Publications
See also: Google Scholar
AI Agents & LLM Systems
-
Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New InsightsACL 2026 (Main Conference)
-
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse TasksPreprint, 2026
-
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated WorkspacesPreprint, 2026
Data-Driven Decision Making
-
Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial ActionsICML 2026 (Spotlight)Spotlight
-
Boosting Column Generation with Graph Neural Networks for Joint Rider Trip Planning and Crew Shift SchedulingTransportation Research Part E, 2025
-
Outbound Load Planning in Parcel Delivery Service Networks Using Machine Learning and OptimizationTransportation Science, 2025
-
Compact Optimality Verification for Optimization ProxiesICML 2024
-
Real-Time Risk Analysis with Optimization ProxiesPSCC 2024 / Electric Power Systems Research, 2024
-
End-to-End Feasible Optimization Proxies for Large-Scale Economic DispatchIEEE Transactions on Power Systems, 2023
-
Compact Optimization Learning for AC Optimal Power FlowIEEE Transactions on Power Systems, 2023
-
Confidence-Aware Graph Neural Networks for Learning Reliability Assessment CommitmentsIEEE Transactions on Power Systems, 2023
-
Two-Stage Learning for the Flexible Job Shop Scheduling ProblemPreprint, 2023
-
Learning Optimization Proxies for Large-Scale Security-Constrained Economic DispatchPSCC 2022 / Electric Power Systems Research, 2022
-
Reinforcement Learning from Optimization Proxy for Ride-Hailing Vehicle RelocationJAIR / IJCAI 2023
-
Improving Learning to Branch via Reinforcement LearningNeurIPS 2020 Workshop (Learning Meets Combinatorial Algorithms)
-
Privacy-Preserving Online Task Allocation in Edge-Computing-Enabled Massive CrowdsensingIEEE Internet of Things Journal, 2019
-
Privacy-Preserving Online Learning Approach for Incentive-based Demand Response in Smart GridIEEE Systems Journal, 2019