6 papers
Information-Theoretic Constraints for Continual Vision-Language-Action Alignment
Libang Zhao, Qixin Zeng, Hongyin Zhang +1
When deployed in open-ended robotic environments, Vision--Language--Action (VLA) models need to continually acquire new skills, yet suffer from severe catastrophic forgetting. We o…
CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains
Qixin Zeng, Hongyin Zhang, Shangke Lyu +3
Robust disturbance rejection remains a longstanding challenge in humanoid locomotion, particularly on unstructured terrains where sensing is unreliable and model mismatch is pronou…
CRL-VLA: Continual Vision-Language-Action Learning
Qixin Zeng, Shuo Zhang, Hongyin Zhang +6
Lifelong learning is critical for embodied agents in open-world environments, where reinforcement learning fine-tuning has emerged as an important paradigm to enable Vision-Languag…
RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models
Hongyin Zhang, Shuo Zhang, Junxi Jin +3
Vision-Language-Action (VLA) models have recently emerged as powerful general-purpose policies for robotic manipulation, benefiting from large-scale multi-modal pre-training. Howev…
Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
Hongyin Zhang, Shiyuan Zhang, Junxi Jin +4
Vision-Language-Action (VLA) models based on flow matching have shown excellent performance in general-purpose robotic manipulation tasks. However, the action accuracy of these mod…
Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs
Guobin Zhu, Rui Zhou, Wenkang Ji +3
Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challen…