Scholar
Milan Ganai
Google Scholar ID: LCMIfaQAAAAJ
Stanford University
Citations & Impact
Citations
73
H-index
5
i10-index
4
Publications
9
Co-authors
0
Publications
Resume
Academic Achievements
- - Publication: Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning (CoRL 2025)
- - Publication: Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey (OJ-CSYS 2024)
- - Publication: Iterative Reachability Estimation for Safe Reinforcement Learning (NeurIPS 2023)
- - Publication: Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models (ICRA 2023)
- - Publication: Target-independent XLA optimization using Reinforcement Learning (ML for Systems @ NeurIPS 2022)
- - Publication: Identifying Merged Tracks in Dense Environments with Machine Learning (CTD/WIT 2019)
- - Conference Reviewer: ICRA 2023, L4DC 2024, ICML (2024, 2025), AAAI 2025, ICLR 2025, CoRL 2025, NeurIPS 2025
Research Experience
- - Collaborated with Professor Sylvia Herbert's Safe Autonomous Systems Lab.
Education
- - Stanford University, Ph.D. in Computer Science (2024-Present), Advisors: Professor Marco Pavone and Professor Clark Barrett
- - UC San Diego, M.S. in Computer Science (2023-2024), Advisor: Professor Sicun Gao
- - UC San Diego, B.S. in Computer Science (2020-2023), Advisor: Professor Sicun Gao, Collaborated with: Professor Sylvia Herbert's Safe Autonomous Systems Lab
Background
- Research interests: Robotics, Control, and AI. Currently a second-year PhD student in the Computer Science Department at Stanford University.