Modeling Student Learning with 3.8 Million Program Traces
Alexis Ross*, Megha Srivastava*, Jeremiah Blanchard, Jacob Andreas
preprint
Policy Learning with a Language Bottleneck
Megha Srivastava, Cedric Colas, Dorsa Sadigh, Jacob Andreas
Transactions of Machine Learning Research (TMLR) 2026
Training large language models on narrow tasks can lead to broad misalignment
Jan Betley*, Niels Warncke*, Anna Sztyber-Betley, Daniel Tan, Xuchan Bao, MartÃn Soto, Megha Srivastava, Nathan Labenz, & Owain Evans
Nature 2026
Shared Autonomy for Proximal Teaching
Megha Srivastava*, Reihaneh Iranmanesh*, Yuchen Cui, Deepak Gopinath, Emily Sumner, Andrew Silva, Laporsha Dees, Guy Rosman, Dorsa Sadigh
ACM/IEEE Conference on Human Robot Interaction (HRI) 2025, Melbourne, Australia
Optimistic Verifiable Training by Controlling Hardware Nondeterminism
Megha Srivastava, Simran Arora, and Dan Boneh
Neural Information Processing Systems (NeurIPS) 2024, Vancouver, Canada
Do Users Write More Insecure Code with AI Assistants?
Neil Perry*, Megha Srivastava*, Deepak Kumar, and Dan Boneh
ACM Conference on Computer and Communications Security (CCS) 2023, Copenhagen, Denmark
Generating Language Corrections for Teaching Physical Control Tasks
Megha Srivastava, Noah Goodman, and Dorsa Sadigh
International Conference of Machine Learning (ICML) 2023, Honolulu, Hawai'i
Evaluating Human-Language Model Interaction
Stanford Center for Research on Foundation Models
⚬ Led both Question Answering (Project Page) and Crossword Puzzles (Project Page).
Transactions of Machine Learning Research (TMLR) 2023
Assistive Teaching of Motor Control Tasks to Humans
Megha Srivastava, Erdem Biyik, Suvir Mirchandani, Noah Goodman, and Dorsa Sadigh
Neural Information Processing Systems (NeurIPS) 2022, New Orleans, Louisiana
LILA: Language-Informed Latent Actions
Siddharth Karamcheti*, Megha Srivastava*, Percy Liang, and Dorsa Sadigh
Conference on Robot Learning (CoRL) 2021, London, United Kingdom
Question Generation for Adaptive Education
Megha Srivastava and Noah Goodman
Assocation for Computational Linguistics (ACL) 2021, virtual
Backward Compatibility in Machine Learning Systems
Megha Srivastava, Besmira Nushi, Ece Kamar, Shital Shah, and Eric Horvitz
Knowledge Discovery and Data Mining (KDD) 2020, virtual
Robustness to Spurious Correlations via Human Annotations
Megha Srivastava, Tatsunori Hashimoto, and Percy Liang
International Conference of Machine Learning (ICML) 2020, virtual
Mathematical Notions vs. Human Perception of Fairness:
A Descriptive Approach to Fairness for Machine Learning
Megha Srivastava, Hoda Heidari, and Andreas Krause
Knowledge Discovery and Data Mining (KDD) 2019, Anchorage, Alaska
Fairness Without Demographics in Repeated Loss Minimization
Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, and Percy Liang
International Conference of Machine Learning (ICML) 2018, Stockholm, Sweden
Best Paper Runner-Up Award
Learning Strategy versus Inherent Architecture on the Ability of CNNs to Develop Transformation Invariance
Megha Srivastava and Kalanit Grill-Spector
Vision Sciences Society (VSS) 2017, Tampa, Flordia
Notes from an AI-Led Research Project on Pharmacovigilance
(Based on the Echo paper by Claude Sonnet 3.5 and Megha Srivastava)
Agents4Science, 2025
Findings from a Pilot Anthropic—OpenAI Alignment Evaluation Exercise
Sam Bowman, Megha Srivastava, Jon Kutasov, Rowan Wang, Trenton Bricken, Benjamin Wright, Ethan Perez, and Nicholas Carlini
Anthropic, 2025
Productive Struggle:
The Future of Human Learning in the Age of AI
Rose Wang and Megha Srivastava
The Stanford AI Lab Blog, 2025
Observations from HALIE:
A Closer Look at Human-LM Interactions in Information-Seeking Contexts
Megha Srivastava and John Thickstun
Center for Research on Foundation Models Blog, 2023
Machine learning for modular multiplication
Kristin Lauter*, Cathy Yuanchen Li*, Krystal Maughan*, Rachel Newton*, Megha Srivastava*
WIN6 at Banff International Research Station for Mathematical Innovation and Discovery, 2023
Designing More "Human-like" Algorithms: A computational complexity perspective
Computational Complexity (CS 254) Final Project, 2023