Search papers, labs, and topics across Lattice.
3
0
7
Guardrails in AI systems may claim safety benefits that are largely illusory, with their actual effectiveness hinging on the specifics of input encoding and channel dynamics.
Stealthy attacks in multi-agent systems can be detected more effectively without relying on explicit interaction graphs, leading to a significant boost in detection accuracy.
Feature caching in diffusion models gets a serious upgrade: LESA boosts speed by up to 6.25x while *improving* generation quality by over 20% compared to prior art.
