Hong Xie

GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series data

Revisiting Overestimation Bias of Q-learning: Breaking Bias Propagation Chains Does Well

Advancing and Benchmarking Personalized Tool Invocation for LLMs

Antagonistic Evolution for LLM Tool Use

Multi-play Multi-armed Bandit Model with Scarce Sharable Arm Capacities

Harnessing Query Heterogeneity for Cost-Effective Proactive Caching in LLM Inference

Multiple-play Stochastic Bandits with Prioritized Resource Sharing