Ethan Zhen LI

About me

• I am a first-year PhD student in the Department of Computing of The Hong Kong Polytechnic University, fortunately supervised by Prof. Hongxia Yang at PolyU and Prof. Wenguang Chen at Tsinghua University.
• Earlier, I received my Master’s degree in Artificial Intelligence at the University of Science and Technology of China (USTC), supervised by Prof. Yong Wang.
• My current research interests are mainly in LLM Low-resource Training & Inference and Foundation Models.

😈I am actively looking for academic collaboration, fell free to contact me if you are interested.

Research Interests

• AI Infrastructure: Efficient LLM Training and Machine Learning System.
• Efficient LLM Inference: Model Comperssion and Inference Accelerate.

Publications and Manuscripts

(*Equal contribution)

• InfiJanice: Joint Analysis and In-situ Correction Engine for Quantization-Induced Math Degradation in Large Language Models
  2025 Under Review
  👥: Zhen Li*, Yupeng Su*, Songmiao Wang, Runming Yang, Congkai Xie, Aofan Liu, Ming Li, Jiannong Cao, Yuan Xie, Ngai Wong✉, Hongxia Yang✉

• Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models
  2025 Under Review
  👥: Zeyu Liu*, Yuhang Liu*, Guanghao Zhu, Congkai Xie, Zhen Li, Jianbo Yuan, Xinyao Wang, Qing Li, Shing-Chi Cheung, Shengyu Zhang, Fei Wu, Hongxia Yang✉

• MD3R: Minimizing Data Distribution Discrepancies to Tackle Inconsistencies in Multilingual Query-Code Retrieval
  2025 ACL@KnowFM
  👥: Aofan Liu, Yuguo Yin, Hongjian Xing, Zhen Li, Yiyan Qi

• Quantization meets reasoning: Exploring llm low-bit quantization degradation for mathematical reasoning
  2025 arXiv
  👥: Zhen Li*, Yupeng Su*, Runming Yang, Congkai Xie, Zheng Wang, Zhongwei Xie, Ngai Wong✉, Hongxia Yang✉

• InfiR: Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning.
  2025 arXiv
  👥: Congkai Xie, Shuo Cai, Wenjun Wang, Pengxiang Li, Zhijie Sang, Kejing Yang, Yiming Zhang, Zhen Li, Guanghao Zhu, Zeyu Liu, Yang Yu, Yuhang Liu, Su Lu, Baoyi He, Qi Zhou, Xiaotian Han, Jianbo Yuan, Shengyu Zhang, Fei Wu, Hongxia Yang✉

Industrial Experiences

• Member of Technical Staff (Intern) @InfiX.ai · 2024.11 - Present
• Algorithm Engineer @Tencent Interactive Entertainment Group (IEG) · 2024.07 - 2024.11
• AI Infra Engineer (Intern) @Ant Group NextEVO Research Center · 2023.06 - 2024.04
• Research Intern @AMD Xilinx DeePhi · 2022.10 - 2024.05
• Research Intern @iFlytek Technology Research Institute · 2022.03 - 2022.06

Project Experiences

ATorch: Make large model training more efficient and reproducible for everyone

DLRover: An automatic distributed deep learning system

Vitis-AI: An Integrated Development Environment that can be leveraged to accelerate AI inference on AMD adaptable platforms

Lookahead: A toolkit to accelerate LLM inference without headache (🤯) and tears (😭) .

Awards

• Outstanding Postgraduate Student, University of Science and Technology of China · 2024
• 1st‑Class Academic Scholarship, University of Science and Technology of China · 2023
• 1st‑Class Academic Scholarship, University of Science and Technology of China · 2022
• 1st‑Class Academic Scholarship, University of Science and Technology of China · 2021
• Outstanding Undergraduate Student, Jiangnan University · 2021
• Merit Student Award of Jiangsu Province, Jiangsu Province · 2021
• Outstanding Student of the Year, Jiangsu Province · 2019
• Merit Student Award, Wuxi · 2019
• Outstanding Student Leader Award, Wuxi · 2021

Teaching

• Teaching Assistant, COMP2021 – Object-oriented Programming, PolyU · 2025 Fall
• Teaching Assistant, ML4432 – Machine Learning, PolyU · 2025 Spring
• Teaching Assistant, CONT010177 – Modern Control Theory, USTC · 2022 Fall

Extracurricular Activities

• President of the Student Union, Jiangnan University