Siyang Gao

Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting

DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS

Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts

Cross-domain Offline Policy Adaptation with Dynamics- and Value-aligned Data Filtering

Best Arm Identification with Correlated Sampling

Internalizing World Models via Self-Play Finetuning for Agentic RL

Beyond Rational Illusion: Behaviorally Realistic Strategic Classification

Query-Efficient Zeroth-Order Algorithms for Nonconvex Optimization

General Risk Measure meets Offline RL: Provably Efficient Risk-Sensitive Offline RL via Optimized Certainty Equivalent

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

AdaptVis: Spatial Understanding in Vision-Language Models Requires Adaptive Attention