Haizhong Zheng

Postdoctoral Researcher @ CMU
Ph.D. @ UMich
Email: haizhonz@andrew.cmu.edu

haizhong.jpeg

I am a postdoctoral researcher at InfiniAI Lab advised by Prof. Beidi Chen at Carnegie Mellon University. I am also a member of Catalyst Group at CMU. I received my Ph.D. degree from University of Michigan and was advised by Prof. Atul Prakash. Before that, I obtained my B.S. and M.S. degree from Shanghai Jiao Tong University, where I was advised by Prof. Haojin Zhu.

Research Interests: Efficient RL for LLMs; ML system; Agent; ML Security.

News

Oct 2026 New preprint: ServeLearnBench, a benchmark for how well agents self-improve from serving experience. [arXiv] [Code]
Oct 2026 Three papers accepted to NeurIPS 2026: AstraFlow, MonarchRT, and ARA.
Aug 2026 Two papers accepted to EMNLP 2026: one to the Main Conference and one to Findings.
May 2026 AstraFlow is released. Check out the GitHub repo.
May 2026 XRPO accepted to ICML 2026.

Selected Publications

* indicates equal contribution.

Preprint

  1. Preprint 2026
    ServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?
    Haizhong Zheng , Yizhuo Di , Ranajoy Sadhukhan , Shuowei Jin , and Beidi Chen
    arXiv Blog Code
  2. Preprint 2026
    Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models
    Yang Zhou , Ranajoy Sadhukhan , Zhaofeng Sun , Zhuoming Chen , Souvik Kundu , Saket Dingliwal , Sai Muralidhar Jayanthi , Aram Galstyan , Haizhong Zheng , and Beidi Chen
    arXiv Code

