Search papers, labs, and topics across Lattice.
Institute of Automation, Chinese Academy of Sciences
3
0
6
Allocating prediction capacity dynamically across semantic slots can boost recommendation accuracy while keeping computational costs in check.
PEARL transforms chaotic LLM outputs into reliable, auditable reasoning graphs, achieving a staggering 300/350 accuracy in scientific reasoning extraction.
LLMs struggle with code migration when APIs evolve, but KCoEvo's knowledge graph augmentation boosts migration accuracy and execution success.
