Jiazheng (Justin) Wang

M.S. in Data Science, University of Chicago

I work on LLM reasoning, reinforcement learning, data-centric AI, instruction generalization, efficient inference, and proof-oriented code generation.

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