Runze Liu

MARTI: A Framework for Multi-Agent LLM Systems Reinforced Training and Inference

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models

PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning

Temporal Difference Learning with Constrained Initial Representations

Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration

Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint

VLP: Vision-Language Preference Learning for Embodied Manipulation