Conference

  1. NeurIPS 2026
    AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
    Haizhong Zheng , Yizhuo Di , Jiahui Wang , Shuowei Jin , Xueshen Liu , Yongji Wu , Z. Morley Mao , Ion Stoica , Jiawei Zhao , and Beidi Chen
    arXiv Blog Code
  2. NeurIPS 2026
    The Last Human-Written Paper: Agent-Native Research Artifacts
    Jiachen Liu , Jiaxin Pei , Jintao Huang , Chenglei Si , Ao Qu , Xiangru Tang , Runyu Lu , Lichang Chen , Xiaoyan Bai , Haizhong Zheng +27 more
    arXiv
  3. NeurIPS 2026
    MonarchRT: Efficient Attention for Real-Time Video Generation
    Krish Agarwal , Zhuoming Chen , Cheng Luo , Yongqi Chen , Haizhong Zheng , Xun Huang , Atri Rudra , and Beidi Chen
    arXiv Blog Code
  4. EMNLP 2026
    CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents
    Jaewon Jung , Haizhong Zheng , Hongsun Jang , Jaeyong Song , Beidi Chen , and Jinho Lee
  5. EMNLP 2026
    (Findings) Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Grounding
    Hyunho Kook , Junhyuk So , Tianyu Fu , Haizhong Zheng , and Beidi Chen
  6. ACL 2026
    When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
    Yibo Peng* , James Song* , Lei Li* , Xinyu Yang , Mihai Christodorescu , Ravi Mangal , Corina Pasareanu , Haizhong Zheng , and Beidi Chen
    arXiv Blog Code
  7. ICML 2026
    XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation
    Udbhav Bamba* , Minghao Fang* , Yifan Yu , Haizhong Zheng , and Fan Lai
    arXiv
  8. ICLR 2026
    Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
    Haizhong Zheng , Jiawei Zhao , and Beidi Chen
    arXiv Blog Code
  9. ICLR 2026
    Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement Learning
    Zhuoming Chen* , Hongyi Liu* , Yang Zhou* , Haizhong Zheng , and Beidi Chen
    arXiv Code
  10. ICLR 2026
    OPPO: Accelerating PPO-based RLHF via Pipeline Overlap
    Kaizhuo Yan* , YingJie Yu* , Yifan Yu , Haizhong Zheng , and Fan Lai
    arXiv
  11. CHI 2026
    EchoScriptor: Automatic Lifelogging Narratives via Activity-Based Audio–Language Model
    Kaylee Yaxuan Li , Xinghao Zhou , Haizhong Zheng , Kang G. Shin , and Alanson P. Sample
    DOI
  12. NSDI 2026
    RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
    Yongji Wu* , Xueshen Liu* , Haizhong Zheng , Juncheng Gu , Beidi Chen , Z. Morley Mao , Arvind Krishnamurthy , and Ion Stoica
    arXiv Code
  13. ASPLOS 2026
    WAVE: Leveraging Architecture Observation for Privacy-Preserving Model Oversight
    Haoxuan Xu* , Chen Gong* , Beijie Liu* , Haizhong Zheng , Beidi Chen , and Mengyuan Li
  14. NeurIPS 2025
    Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
    Haizhong Zheng , Yang Zhou , Brian R. Bartoldson , Bhavya Kailkhura , Fan Lai , Jiawei Zhao , and Beidi Chen
    arXiv Blog Code
  15. NeurIPS 2025
    Kinetics: Rethinking Test-Time Scaling Laws
    Ranajoy Sadhukhan* , Zhuoming Chen* , Haizhong Zheng , Yang Zhou , Emma Strubell , and Beidi Chen
    arXiv Blog Code
  16. COLM 2025
    Plato: Plan to Efficiently Decode for Large Language Model Inference
    Shuowei Jin* , Xueshen Liu* , Yongji Wu* , Haizhong Zheng , Qingzhao Zhang , Atul Prakash , Matthew Lentz , Danyang Zhuo , Feng Qian , and Z. Morley Mao
    arXiv
  17. ICLR 2025
    ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
    Haizhong Zheng* , Elisa Tsai* , Yifu Lu , Jiachen Sun , Brian R. Bartoldson , Bhavya Kailkhura , and Atul Prakash
    arXiv
  18. WWW 2025
    Harmful Terms and Where to Find Them: Measuring and Modeling Unfavorable Financial Terms and Conditions in Shopping Websites at Scale
    Elisa Tsai , Neal Mangaokar , Boyuan Zheng , Haizhong Zheng , and Atul Prakash
    Oral
    arXiv
  19. NeurIPS 2024
    Learn To be Efficient: Build Structured Sparsity in Large Language Models
    Haizhong Zheng , Xiaoyan Bai , Xueshen Liu , Z. Morley Mao , Beidi Chen , Fan Lai , and Atul Prakash
    Spotlight
    arXiv
  20. ECCV 2024
    Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation
    Haizhong Zheng , Jiachen Sun , Shutong Wu , Bhavya Kailkhura , Z. Morley Mao , Chaowei Xiao , and Atul Prakash
    arXiv
  21. ICLR 2024
    CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
    Jiachen Sun , Haizhong Zheng , Qingzhao Zhang , Atul Prakash , Z. Morley Mao , and Chaowei Xiao
    arXiv
  22. ICLR 2023
    Coverage-centric Coreset Selection for High Pruning Rates
    Haizhong Zheng , Rui Liu , Fan Lai , and Atul Prakash
    arXiv Code
  23. CVPR 2020
    Efficient Adversarial Training with Transferable Adversarial Examples
    Haizhong Zheng , Ziqi Zhang , Juncheng Gu , Honglak Lee , and Atul Prakash
    arXiv Code
  24. NDSS 2018
    Smoke Screener or Straight Shooter: Detecting Elite Sybil Attacks in User-Review Social Networks
    Haizhong Zheng , Minhui Xue , Hao Lu , Shuang Hao , Haojin Zhu , Xiaohui Liang , and Keith Ross
    arXiv

Work Experience

Research Intern, Lawrence Livermore National Laboratory (LLNL), Livermore, CA May 2023 - Aug. 2023

Applied Scientist Intern, Amazon Web Services (AWS), Inc., Seattle, WA May 2021 - Aug. 2021