Search papers, labs, and topics across Lattice.
Chinese Academy of Sciences, University of Chinese Academy of Sciences
2
0
3
Reorganizing expert groups in MoE models can slash accuracy degradation by over 71% while boosting throughput by more than twofold.
LLM serving isn't just about carbon footprints – it's quietly eroding biodiversity, and this framework finally lets you quantify the ecological cost per query.
