Video2GUI converts 500 million video metadata entries into a 12-million-trajectory dataset spanning 1500+ applications, and pretraining on it improves GUI grounding and action benchmarks by 5-20%.
Shot Segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Video2GUI converts 500 million video metadata entries into a 12-million-trajectory dataset spanning 1500+ applications, and pretraining on it improves GUI grounding and action benchmarks by 5-20%.