3 papers
cs.CV2026
PVI: Plug-in Visual Injection for Vision-Language-Action Models
Zezhou Zhang, Songxin Zhang, Xiao Xiong +8
VLA architectures that pair a pretrained VLM with a flow-matching action expert have emerged as a strong paradigm for language-conditioned manipulation. Yet the VLM, optimized for…
cs.AI2025
Orcust: Stepwise-Feedback Reinforcement Learning for GUI Agent
Junyu Lu, Songxin Zhang, Zejian Xie +2
Recent advances in GUI agents have achieved remarkable grounding and action-prediction performance, yet existing models struggle with unreliable reward signals and limited online t…
cs.CL2025
L0: Reinforcement Learning to Become General Agents
Junjie Zhang, Jingyi Xi, Zhuoyang Song +7
Training large language models (LLMs) to act as autonomous agents for multi-turn, long-horizon tasks remains significant challenges in scalability and training efficiency. To addre…