Huanxuan Liao

PhD Student @ UCAS & CASIA focusing on Long Context Modeling

I am a third-year PhD student in Pattern Recognition and Intelligent Systems at University of Chinese Academy of Sciences (UCAS) and Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Shizhu He and Prof. Kang Liu. Before that, I received B.Eng. from North China Electric Power University (NCEPU) in 2023, under the supervision of Prof. Min Shi and Prof. Yun Ju.

My research lies at the intersection of natural language processing and machine learning, with a focus on Long Context Modeling, Efficient Reasoning, Efficient Attention and Architecture, and Long Video Understanding in large language models (LLMs). I aim to enhance the practicality and accessibility of LLMs (including Multimodal LLMs) in real-world scenarios through two complementary approaches: optimizing LLMs for efficient deployment and strengthening smaller, more economical models for efficient reasoning.

liaohuanxuan2023@ia.ac.cn