Princeton University · AI Research

Yifan Zhang

PhD candidate at Princeton University and Princeton AI Lab Fellow, focusing on Large Language Models and Multimodal Foundation Models — especially Agentic Reinforcement Learning, Model Architectures for Continual Learning, and AutoResearch.

About

About Me

I am a PhD candidate at Princeton University and a Princeton AI Lab Fellow. My research focuses on improving the agentic and reasoning capabilities of LLMs through reinforcement learning; designing efficient and expressive model architectures that enable continual learning; and automating AI research itself.

I am working on scaling agentic reinforcement learning and developing new model architectures with NVIDIA Research. Previously, I was a Top Seed researcher with the ByteDance Seed Foundation Model Team, where I worked on LLM and MLLM pretraining and scaling, and a visiting PhD student at the UCLA AGI Lab.

For a concise overview of my research, see my interactive research-talk slides.

If you are interested in my research or projects, I would be happy to discuss potential collaborations via email.

Yifan Zhang
Focus

Research Interests

01 Agentic Reinforcement Learning Scaling
02 Model Architectures and Continual Learning
03 AutoResearch, Automating AI Research

You can find my publications on Google Scholar, and my writing at Yifan's Blog.

Research

Selected Works

(* denotes equal contribution, † denotes corresponding authors)

Papers

Recent Publications

(* denotes equal contribution)

Writing

Blog Highlights

Service

Professional Activities

Teaching
  • Teaching Assistant, Machine Learning for Yao class, IIIS, Tsinghua University
Academic Services
  • Conference Reviewer: NeurIPS, ICLR, ICML, COLM, AAAI, AISTATS
  • Journal Reviewer: TMLR, IEEE TDSC, ACM TKDD, ACM TIST, Neuralcomputing, Neural Networks
Awards
  • William G. Bowen Merit Fellowship at Princeton University (only one in each academic division)
  • 2025 & 2026 Stanford University-Elsevier World's Top 2% Scientist