Search papers, labs, and topics across Lattice.
4
0
8
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.
Chain-of-thought is far more than surface imitation: LLMs carve out discrete, context-dependent geometric subspaces for functional operations like deduction and decomposition, with middle layers encoding the abstract reasoning step rather than the literal tokens.
Speculative decoding can be significantly accelerated by training models to anticipate verification outcomes, leading to faster and more efficient inference.
