SpecSlot raises pixel-space detail without longer global attention
On ImageNet-512, SpecSlot improves FID by 2.84 versus a FLOPs-matched JiT control and uses 3.9% fewer FLOPs.
6 stories, newest first · one card per story
On ImageNet-512, SpecSlot improves FID by 2.84 versus a FLOPs-matched JiT control and uses 3.9% fewer FLOPs.
SILSA generates high-resolution 3D shapes from sliding-window slice latents, using far fewer tokens and improving topology.
SILSA generates high-resolution 3D shapes from compact slice latents while preserving topology and cutting token cost.
ALICE estimates mutual information zero-shot from samples without retraining on each distribution.
Open-source speech foundation model AuK unifies generation and editing, trained on 1.95 million hours, with distilled AuK-Flash achieving 4.5x speedup.
TransNormal-2 improves monocular surface-normal estimation by fixing VAE edge degradation with geometry-aware losses and refinement, matching MoGe-2 with 1.4% of annotations.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views