I work on data and evaluation for AI agents.

I am a Computer Science PhD candidate in the Stanford AI Lab, advised by Serena Yeung-Levy, Ludwig Schmidt, and Tatsunori Hashimoto. I contribute to the team projects Terminal-Bench, OpenThoughts, and Harbor-Index.

In 2025, I was a research intern at Meta Superintelligence Labs, where I worked on test-time scaling for unified multimodal models. Before Stanford, I studied at Nanyang Technological University and then worked as a research engineer at MMLab with Ziwei Liu. I also worked with Alan Yuille and Zongwei Zhou at Johns Hopkins.

Email / Scholar / GitHub / LinkedIn

Talks

Papers

* denotes equal contribution.

At Stanford

• Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
  Harbor Adapter Team
  NeurIPS 2026, Evaluations and Datasets Track
  paper · blog · dataset · bibtex
• OpenThoughts-Agent: Data Recipes for Agentic Models
  OpenThoughts-Agent Team
  arXiv 2026
  paper · project · bibtex
• UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
  Leon Liangyu Chen, Haoyu Ma, Zhipeng Fan, Ziqi Huang, Animesh Sinha, Xiaoliang Dai, Jialiang Wang, Zecheng He, Jianwei Yang, Chunyuan Li, Junzhe Sun, Chu Wang, Serena Yeung-Levy, Felix Juefei-Xu
  CVPR 2026
  paper · bibtex
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
  Terminal-Bench Team
  ICLR 2026
  paper · benchmark · code · bibtex
• OpenThoughts: Data Recipes for Reasoning Models
  OpenThoughts Team
  ICLR 2026 Oral
  paper · code · datasets · blog · bibtex
• The Impact of Image Resolution on Biomedical Multimodal Large Language Models
  Liangyu Chen, James Burgess, Jeffrey J Nirschl, Orr Zohar, Serena Yeung-Levy
  MLHC 2025
  paper · code · bibtex
• BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature
  Alejandro Lozano*, Min Woo Sun*, James Burgess*, Liangyu Chen, Jeffrey J Nirschl, Jeffrey Gu, Ivan Lopez, Josiah Aklilu, Austin Wolfgang Katzer, Collin Chiu, Anita Rau, Xiaohan Wang, Yuhui Zhang, Alfred Seunghoon Song, Robert Tibshirani, Serena Yeung-Levy
  CVPR 2025
  paper · code · bibtex
• Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement
  Simon Yu*, Liangyu Chen*, Sara Ahmadian, Marzieh Fadaee
  ICML 2025 Workshop on DataWorld
  paper · code · bibtex

Before Stanford

• MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations
  Yubo Ma*, Yuhang Zang*, Liangyu Chen, Meiqi Chen, Yizhu Jiao, Xinze Li, Xinyuan Lu, Ziyu Liu, Yan Ma, Xiaoyi Dong, Pan Zhang, Liangming Pan, Yu-Gang Jiang, Jiaqi Wang, Yixin Cao, Aixin Sun
  NeurIPS 2024, Datasets and Benchmarks Track Spotlight
  paper · project · code · bibtex
• MMInA: Benchmarking Multihop Multimodal Internet Agents
  Shulin Tian*, Ziniu Zhang*, Liangyu Chen*, Ziwei Liu
  ACL Findings 2025
  paper · leaderboard · code & dataset · demo · bibtex
• Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
  Aurora-M Team
  COLING 2025, Industry Track
  paper · models · bibtex
• Benchmarking and Analyzing Generative Data for Visual Recognition
  Bo Li, Haotian Liu, Liangyu Chen, Yong Jae Lee, Chunyuan Li, Ziwei Liu
  TPAMI 2025
  paper · code · bibtex
• MIMIC-IT: Multi-Modal In-Context Instruction Tuning
  Bo Li*, Yuanhan Zhang*, Liangyu Chen*, Jinghao Wang*, Fanyi Pu*, Jingkang Yang, Chunyuan Li, Ziwei Liu
  arXiv 2023
  paper · code · bibtex
• Otter: A Multi-Modal Model with In-Context Instruction Tuning
  Bo Li*, Yuanhan Zhang*, Liangyu Chen*, Jinghao Wang*, Fanyi Pu*, Joshua Adrian Cahyono, Jingkang Yang, Ziwei Liu
  TPAMI 2025
  paper · code · bibtex
• Large Language Models are Visual Reasoning Coordinators
  Liangyu Chen*, Bo Li*, Sheng Shen, Jingkang Yang, Chunyuan Li, Kurt Keutzer, Trevor Darrell, Ziwei Liu
  NeurIPS 2023; ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models
  paper · code · talk (English) · talk (中文) · bibtex
• Panoptic Video Scene Graph Generation
  Jingkang Yang, Wenxuan Peng, Xiangtai Li, Zujin Guo, Liangyu Chen, Bo Li, Zheng Ma, Wayne Zhang, Kaiyang Zhou, Chen Change Loy, Ziwei Liu
  CVPR 2023
  paper · bibtex
• Making Your First Choice: To Address Cold Start Problem in Vision Active Learning
  Liangyu Chen, Yutong Bai, Siyu Huang, Yongyi Lu, Bihan Wen, Alan Yuille, Zongwei Zhou
  MIDL 2023; RSNA 2024 Abstracts; NeurIPS 2022 Workshop on Human in the Loop Learning
  paper · code · poster · talk (English) · talk (中文) · bibtex
• Automatic Calcification Morphology and Distribution Classification for Breast Mammograms with Multi-task Graph Convolutional Neural Network
  Hao Du, Melissa Min-Szu Yao, Siqi Liu, Liangyu Chen, Wing P. Chan, Mengling Feng
  JBHI 2023
  paper · bibtex
• Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning
  Linsen Dong, Guanyu Gao, Xinyi Zhang, Liangyu Chen, Yonggang Wen
  arXiv 2020
  paper · code · docs · demo · bibtex

Service

• Organizer of the CVPR 2026 J2A Workshop on Journey to the Awards: Generative AI for Movie-Grade Video Production.
• Editorial board member of the Stanford AI Lab (SAIL) Blog.
• Coach of Singapore's teams at the first International Olympiad in Artificial Intelligence in 2024. The two teams won 2 of the 4 gold medals awarded in the Scientific Round.
• Reviewer for TIP, The Visual Computer, IET Computer Vision, IJCV, TMLR, NeurIPS 2025/23, ICLR 2026/25, COLM 2025, AAAI 2025, ECCV 2024, CVPR 2026/24, MLHC 2025, ICCV CVAMD 2023, CVPR CVinW 2023, ICML IMLH 2023/22, NeurIPS GenAI4Health 2024.