Bio
Hi there! I'm a CS Ph.D student at Rice University. My advisor is
Dr. Xia Ben Hu. I got my B.S. degree in physics from University of Science and Technology of China(USTC). I previously worked with
Dr. Ang Chen on network system and security.
Research Interests
I design efficient machine learning algorithms and systems using techniques such as sparsification
and speculative decoding, while improving system robustness and security.
My research centers on LLM post-training, including efficiency, long-context, LLM agents,
routing, and security.
I am seeking full-time research scientist/engineer positions. Please feel free to contact me regarding any opportunities!
Industry Experiences
Amazon Web Services
Applied Science Intern, Annapurna Lab
|
Santa Clara, CA
May 2025 – Aug 2025
|
Amazon Web Services
Applied Science Intern, Deep Engine
|
Santa Clara, CA
May 2024 – Aug 2024
|
Publications
Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs
Rui Pan, Zhuofu Chen,
Hongyi Liu, Arvind Krishnamurthy, Ravi Netravali
Preprint
Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
Hongyi Liu, Jiaji Huang, Zhen Jia, Youngsuk Park, Yu-Xiang Wang
To appear in ICLR 2026
RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers
Yifan Lu, Rixin Liu, Jiayi Yuan, Xingqi Cui, Shenrun Zhang,
Hongyi Liu, Jiarong Xing
To appear in ICLR 2026
Who Routes the Router: Rethinking the Evaluation of LLM Routing Systems
Jiayi Yuan, Yifan Lu, Rixin Liu, Yu-Neng Chuang,
Hongyi Liu, Shaochen Zhong, Yang Sui, Guanchu Wang, Jiarong Xing, Xia Hu
Preprint
Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration
Songyuan Sui,
Hongyi Liu, Serena Liu, Li Li, Soo-Hyun Choi, Rui Chen, Xia Hu
AACL'25 (Oral)
AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Model
Feng Luo, Yu-Neng Chuang, Guanchu Wang, Hoang Anh Duy Le, Shaochen Zhong,
Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, Xia Hu
Preprint
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Yang Sui, Yu-Neng Chuang, Guanchu Wang, Jiamu Zhang, Tianyi Zhang, Jiayi Yuan,
Hongyi Liu, Andrew Wen, Shaochen Zhong, Hanjie Chen, Xia Hu
TMLR
ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
Hongyi Liu, Rajarshi Saha, Zhen Jia, Youngsuk Park, Jiaji Huang, Shoham Sabach, Yu-Xiang Wang, George Karypis
ICML25
Attack on LLMs: LoRA once, backdoor everywhere in the share-and-play echosystem
Hongyi Liu*, Shaochen Zhong*, Xintong Sun*, Minghao Tian, Zirui Liu, Ruixiang Tang, Jiayi Yuan, Yu-Neng Chuang, Li Li, Soo-Hyun Choi, Rui Chen, Vipin Chaudhary, Xia Hu
EMNLP finding 2025
StructDrop: A Structured Random Algorithm Towards Efficient Large-scale Graph Training
Hongyi Liu, Zirui Liu, Kaixiong Zhou, Tong Zhao, Neil Shah, Xia Ben Hu
Preprint
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
Hongyi Liu*, Jiayi Yuan*, Shaochen Zhong*, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu
EMNLP finding 2024
Simplifying Cloud Management with Cloudless Computing
Yiming Qiu, Patrick Tser Jern Kon, Jiarong Xing, Yibo Huang,
Hongyi Liu, Xinyu Wang, Peng Huang, Mosharaf
Chowdhury and Ang Chen
HotNets 2023
Remote Direct Memory Introspection
Hongyi Liu, Jiarong Xing, Yibo Huang, Danyang Zhuo, Srinivas Devadas, Ang Chen
USENIX Security 2023 (Distinguished Paper Award)
Bedrock: Programmable Network Support for Secure RDMA Systems
Jiarong Xing, Kuo-Feng Hsu, Yiming Qiu, Ziyang Yang,
Hongyi Liu, and Ang Chen
USENIX Security 2023
A Vision for Runtime Programmable Networks
Jiarong Xing, Yiming Qiu, Kuo-Feng Hsu,
Hongyi Liu, Matty Kadosh, Alan Lo, Aditya Akella, Thomas Anderson, Arvind Krishnamurthy, T. S. Eugene Ng, and Ang Chen
HotNets 2021
Toward Reconfigurable Kernel Datapaths with Learned Optimizations
Yiming Qiu,
Hongyi Liu, Thomas E.Anderson, Yingyan Lin, Ang Chen
HotOS 2021