2 papers
cs.AI2026
From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation
Zezhou Wang, Ziyun Zhang, Xiaoyi Zhang +2
Vision-language models are increasingly deployed as computer-use agents (CUAs) that operate desktops and browsers. Top-performing CUAs are framework-based systems that decompose pl…
cs.LG2024
Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models
Zezhou Wang, Yaxin Du, Xingjun Ma +3
Federated domain-specific instruction tuning (FedDIT) for large language models (LLMs) aims to enhance performance in specialized domains using distributed private and limited data…