Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Paper • 2605.14747 • Published • 147
ivanovdenial
dongyh-official
AI & ML interests
Vision-language-model
Recent Activity
new activity 28 days ago
OpenGVLab/ScaleCUA-Data:Missing or Unavailable Dataset Files upvoted a paper about 1 month ago
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining upvoted a paper 6 months ago
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge DevicesOrganizations
None yet
Missing or Unavailable Dataset Files
5
#3 opened 9 months ago
by 
yk3701208
upvoted a paper about 1 month ago