arXiv introduces Visual Token Routing for efficient computer-use agents
VTR matches full-resolution performance on OSWorld and CUA-World using 2.5-5.8x fewer visual tokens, reducing inference cost by up to 3.3x.
1 stories, newest first · one card per story
VTR matches full-resolution performance on OSWorld and CUA-World using 2.5-5.8x fewer visual tokens, reducing inference cost by up to 3.3x.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views