4 papers
Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models
Lang Cao, Renhong Chen, Luyi Li +3
Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control. However,…
TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL
Lang Cao, Hui Ruan, Yongqian Li +5
Reinforcement learning with group-based objectives, such as Group Relative Policy Optimization (GRPO), is a common framework for aligning large language models on complex reasoning…
More Bang for the Buck: Process Reward Modeling with Entropy-Driven Uncertainty
Lang Cao, Renhong Chen, Yingtian Zou +9
We introduce the Entropy-Driven Uncertainty Process Reward Model (EDU-PRM), a novel entropy-driven training framework for process reward modeling that enables dynamic, uncertainty-…
Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning
Lang Cao, Yingtian Zou, Chao Peng +3
Mathematical reasoning has been challenging for large language models (LLMs), and the introduction of step-by-step Chain-of-Thought (CoT) inference has significantly advanced the m…