WinARDet cuts repeated-box loops in dense vision-language grounding
On RSDense, authors report F1 rising from 32.16 to 39.36 and redundancy falling from 35.48% to 13.00%.
3 stories, newest first · one card per story
On RSDense, authors report F1 rising from 32.16 to 39.36 and redundancy falling from 35.48% to 13.00%.
Researchers model diffusion and autoregressive decoding as lattice paths and predict schedule cost from data geometry.
NAMVIS generates consistent multi-view images with geometry-conditioned autoregression, beating diffusion baselines and running over 3x faster.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views