Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Paper • 2605.14747 • Published • 145
xlch
xlch
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 6 months ago
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge DevicesOrganizations
upvoted a paper 22 days ago