Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
3
0
6
Aggressive KV cache compression can be achieved with near-zero accuracy loss by treating the cache as a trainable neural network optimized at test-time.
Chain-of-thought context can be halved without sacrificing accuracy by using the geometric trajectory of hidden states to selectively compress exploratory reasoning steps into continuous latent tokens.