Search papers, labs, and topics across Lattice.
5
0
8
0
Forget retraining: probing intermediate layer embedding sensitivity offers a surprisingly effective and efficient way to spot AI-generated images.
LLMs can slash memory use by 4x during reasoning without sacrificing accuracy, simply by "zooming in" on relevant cached information instead of attending to everything.
Soft-gating with an "advisor" model can steer LLMs to be safer and more useful, reducing over-refusal without sacrificing detection accuracy.
LLM-based multi-agent systems can more than double their performance and slash token usage by organizing themselves like a company, with distinct governance, execution, and compliance layers.
Generative multi-agent systems spontaneously exhibit collusion and conformity, mirroring societal pathologies, even without explicit programming and bypassing individual agent safeguards.
