Yu Luo

$Re^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving

Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models

Flow-Based Policy for Online Reinforcement Learning

Towards Robust Zero-Shot Reinforcement Learning

RedHat: Towards Reducing Hallucination in Essay Critiques with Large Language Models

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling