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,
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!
Google Scholar  /
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
Annie S Chen*,
Percy Liang, and
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
Archit Sharma*, and
Advances in Neural Information Processing Systems (NeurIPS), 2022
RSS Workshop on Scaling Robot Learning (SRL) (Spotlight), 2022
Do Deep Networks Transfer Invariances Across Classes?
George J Pappas,
Hamed Hassani, and
International Conference on Learning Representations (ICLR), 2022
No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
Sang Michael Xie*, and
ICML Workshop on Uncertainty & Robustness in Deep Learning (UDL), 2021
Scalable deep learning to identify brick kilns and aid regulatory capacity
Nina R. Brooks*,
David B. Lobell,
Debashish Biswas, and
Proceedings of the National Academy of Sciences (PNAS), 2021