Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
2
0
4
Token-level LLM routing, previously hindered by system inefficiencies, now achieves up to 64x higher throughput with a novel request-centric, model-centric serving architecture.
Uniform layer looping wastes latent compute on trivial tokens, but dynamically routing iteration depth beats standard transformers on AIME with a 53% steeper test-time scaling slope.