الباحثون

Peter W. J. Staar

المنشورات 1

نسخة أولية وصول مفتوح

DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents

A. Said Gurbuz, Ahmed Nassar, Sunghwan Hong وآخرون · 2026

Computer-use agents need to reliably ground action targets in complex desktop scenes, where multiple applications, overlapping windows, and visually similar controls compete for attention. Existing training data rarely pair such scenes with dense annotations or vary them in a controlled way. We introduce DeskForge, a c …

المؤلفون المشاركون