Search papers, labs, and topics across Lattice.
3
2
7
6
Discarding irrelevant reasoning tokens can make language models up to 3x faster at test time without sacrificing performance.
Achieving a staggering 95.5% on the ARC-AGI-3 benchmark, Prime Agent redefines the capabilities of long-horizon coding agents by seamlessly integrating memory and computation.
A new family of sparse Mixture-of-Experts models, Arcee Trinity, achieves stable training at scale thanks to a novel MoE load balancing strategy (SMEBU).
