Fan Nie

I am a first year M.S. student at Stanford University, advised by Prof. James Zou. I am also fortunate to work closely with Prof. Alexandre Alahi, Prof. Percy Liang, Prof. Huaxiu Yao and Prof. Linjun Zhang. Previously, I received my B.S. degree in Computer Science (IEEE Honor Class) from Shanghai Jiao Tong University, where I fortunately worked with Prof. Junchi Yan and Prof. Hang Zhao.

If you are interested in connecting with me, please feel free to reach out.

Email: niefan [at] stanford.edu

LinkedIn / Resume / Google Scholar / Github

Research

I am broadly interested in various research topics including reliable AI, foundation models, reinforcement learning and novel evaluation strategies.

My current work focuses on training LLM/MLLM agents through reinforcement learning to enhance their capabilities and reliability.

Selected Publications

UQ: Assessing Language Models on Unsolved Questions
Fan Nie*, Ken Ziyu Liu*, Zihao Wang, Rui Sun, Wei Liu, Weijia Shi, Huaxiu Yao, Linjun Zhang, Andrew Y. Ng, James Zou, Sanmi Koyejo, Yejin Choi, Percy Liang, Niklas Muennighoff*
arXiv preprint arXiv:2508.17580.

EvoLM: In Search of Lost Language Model Training Dynamics
Zhenting Qi, Fan Nie, Alexandre Alahi, James Zou, Himabindu Lakkaraju, Yilun Du, Eric Xing, Sham Kakade, Hanlin Zhang
arXiv preprint arXiv:2506.16029. (NeurIPS'25 Oral Presentation (0.03%))

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors
Fan Nie, Lan Feng, Haotian Ye, Weixin Liang, Pan Lu, Huaxiu Yao, Alexandre Alahi, James Zou
arXiv preprint arXiv:2504.04785. (R2-FM@ICML'25 Oral Presentation) (COLM'25)

TAROT: Targeted Data Selection via Optimal Transport
Lan Feng*, Fan Nie*, Yuejiang Liu, Alexandre Alahi
arXiv preprint arXiv:2412.00420. (ICML'25)

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees
Fan Nie, Xiaotian Hou, Shuhang Lin, James Zou, Huaxiu Yao, Linjun Zhang
arXiv preprint arXiv:2411.02603. (ICML'25)

Boosting Offline Reinforcement Learning for Autonomous Driving with Hierarchical Latent Skills
Zenan Li*, Fan Nie*, Qiao Sun, Fang Da, Hang Zhao
2024 IEEE International Conference on Robotics and Automation. (ICRA'24 Oral Presentation)

Uncertainty-Aware Decision Transformer for Stochastic Driving Environments
Zenan Li, Fan Nie, Qiao Sun, Fang Da, Hang Zhao
8th Annual Conference on Robot Learning. (CoRL'24 Oral Presentation)

Learning divergence fields for shift-robust graph representations.
Qitian Wu, Fan Nie, Chenxiao Yang, Junchi Yan
Forty-first International Conference on Machine Learning. (ICML'24)

Graph Out-of-Distribution Generalization via Causal Intervention
Qitian Wu, Fan Nie, Chenxiao Yang, Tianyi Bao, Junchi Yan
The ACM Web Conference, 2024. (WWW'24 Oral Presentation)

Simplifying and Empowering Transformers for Large-graph Representations
Qitian Wu, Wentao Zhao, Chenxiao Yang, Hengrui Zhang, Fan Nie, Haitian Jiang, Yatao Bian, and Junchi Yan
In Advances in Neural Information Processing Systems, 2023. (NeurIPS'23)

A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs
Zenan Li, Qitian Wu, Fan Nie, and Junchi Yan
In Advances in Neural Information Processing Systems, 2022. (NeurIPS'22)

Services

Reviewer for NeurIPS 2024-2025, ICRA 2024-2025, ICLR 2025-2026, AISTATS 2025-2026, ICML 2025, COLM 2025.

Awards

2025: Best Reviewer Award, AISTATS 2025

2024: Outstanding Graduate of Shanghai Jiao Tong University

2023: Outstanding Student Leader of Shanghai Jiao Tong University

2023: Excellence Scholarship, Department of Computer Science (RMB 25,000)

2022: Rongchang Scientific & Technological Innovation Scholarship (RMB 30,000)

Miscellaneous

I am passionate about the arts, especially music, drawing, and poetry.

My favorite movie is Atonement. My favorite poet is Jorge Luis Borges.

I also enjoy reading, travelling, photography and yoga (especially Pilates).

Updated at May 2025

Thanks Jon Barron for this amazing template