Jiazheng Li

• About me
• 
• A fifth-year CSE PhD student at UConn
• Advisor: Prof. Chuxu Zhang
• Research interests
• Everything about LLMs
• Contact me
• jiazheng.li@uconn.edu
• GitHub
• LinkedIn
• Google Scholar
• Personal life
• I grew up in China. My Chinese name is 李嘉政.
• I love sports, especially basketball and soccer. I'm a fan of Real Madrid and LA Lakers.
• I love animals (except for bugs). I have a cat and a dog.
• I love listening to R&B and Hip-Hop songs.
• I love fitness.
• Education
• PhD student in Computer Science (Transferred)
  University of Connecticut, CT, USA
  01/2025-12/2026(expected)
• PhD student in Computer Science
  Brandeis University, MA, USA
  08/2022-12/2024
• B.E. in Biomedical Engineering
  Shanghai Jiao Tong University, Shanghai, China
  09/2017-06/2021
• Industry Experience
• Algorithm Engineer Intern @ Alibaba (Accio Work team), Bay Area, USA
  05/2026-08/2026
  Co-developed the end-to-end post-training of Occamy-1.0, an open-weights 35B-A3B co-work agent model. [Website]
• Applied Scientist Intern @ Amazon (Agent customization team), Bay Area, USA
  06/2025-08/2025
  Designed a step-level credit assignment algorithm for training long-horizon LLM agents with RL. [EACL 2026 Paper]
• Research Intern @ Ant Group (Ling team), Hangzhou, China
  06/2024-01/2025
  Designed a skill-targeted data selection algorithm for mid-training of large language models. [ICML 2025 Paper]
• Publications
• [Tech Report], Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
  Authors: Accio Team
• [EACL 2026 Findings], SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph
  Authors: Jiazheng Li, Yawei Wang, David Yan, Yijun Tian, Zhichao Xu, Huan Song, Panpan Xu, Lin Lee Cheong
• [ICML 2025], MASS: MAthematical Data Selection via Skill Graphs for Pretraining Large Language Models
  Authors: Jiazheng Li*, Lu Yu*, Qing Cui, Zhiqiang Zhang, Jun Zhou, Yanfang Ye, Chuxu Zhang
• [Arxiv 2026], Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
  Authors: Jiazheng Li, Chi-Hao Wu, Yunze Liu, Kaize Ding, Jundong Li, Chuxu Zhang
• [TMLR 2025], Instance-Aware Graph Prompt Learning
  Authors: Jiazheng Li, Jundong Li, Chuxu Zhang
• [CIKM 2023], Heterogeneous Temporal Graph Neural Network Explainer
  Authors: Jiazheng Li, Chunhui Zhang, Chuxu Zhang
• [ICML 2026], Graph is a Substrate Across Data Modalities
  Authors: Ziming Li, Xiaoming Wu, Zehong Wang, Jiazheng Li, Yijun Tian, Jinhe Bi, Yunpu Ma, Yanfang Ye, Chuxu Zhang
• [KDD 2026], Generalizing GNNs with Tokenized Mixture of Experts
  Authors: Xiaoguang Guo, Zehong Wang, Jiazheng Li, Shawn Spitzel, Qi Yang, Kaize Ding, Jundong Li, Chuxu Zhang
• [Arxiv 2025], Semantic Refinement with LLMs for Graph Representations
  Authors: Safal Thapaliya, Zehong Wang, Jiazheng Li, Ziming Li, Yanfang Ye, Chuxu Zhang
• [Arxiv 2025], Graph Foundation Models: A Comprehensive Survey
  Authors: Zehong Wang, Zheyuan Liu, Tianyi Ma, Jiazheng Li, Zheyuan Zhang, Xingbo Fu, Yiyang Li, Zhengqing Yuan, Wei Song, Yijun Ma, Qingkai Zeng, Xiusi Chen, Jianan Zhao, Jundong Li, Meng Jiang, Pietro Lio, Nitesh Chawla, Chuxu Zhang, Yanfang Ye
• [KDD 2025], Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
  Authors: Xingbo Fu, Zehong Wang, Zihan Chen, Jiazheng Li, Yaochen Zhu, Zhenyu Lei, Cong Shen, Yanfang Ye, Chuxu Zhang, Jundong Li
• [CIKM 2023], A Multi-Modality Framework for Drug-Drug Interaction Prediction by Harnessing Multi-source Data
  Authors: Qianlong Wen, Jiazheng Li, Chuxu Zhang, Yanfang Ye