Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
Grounding exploration trajectories in an external fact-intent DAG prevents catastrophic context drift in autonomous agents, lifting hard CTF exploitation rates from ~25% to 75%.
Environmental illusions can degrade lane detection accuracy by over 7%, posing serious safety risks for autonomous vehicles.
GCD, designed to enhance code reliability, can paradoxically serve as a vulnerability that enables LLMs to produce malicious code through a novel attack called CodeSpear.
