intern! Looking forward to working on LLM pretraining!
• Sep, 2025 A new paper “Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and State” on Arxiv!
• Sep, 2025 A new paper “Data-Effient Training by Evolved Sampling” on Arxiv!
• Sep, 2025 Our paper “OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models”, “Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning” accepted at NeurIPS 2025!
• Jan, 2025 Our paper “Convergence of Distributed Adaptive Optimization with Local Updates” accepted at ICLR 2025!

Selected Publications

• (ICML 2026) Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
  Ziheng Cheng*, Yixiao Huang*, Hanlin Zhu, Haoran Geng, Somayeh Sojoudi, Jitendra Malik, Pieter Abbeel, Xin Guo
  [Arxiv]

• (Preprint) Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and State
  Ziheng Cheng, Xin Guo, Yufei Zhang
  [Arxiv]

• (NeurIPS 2025) OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
  Ziheng Cheng*, Yixiao Huang*, Hui Xu, Somayeh Sojoudi, Xuandong Zhao, Dawn Song, Song Mei
  [Arxiv]

• (NeurIPS 2025) Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
  Ziheng Cheng, Tianyu Xie, Shiyue Zhang, Cheng Zhang
  [Arxiv]

• (Preprint) Semi-Implicit Functional Gradient Flow
  Shiyue Zhang*, Ziheng Cheng*, Cheng Zhang
  [Arxiv]

• (ICLR 2025) Convergence of Distributed Adaptive Optimization with Local Updates
  Ziheng Cheng, Margalit Glasgow
  [Arxiv]

• (COLT 2024) The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication
  Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro
  [Arxiv]

• (ICML 2024) Kernel Semi-Implicit Variational Inference
  Ziheng Cheng*, Longlin Yu*, Tianyu Xie, Shiyue Zhang, Cheng Zhang
  [Arxiv]

• (ICLR 2024) Momentum Benefits Non-IID Federated Learning Simply and Provably
  Ziheng Cheng*, Xinmeng Huang*, Pengfei Wu, Kun Yuan
  [Arxiv]

Industry Experiences

• Bytedance Seed
  Research Intern, working on LLM pretraining
  Jan. 2026 – Present

• Microsoft Research Asia
  Research Intern, working on data selection
  Oct. 2023 – May. 2024