Vision

3 posts in Vision

16x Faster On-Device Video Generation: Qualcomm's ReHyAt Distills Attention in 160 GPU Hours

January 2026Vision

16x Faster On-Device Video Generation: Qualcomm's ReHyAt Distills Attention in 160 GPU Hours

Training-Free Fix Boosts Vision-Language Models 3 Points by Correcting Attention Errors

January 2026Vision

Training-Free Fix Boosts Vision-Language Models 3 Points by Correcting Attention Errors

40% Faster Video from Single Images: Pixel-to-4D Predicts Dynamic 3D Gaussians in One Pass

January 2025Vision

40% Faster Video from Single Images: Pixel-to-4D Predicts Dynamic 3D Gaussians in One Pass