Lichang Chen

I am an AI research scientist at Meta Superintelligence Lab, working on agents for automating AI researchers. I did my PhD at the Computer Science Department, University of Maryland, College Park, where I work closely with Dr. Tianyi Zhou. I obtained my bachelor's degree from Zhejiang University. I can be reached at {bob}{my-last-name}@cs.umd.edu.

My name in Chinese: 陈力畅

Google Scholar / Twitter / LinkedIn / Github

Research Interests

My research interests are in AI alignment and agentic systems, especially in how we can automate the realistic workflows such as foundational model research, Machine Learning, and Data Analysis. I am also interested in how to create RL enviroments scalable for improving the capabilities of AI, e.g., reasoning and instruction following.

Working Experience

AI Research Scientist@Meta SuperIntelligence, 2025.8 - Present, Agents for automating AI researchers.

Internship Experience

Intern@Google Deepmind, 2024.9 - 2025.5, Meta RL for reasoning & Thinking to Learn.
Intern@Google Deepmind, 2024.5 - 2024.8, The evaluation/alignment of Omni-Modality Language Models.
Intern@Google Research & Cloud AI Research, 2024.2 - 2024.5, The self-improvement of multimodal LLMs.
Intern@NVIDIA ADLR team, 2023.9 - 2024.1, Mitigate hackings in RLHF/More Robust Reward Models
Intern@Samsung AI Research, 2023.5 - 2023.8, Data Filter for Instruction Tuning.

Selected Publications

	OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities Lichang Chen, Hexiang Hu, Pranav Shyam, Ming-Hsuan Yang, Boqing Gong, et al. Work Done@Google Deepmind, ICLR 2025
	From Lists to Emojis: How Format Bias Affects Model Alignment Lichang Chen, Xuanchang Zhang, Wei Xiong, Tianyi Zhou, Heng Huang, Tong Zhang. ACL*, 2025
	RRM: Robust Reward Model Training Mitigates Reward Hacking Tianqi Liu, Wei Xiong, Jie Ren, Lichang Chen, Tianhe Yu, Mohammad Saleh, et al. Work Done@Google Deepmind, ICLR 2025
	ODIN: Disentangled Reward Mitigates Hacking in RLHF Lichang Chen, Chen Zhu, Davit Soselio, Tianyi Zhou, Tom Goldstein, Heng Huang, Mohammad Shoeybi, Bryan Catanzaro ICML, 2024.
	InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models Lichang Chen, Jiuhai Chen, Tom Goldstein, Heng Huang, Tianyi Zhou ICML, 2024
	AlpaGasus: Training a Better Alpaca with Fewer Data Lichang Chen, Shiyang Li, Jun Yan, Hai Wang, Kalpa Gunaratna, Vikas Yadav, Zheng Tang, Vijay Srinivasan, Tianyi Zhou, Heng Huang, Hongxia Jin ICLR, 2024
	Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin NAACL , 2024
	HallusionBench: an image-context reasoning benchmark challenging for multi-modality models Fuxiao Liu, Tianrui Guan, Zongxia Li, Lichang Chen, et al. CVPR, 2024
	How Many Demonstrations Do You Need for In-context Learning? Jiuhai Chen, Lichang Chen, Chen Zhu, Tianyi Zhou EMNLP, 2023
	PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer Lichang Chen, Jiuhai Chen, Heng Huang, Minhao Cheng EMNLP, 2023