About Me

I am currently a PhD student in Computer Science at the University of Illinois at Chicago under the supervision of Prof. Philip S. Yu (Fellow of ACM, IEEE and AAAS). Prior to that, under the guidance of Prof. Michael Tippett, I completed a Master of Science in Applied Mathematics at Fu Foundation School of Engineering and Applied Science, Columbia University in the City of New York. Before joining Columbia, I completed my undergraduate studies in Mathematics and Applied Mathematics at the University of North Carolina Wilmington.

Research Interests

News & Highlights

  • [2026.09] 🎉 Our paper is accepted to NeurlPS 2026. Thanks for authors' hard work!
  • [2026.08] 🎉 Our two papers are accepted to EMNLP 2026. Congratulation!
  • [2026.07] 🎉 Our paper is accepted to COPA 2026. Congratulation!
  • [2026.07] 🎉 Our paper is accepted to COLM 2026. See you in San Francisco!
  • [2026.05] 🎉 Our paper is accepted to KDD 2026. See you in Jeju, Korea!

Professional Experience

Exploration Experience

UCLA Health

Research Assistant

UCLA Medical School

Los Angeles, CA, USA –

Researched medical LLMs and image segmentation.

Research Assistant

University of Virginia

Virginia, USA –

Optimized LLM KV caching and cache replacement.

Academic Service

  • WWW 2026
  • NeurIPS 2026
  • ICLR 2027
  • TKDE 2026

Publications

ARC-STAR paper

ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models

Chengze Li, Lingwei Wei, Li Sun, ... , Philip Yu

Under Review

PDF
Deployment paper

A Deployment Audit of Release-Side Risk in Conformal Triage under Prevalence Shift

Chengze Li, Xiao Liu, Hanrong Zhang, ... , Xiangrong Qi, Qichao Zhou

Conformal and Probabilistic Prediction with Applications (COPA) 2026

PDF
CoEvoSkills paper

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

Hanrong Zhang, Shicheng Fan, ... , Chengze Li, ... , Philip Yu

Conference on Language Modeling (COLM) 2026

PDF
Sycophancy paper

Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update

Huanhuan Ma, Henry Peng Zou, Chengze Li, Enze Ma, Yunyue Su, Philip Yu

Conference on Empirical Methods in Natural Language Processing (EMNLP) 2026 Findings

PDF
MEMPROBE paper

MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery

Enze Ma, Yufan Zhou, ... , Chengze Li, ... , Philip Yu

Under Review

PDF
Geometry-aware paper

Geometry-aware Test-Time Adaptation on Graphs

Lingwei Wei, Dou Hu, Li Sun, Chengze Li, Wei Zhou, Songlin Hu, Philip S Yu

Knowledge Discovery and Data Mining (KDD) 2026

PDF
Ever paper

EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy

Kening Zheng, Aoying Zheng, ... , Chengze Li, ... , Philip Yu

Under Review

PDF
scaling paper

Scaling LLM Agent Learning with Data Synthesis: A Comprehensive Survey

Hanrong Zhang, Yankai Chen, ... , Chengze Li, ... , Philip Yu

Under Review

PDF
NodeRAG paper

NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes

Tianyang Xu, Haojie Zheng, Chengze Li, Haoxiang Chen, Yixin Liu, Ruoxi Chen, Lichao Sun

https://arxiv.org/pdf/2504.11544

PDF
Auto-Segmentation paper

Patient-specific Daily Updated Deep-Learning Auto-Segmentation for MRI-Guided Adaptive Radiotherapy

Zhenjiang Li, Wei Zhang, Baosheng Li, Jian Zhu, Yinglin Peng, Chengze Li, …

Radiotherapy and Oncology, Dec 2022

PDF