Search papers, labs, and topics across Lattice.
3
0
7
Standard pixel augmentations frequently corrupt delicate vision-language alignment, but injecting diffusion-style isotropic noise directly into embedding spaces breaks through the longstanding performance ceiling of stacked CutMix, Mixup, and RandAug recipes.
Speculative decoding can be significantly accelerated by training models to anticipate verification outcomes, leading to faster and more efficient inference.
