[Google Scholar] [Twitter] [Github]

Contact: [email protected]

I’m a research scientist at NVIDIA, where I conduct research and develop infrastructure for LLMs post-training and LLM-based coding agents. I received my CS Ph.D. in UIUC (Advisor: Prof. Heng Ji).

Experience / Education

• NVIDIA, Research Scientist; 2025-Present

• University of Illinois Urbana-Champaign, Ph.D. in Computer Science; 2022-2025

• Huazhong University of Science and Technology, BS in Software Engineering; 2018-2022

Recent Publications

[Full Publications]

^* indicates equal contribution

• (LLMs RL Post-Training) Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models [paper]
  Boxin Wang^*, Chankyu Lee^*, Nayeon Lee^*, Sheng-Chieh Lin^*, Wenliang Dai^*, Yang Chen^*, Yangyi Chen^*, Zhuolin Yang^*, Zihan Liu^*, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping^* (ordered alphabetically by first name with equal technical contribution^*)
  Arxiv 2025

• (Vision-Language Pre-Training) Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training [paper]
  Yangyi Chen, Hao Peng, Tong Zhang, Heng Ji
  Arxiv 2025

• (LLMs Pre-Training Scaling Laws) Scaling Laws for Predicting Downstream Performance in LLMs [paper]
  Yangyi Chen, Binxuan Huang, Yifan Gao, Zhengyang Wang, Jingfeng Yang, Heng Ji
  TMLR 2025

• (MLLMs Architecture) A Single Transformer for Scalable Vision-Language Modeling [paper]
  Yangyi Chen^*, Xingyao Wang^*, Hao Peng, Heng Ji
  TMLR 2024

• (Coding Agent) Executable Code Actions Elicit Better LLM Agents [paper]
  Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji
  ICML 2024