Search papers, labs, and topics across Lattice.
3
0
5
0
SkillShield slashes malware-generation severity from 3.37 to 0.58, showcasing a new frontier in prompt-space security for coding agents.
Self-evolving coding agents can unwittingly amplify malicious skills, with self-poisoning rates soaring to 86.7% under tailored conditions.
ConceptFormer reveals that adaptive latent concepts can dramatically enhance visual document retrieval by linking complex visual structures to semantic relevance without traditional textual dependencies.
