Publications
* Equal contribution. Underline indicates me.
Recent Preprints
Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation
arXiv:2610.23831, 2026. [arXiv]
When Reasoning Traces Conflict with Evidence: How Answer Configuration Shapes Evidence Following
arXiv:2610.20805, 2026. [arXiv]
Constraint Tree Exploration for Learning from Language Feedback
arXiv:2610.09107, 2026. [arXiv]
From Discovery to Decision: Finite-Budget Recoverability in LLM Voting
arXiv:2610.01014, 2026. [arXiv]
Accepted Papers
Learning Evidence Highlighting for Frozen LLMs
NeurIPS 2026. [arXiv]
POLAR: Online Learning for LoRA Adapter Caching and Routing in Edge LLM Serving
MobiHoc 2026. [arXiv]
Don't Restart, Just Reuse: Reoptimizing MILPs with Dynamic Parameters
ICML 2025. [Paper]
Guiding Large Language Models in Modeling Optimization Problems via Question Partitioning
IJCAI 2025. [Paper]
Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation
ICLR 2025. [Paper]
DPShaping: Balancing Privacy Guarantee and Communication Cost in IoT Traffic Shaping
ACM TOSN 2025. [Paper]
FFCG: Effective and Fast Family Column Generation for Solving Large-Scale Linear Program
Bandits with Concave Aggregated Reward
IJCAI 2024. [Paper]
Optimal Arms Identification with Knapsacks
ICML 2023. [Paper]
TVFL: Tunable Vertical Federated Learning towards Communication-Efficient Model Serving
INFOCOM 2023. [Paper]
Reinforcement Learning for Node Selection in Mixed Integer Programming
MASS 2023. [Paper]
Online Pricing with Limited Supply and Time-Sensitive Valuations
INFOCOM 2022. [Paper]