Search papers, labs, and topics across Lattice.
2
0
4
0
Forget slow attention: FlashPrefill achieves a staggering 27x speedup in long-context prefilling by instantly discovering and thresholding sparse attention patterns.
Reasoning models aren't just verbose, they're actively *harmed* by their own verbosity, but a simple self-distillation trick can compress their outputs by up to 59% while boosting accuracy by up to 16 points.
