Search papers, labs, and topics across Lattice.
2
0
5
8
Malicious modifications to router weights can turn Mixture-of-Experts models into trigger-controlled bottlenecks, revealing a critical vulnerability in AI serving architectures.
LLM safety is a cat-and-mouse game: ORPO excels at breaking alignment, while DPO is best at restoring it, but at the cost of overall usefulness.
