5 papers
VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos
Dunjie Lu, Yiheng Xu, Junli Wang +12
Training computer-use agents requires massive amounts of GUI interaction data, but manually annotating action trajectories at scale is prohibitively expensive. We present VideoAgen…
Autonomous Data Agents: A New Opportunity for Smart Data
Yanjie Fu, Dongjie Wang, Wangyang Ying +4
As data continues to grow in scale and complexity, preparing, transforming, and analyzing it remains labor-intensive, repetitive, and difficult to scale. Since data contains knowle…
Brownian Bridge Augmented Surrogate Simulation and Injection Planning for Geological CO Storage
Haoyue Bai, Guodong Chen, Wangyang Ying +7
Geological CO2 storage (GCS) involves injecting captured CO2 into deep subsurface formations to support climate goals. The effective management of GCS relies on adaptive injection…
BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models
Xinyuan Wang, Victor Shea-Jay Huang, Renmiao Chen +4
While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabil…
Continuity Reinforcement Skeleton for Pixel-based Haptic Display
Xinyuan Wang, Zhiqiang Meng, Chang Qing Chen
Haptic displays are crucial for facilitating an immersive experience within virtual reality. However, when displaying continuous movements of contact, such as stroking and explorat…