Avatar

Xize Liang

PhD Student


xizeliang@miralab.ai, xizeliang@mail.ustc.edu.cn

Interests

  • Large Language Models
  • AI Agents
  • Graph Machine Learning

Education

  • B.S., School of Mathematical Sciences, 2022

    University of Science and Technology of China

About me

I am currently a PhD student at USTC. I am from Tianjin, China. My advisor is Prof. Jie Wang, who leads the MIRA Lab. My research interests include large language models, AI agents, and graph machine learning.

Experience

  • Intern at Huawei Technologies, 2024/12 - 2025/12
  • Intern at Alibaba Cloud, 2023/10 - 2024/10
  • Intern at MSRA, 2022/02 - 2022/08

Publications

Hanzhu Chen, Lin Yang, Jie Wang, Junhao Yan, Zhe Wang, Xize Liang, Jianye Hao. Latent-Guided Reasoning: Empowering Small LLMs with Large-Model Thinking. ICLR 2026.

Xize Liang, Lin Yang, Jie Wang, Rui Liu, Yang Lu, Jinliang Zeng, Hanzhu Chen, Dong Li, Jianye Hao. Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization. ICLR 2026.

Xize Liang, Chao Chen, Shuang Qiu, Jie Wang, Yue Wu, Zhihang Fu, Hanzhu Chen, Feng Wu, Jieping Ye. ROPO: Robust Preference Optimization for Large Language Models. ICML 2025.

Xize Liang, Lin Yang, Jie Wang, Yiyang Lu, Runyu Wu, Hanzhu Chen, Jianye Hao. Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples. ICML 2025.

Zhihao Shi, Jie Wang, Zhiwei Zhuang, Xize Liang, Bin Li, Feng Wu. Accurate and Scalable Graph Neural Networks via Message Invariance. ICLR 2025.

Zhihao Shi, Xize Liang, Jie Wang. LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence (Spotlight). ICLR 2023.

PDF Code