Search papers, labs, and topics across Lattice.
James
3
0
3
16
Early failure prediction can save up to 20.4% of execution tokens while improving resolution rates in software engineering tasks, transforming how agents handle long trajectories.
Brevis compresses tensor data by synthesizing a DSL program, achieving over 30% smaller archives than leading general-purpose compressors while ensuring bit-exact reconstruction.
Run code LLMs 10x faster and with 6x less memory on your laptop without sacrificing accuracy, thanks to a new quantization and compilation approach.
