Search papers, labs, and topics across Lattice.
3
0
6
10
Token-level feedback in SecOPD slashes adaptive prompt injection success rates from 94% to just 9%, revolutionizing defenses for AI agents.
MLLMs can now handle 4K videos up to 100x faster thanks to AutoGaze, which selectively attends to only the most informative patches.
Models are substantially better at pairwise self-verification than independent scoring, unlocking a more efficient and accurate approach to test-time scaling for complex reasoning.
