Search papers, labs, and topics across Lattice.
4
0
7
16
Defensive poisoning can effectively clear over half of original backdoors in LLMs, but the dynamics of trigger recognition reveal deeper vulnerabilities.
Even advanced LLMs struggle to prevent privacy breaches in multi-user settings, exposing critical data spillage risks that current benchmarks overlook.
Conditioning LLMs on human privacy judgments leads to a remarkable increase in alignment with user expectations, showcasing a new standard for agent training.
Forcing VLMs to "think" visually with panoramic renderings, rather than relying on language alone, unlocks surprisingly robust spatial reasoning.
