Fahim Tajwar

I am a first-year computer science MS student at Stanford University and affliated with the Stanford Artificial Intelligence Laboratory (SAIL). I am grateful to have my research supervised by Prof. Chelsea Finn. My primary research interest is in machine learning methods that can handle the intricacies of real world data, e.g., ML models that are robust to distribution shifts and autonomous RL systems that can be trained in environments that have irreversible states, among other things. I am also interested in using machine learning for the problems that we are facing today --- climate change, poverty, education for all etc.

Previously, I graduated with distinction from Stanford University in 2022 where I studied mathematics. I am also fortunate to have worked with Prof. Percy Liang, Stefano Ermon, and Stephen Luby during my undergraduate studies at Stanford. Feel free to reach out to me in case you have any questions or want to chat about my work!

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo
Research
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
Yoonho Lee*, Annie S Chen*, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, and Chelsea Finn
Under Review in International Conference on Learning Representations (ICLR), 2023
[Paper (Coming soon)], [Code (Coming soon)]
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
Annie Xie*, Fahim Tajwar*, Archit Sharma*, and Chelsea Finn
Advances in Neural Information Processing Systems (NeurIPS), 2022
RSS Workshop on Scaling Robot Learning (SRL) (Spotlight), 2022
[Paper], [Code], [Project Website]
Do Deep Networks Transfer Invariances Across Classes?
Allan Zhou*, Fahim Tajwar*, Alexander Robey, Tom Knowles, George J Pappas, Hamed Hassani, and Chelsea Finn
International Conference on Learning Representations (ICLR), 2022
[Paper], [Code]
No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
Fahim Tajwar, Ananya Kumar*, Sang Michael Xie*, and Percy Liang
ICML Workshop on Uncertainty & Robustness in Deep Learning (UDL), 2021
[Paper], [Code]
Scalable deep learning to identify brick kilns and aid regulatory capacity
Jihyeon Lee*, Nina R. Brooks*, Fahim Tajwar, Marshall Burke, Stefano Ermon, David B. Lobell, Debashish Biswas, and Stephen Luby
Proceedings of the National Academy of Sciences (PNAS), 2021
[Paper], [Code]

Website template