Search papers, labs, and topics across Lattice.
4
0
7
4
QV-PIC closes the quality gap between visual and text caching in RAG, achieving unprecedented efficiency gains without sacrificing performance.
Attack success rates in cowork agents can vary dramatically, with some models achieving up to 94.4% effectiveness in executing adversarial tasks.
DREvo achieves unprecedented stability and performance in harness self-evolution, outperforming existing methods by over 16% on key benchmarks.
Persona conditioning in LLMs can be exploited to amplify inference costs by over 200 times, revealing a critical vulnerability in their deployment.
