Zhen (Ethan) LI

Zhen (Ethan) LI

Ph.D. Candidate in Artificial Intelligence at PolyU

Publications

You can also find my articles on my Google Scholar profile.

Reinforcement Learning Model Training Method and Device

Published in Patent, 2025

U.S., China and Singapore patent on reinforcement learning model training method and device.

Recommended citation: Xiaotian Han, Zhen Li, et al. Reinforcement Learning Model Training Method and Device. U.S., China and Singapore Patent.

Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models Permalink

Published in Under Review, 2025

Curriculum-based phased reinforcement learning for multimodal reasoning in multimodal small language models.

Recommended citation: 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. Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models. Under review, 2025.
Download Paper

InfiJanice: Joint Analysis and In-situ Correction Engine for Quantization-Induced Math Degradation in Large Language Models Permalink

Published in Under Review, 2025

An analysis and in-situ correction engine for quantization-induced mathematical reasoning degradation in LLMs.

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

InfiR: Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning Permalink

Published in arXiv, 2025

A study on crafting effective small language models and multimodal small language models for reasoning.

Recommended citation: 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. InfiR: Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning. arXiv, 2025.
Download Paper

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning Permalink

Published in arXiv, 2025

Low-bit quantization degradation analysis and mitigation for mathematical reasoning in large language models.

Recommended citation: Zhen Li*, Yupeng Su*, Runming Yang, Congkai Xie, Zheng Wang, Zhongwei Xie, Ngai Wong, Hongxia Yang. Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning. arXiv, 2025.
Download Paper