Mehul Damani

21 papers A* 2A 1Journal 16Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control.
CoRR
Yifeng Zhang, Harsh Goel, Peizhuo Li, Mehul Damani, Sandeep Chinchali, Guillaume Sartoretti
2026 J jnl
Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models.
CoRR
Isha Puri, Mehul Damani, Idan Shenfeld, Marzyeh Ghassemi, Jacob Andreas, Yoon Kim
2026 J jnl
Self-Distillation Enables Continual Learning.
CoRR
Idan Shenfeld, Mehul Damani, Jonas Hübotter, Pulkit Agrawal
2025 J jnl
Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty.
CoRR
Mehul Damani, Isha Puri, Stewart Slocum, Idan Shenfeld, Leshem Choshen, Yoon Kim, Jacob Andreas
2025 J jnl
CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control.
IEEE Trans. Intell. Transp. Syst.
Yifeng Zhang, Harsh Goel, Peizhuo Li, Mehul Damani, Sandeep Chinchali, Guillaume Sartoretti
2025 J jnl
Latency and Token-Aware Test-Time Compute.
CoRR
Jenny Y. Huang, Mehul Damani, Yousef El-Kurdi, Ramón Fernandez Astudillo, Wei Sun
2025 A* conf
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation.
ICLR
Mehul Damani, Idan Shenfeld, Andi Peng, Andreea Bobu, Jacob Andreas
2025 A* conf
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning.
ICML
Ekin Akyürek, Mehul Damani, Adam Zweiger, Linlu Qiu, Han Guo, Jyothish Pari, Yoon Kim, Jacob Andreas
2024 J jnl
Formal contracts mitigate social dilemmas in multi-agent reinforcement learning.
Auton. Agents Multi Agent Syst.
Andreas A. Haupt, Phillip J. K. Christoffersen, Mehul Damani, Dylan Hadfield-Menell
2024 J jnl
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation.
CoRR
Mehul Damani, Idan Shenfeld, Andi Peng, Andreea Bobu, Jacob Andreas
2024 J jnl
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning.
CoRR
Ekin Akyürek, Mehul Damani, Linlu Qiu, Han Guo, Yoon Kim, Jacob Andreas
2023 J jnl
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.
CoRR
Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Tong Wang, Samuel Marks, Charbel-Raphaël Ségerie, Micah Carroll, Andi Peng, Phillip J. K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca D. Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell
2023 J jnl
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.
Trans. Mach. Learn. Res.
Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Tong Wang, Samuel Marks, Charbel-Raphaël Ségerie, Micah Carroll, Andi Peng, Phillip J. K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca D. Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell
2023 A conf
SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control.
AAMAS
Harsh Goel, Yifeng Zhang, Mehul Damani, Guillaume Sartoretti
2023 J jnl
SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control.
CoRR
Harsh Goel, Yifeng Zhang, Mehul Damani, Guillaume Sartoretti
2022 J jnl
Distributed Reinforcement Learning for Robot Teams: A Review.
CoRR
Yutong Wang, Mehul Damani, Pamela Wang, Yuhong Cao, Guillaume Sartoretti
2022 — conf
Multi-agent Traffic Signal Control via Distributed RL with Spatial and Temporal Feature Extraction.
AAMAS Workshops
Yifeng Zhang, Mehul Damani, Guillaume Sartoretti
2021 J jnl
Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World.
CoRR
Florian Laurent, Manuel Schneider, Christian Scheller, Jeremy D. Watson, Jiaoyang Li, Zhe Chen, Yi Zheng, Shao-Hung Chan, Konstantin Makhnev, Oleg Svidchenko, Vladimir Egorov, Dmitry Ivanov, Aleksei Shpilman, Evgenija Spirovska, Oliver Tanevski, Aleksandar Nikov, Ramon Grunder, David Galevski, Jakov Mitrovski, Guillaume Sartoretti, Zhiyao Luo, Mehul Damani, Nilabha Bhattacharya, Shivam Agarwal, Adrian Egli, Erik Nygren, Sharada P. Mohanty
2021 J jnl
PRIMAL$_2$: Pathfinding Via Reinforcement and Imitation Multi-Agent Learning - Lifelong.
IEEE Robotics Autom. Lett.
Mehul Damani, Zhiyao Luo, Emerson Wenzel, Guillaume Sartoretti
2020 — conf
Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World.
NeurIPS (Competition and Demos)
Florian Laurent, Manuel Schneider, Christian Scheller, Jeremy D. Watson, Jiaoyang Li, Zhe Chen, Yi Zheng, Shao-Hung Chan, Konstantin Makhnev, Oleg Svidchenko, Vladimir Egorov, Dmitry Ivanov, Aleksei Shpilman, Evgenija Spirovska, Oliver Tanevski, Aleksandar Nikov, Ramon Grunder, David Galevski, Jakov Mitrovski, Guillaume Sartoretti, Zhiyao Luo, Mehul Damani, Nilabha Bhattacharya, Shivam Agarwal, Adrian Egli, Erik Nygren, Sharada P. Mohanty
2020 J jnl
PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Lifelong.
CoRR
Mehul Damani, Zhiyao Luo, Emerson Wenzel, Guillaume Sartoretti