Search papers, labs, and topics across Lattice.
6
0
8
2
SFC redefines semantic understanding in spoken language tasks, achieving superior accuracy and adaptability in open-domain contexts.
Selective distillation can unlock critical learning signals in reinforcement learning, leading to significant performance gains in complex tasks.
Directly editing LLM responses can boost correction success rates by over 25% while slashing token usage by nearly 40%.
APV enables LLMs to discern pedagogical intent with unprecedented accuracy, achieving a correlation of $r=0.958$ with human judgments.
Privacy alone won't drive information sharing in oligopolies; firms need an external signal to make disclosure worthwhile.
Web agents can actually get *more* efficient as they learn, achieving state-of-the-art performance with significantly fewer tokens via online skill distillation.
