Carlee Joe-Wong

Internal Planning in Language Models: Characterizing Horizon and Branch Awareness

MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance

Neural Bandit Based Optimal LLM Selection for a Pipeline of Tasks

Offline Clustering of Linear Bandits: The Power of Clusters under Limited Data

Contextual Bandits with LLM-Derived Priors and Adaptive Calibration

Efficient Privacy-Preserving Federated Learning With Selective Parameter Encryption

Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy

Offline Learning for Combinatorial Multi-armed Bandits