Xinyu Lian

prof_pic.jpg

I am a third-year CS Ph.D. candidate at the University of Illinois Urbana-Champaign, working with Minjia Zhang. I study machine learning systems and reinforcement learning, with a current focus on long-horizon agentic RL.

šŸ™‹ Feel free to reach out via email if you are interested in my research.


šŸ”„ News

Jun 29, 2026 Excited to open-source Arctic-RL, a RL backend that accelerates training by up to 3.5Ɨ.
Apr 1, 2026 Our work SuperOffload received the ASPLOS 2026 Best Paper Honorable Mention.
Mar 2, 2026 I am honored to receive the Microsoft Research Fellowship.
Feb 3, 2025 I am honored to receive the Amazon AI PhD Fellowship.

šŸ“ƒ Selected Papers

  1. EMNLP’26
    Ā  To Appear Ā 
    Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models
    Xinyu Lian,Ā Walid Krichene,Ā Beichen Huang,Ā Masahiro Tanaka,Ā Olatunji Ruwase,Ā Li Zhang,Ā  and Minjia Zhang
    Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. 2026
  2. ASPLOS’26
    Atifact AvailableAtifact FunctionalAtifact Reusable
    SuperOffload: Unleashing the Power of Large-Scale LLM Training on Superchips
    Xinyu Lian,Ā Masahiro Tanaka,Ā Olatunji Ruwase,Ā  and Minjia Zhang
    Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating System. 2026
    šŸ† ASPLOS 2026 Best Paper Award Honorable Mention
    Featured by PyTorch Official Blog
    Presented at PyTorch Conference 2025, Ray x DeepSpeed Meetup
  3. ATC’25
    Atifact AvailableAtifact FunctionalAtifact Reusable
    Universal Checkpointing: A Flexible and Efficient Distributed Checkpointing System for Large-Scale DNN Training with Reconfigurable Parallelism
    Xinyu Lian,Ā Sam Ade Jacobs,Ā Lev Kurilenko,Ā Masahiro Tanaka,Ā Stas Bekman,Ā Olatunji Ruwase,Ā  and Minjia Zhang
    Proceedings of the 2025 USENIX Annual Technical Conference. 2025
    Adopted by Microsoft for Phi-3.5-MoE (42B) Pre-Training
    Adopted by BigScience for BLOOM (176B) Pre-Training
    Adopted by StepFun and Baidu for multimodal model post-training.
    Presented at PyTorch Day 2025, FMS 2025, SDC 2025
  4. ICSE’25
    Atifact AvailableAtifact FunctionalAtifact Reusable
    Large Language Models as Configuration Validators
    Xinyu Lian,Ā Yinfang Chen,Ā Runxiang Cheng,Ā Jie Huang,Ā Parth Thakkar,Ā Minjia Zhang,Ā  and Tianyin Xu
    Proceedings of the 47th IEEE/ACM International Conference on Software Engineering. 2025


šŸ… Awards & Honors

Microsoft Research Fellowship ($43K)
Amazon AI PhD Fellowship ($70K)
ASPLOS 2026 Best Paper Honorable Mention
ASPLOS 2026 Travel Grant
USENIX ATC 2025 Travel Grant
SIGSOFT CAPS Travel Grant
UIUC Conference Presentation Award
Outstanding Graduate of Zhejiang Province

šŸ–ļø Service

Organizer: Brett Daniel Software Engineering Seminar
Program Committee: MSR'25
Reviewer: ICML, NeurIPS, TSE
Artifact Evaluation Committee: SOSP'24