Search papers, labs, and topics across Lattice.
4
0
6
Claw-like agents are vulnerable to severe security breaches, with malicious plugins achieving a 100% success rate in attacks.
Sentence-level watermarks can now survive aggressive paraphrasing attacks like sentence splitting and merging, thanks to a new alignment-based approach.
Text watermarks can now survive even aggressive paragraph-level paraphrasing, thanks to a new self-anchoring technique that breaks the robustness-quality tradeoff.
LLM agents struggle to maintain performance in multi-day collaborative tasks, dropping significantly after just one environmental update, revealing a critical gap in adaptation to evolving real-world conditions.
