Search papers, labs, and topics across Lattice.
4
0
6
3
A single prompt can completely strip invisible watermarks from images, revealing a critical vulnerability in current watermarking schemes.
CM2 achieves unprecedented gains in cultural reasoning for MLLMs, revealing the power of a multi-agent approach to interdisciplinary challenges.
SkillShield reduces malware-generation severity from 3.37 to 0.58 while achieving a mere 0.14% safety-refusal rate across 731 benign tasks.
Self-evolving coding agents can unwittingly amplify malicious skills, leading to a self-propagating worm effect that evades traditional defenses.
