Publication list filterable by topic and type.
Research philosophy: Transportation is both an impact area and a source
of methodological motivation. Machine learning for specific optimization
applications generates insights for broadly generalizable methods with
real-world relevance.
Filter by Area:
Filter by Publication Type:
-
FeaturedLearning-Guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation
Journal of Artificial Intelligence Research (JAIR) 2026 -
Learning to Segment for Vehicle Routing Problems
Also presented at: 12th Triennial Symposium on Transportation Analysis conference (TRISTAN XII) (33% acceptance) -
Probability-Aware Parking Selection
IEEE Transactions on Intelligent Transportation Systems (T-ITS) 2026 -
-
-
-
-
-
Formalizing Task-Space Complexity for Zero-Shot Generalization
Learning for Dynamics & Control Conference (L4DC) 2026 -
AutoTune: A Unified Benchmark for Highway Traffic Microsimulation Calibration
IEEE Intelligent Vehicles Symposium (IV) 2026 -
-
Featured -
FeaturedLearning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job Shop Scheduling
International Conference on Learning Representations (ICLR) 2025 MIT Home Page Feature (32% acceptance rate)Media:MIT News -
Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy
Also presented at: IEEE International Conference on Robotics and Automation (ICRA), 2026 -
-
-
-
-
-
-
Reinforcement Learning for Robust Advisories under Driving Compliance Errors
-
-
-
Featured -
FeaturedReproducibility in Transportation Research: A Hands-on Tutorial
-
FeaturedNeural Neighborhood Search for Multi-agent Path Finding
International Conference on Learning Representations (ICLR) 2024 MIT Home Page Feature (31% acceptance rate) -
-
-
-
-
-
-
-
-
Robust Reinforcement Learning Strategies with Evolving Curriculum for Efficient Bus Operations in Smart Cities
Smart Cities 2024 -
-
Scalability of Platoon-based Coordination for Mixed Autonomy Intersections
-
Multi-Agent Path Finding for Mixed Autonomy Traffic Coordination
-
FeaturedLearning to Configure Separators in Branch-and-Cut
Advances in Neural Information Processing Systems (NeurIPS) 2023 MIT Home Page Feature (31% acceptance rate)Media:MIT News -
-
-
-
-
-
What Is a Typical Signalized Intersection in a City? A Pipeline for Intersection Data Imputation from OpenStreetMap
Transportation Research Board (TRB) Annual Meeting 2023 -
Featured -
Unified Automatic Control of Vehicular Systems with Reinforcement Learning
Also presented at: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022 -
Artificial Intelligence for Automated Vehicle Control and Traffic Operations: Challenges and Opportunities
-
Learning Eco-Driving Strategies at Signalized Intersections
Also presented at: IEEE International Conference on Robotics and Automation (ICRA), 2022. Robotics for Climate Change Workshop (Invited flash talk) -
The Third Workshop on Data-driven Intelligent Transportation
Proceedings of the 31st ACM International Conference on Information & Knowledge Management 2022 (28% acceptance rate) -
-
FeaturedLearning to Delegate for Large-scale Vehicle Routing
Advances in Neural Information Processing Systems (NeurIPS) 2021 Spotlight (3%) (26% acceptance rate)Also presented at: International Conference on Machine Learning (ICML), 2021. Workshop on Subset Selection in Machine LearningMedia:MIT News, ACM TechNews -
Featured -
-
-
-
-
-
FeaturedTutorial on Deep Reinforcement Learning and Transportation
IEEE International Conference on Intelligent Transportation Systems (ITSC) 2018 -
FeaturedVariance Reduction for Policy Gradient with Action-dependent Factorized Baselines
Also presented at: Conference on Neural Information Processing Systems (NeurIPS), 2017. Deep Reinforcement Learning Symposium (Contributed talk) -
-
Flow: Deep Reinforcement Learning for Control in SUMO
-
-
-
-
-
-
-
-
Clustering for Set Partitioning with a Case Study in Ridesharing
2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC) 2016 Best Paper Award Honorable Mention -
-
-
-
-
-
-
-
-
Featured -
Formalizing and Estimating Task-Space Complexity for Zero-shot Generalization
Under Review -
CrossRoads: A Robustness Benchmark for Driving Foundation Models on Roadway Counterfactuals
Under Review -
-
-
-
Multi-Agent Scheduling of Intersection Crossings for Cooperative Autonomous Driving
Under Review -
Hierarchical Aggregation Deconstruction Search for Vehicle Routing Problems
Under Review -
GECO: Towards Generic and Efficient Architectures for Graph-based Neural Combinatorial Optimization
Under Review -
A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention
Under Review -
AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library
Under Review -
