Jiazheng (Justin) Wang

Ph.D. Student, University of Virginia

Portrait of Jiazheng Wang

I am a Ph.D. student at the University of Virginia, advised by Xi Peng. My research interests include LLM post-training dynamics, multi-model robustness, and interpretability.

Publications

  1. ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning NeurIPS 2025 Jingyang Yi*, Jiazheng Wang*, Sida Li project openreview
  2. Diversification Catalyzes Language Models' Instruction Generalization To Unseen Semantics Findings of ACL 2025 Dylan Zhang, Jiazheng Wang, Francois Charton paper
  3. Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity Findings of ACL 2025 Dylan Zhang, Jiazheng Wang, Tianran Sun paper

Experience