Luoyi Fu

Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets

Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities

OceanVerse: Evaluable 4D Ocean Element Reconstruction Dataset under Realistic Sparsity

Learning to Reason in Structured In-context Environments with Reinforcement Learning

PREP: Pre-inference Guided Token Pruning for Efficient Vision-Language Models

Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration

Extreme Value Policy Optimization for Safe Reinforcement Learning

MICE: Memory-driven Intrinsic Cost Estimation for Mitigating Constraint Violations