Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
0
Attackers can exploit lifecycle-hook updates to execute malicious commands with host privileges, compromising AI agent harnesses at alarming rates.
LCAR slashes hallucination failures by over 50% in LLM-based ASR systems without any additional training or external models.
Muon-inspired optimizers can provably converge linearly even in non-smooth settings, expanding their applicability beyond the smooth landscapes typically assumed.
