Search papers, labs, and topics across Lattice.
Peking University
2
0
3
LLM agent systems can achieve up to 76% speedups and significantly reduced hotspot miss rates by intelligently caching logits and scheduling compute resources based on agent behavior.
Automating equality saturation strategy synthesis is now possible: EggMind uses LLMs to reduce cost by 45% and RAM by 69% on vectorization tasks.
