Search papers, labs, and topics across Lattice.
4
0
8
10
Stop retraining watermarks for every LoRA: LoRA-Key lets you inject a reusable, user-specific copyright key into text-to-image models without sacrificing image quality or style.
Auditing MoE LLM safety doesn't require peeking at user prompts: GPU-level expert routing telemetry reveals enough to detect harmful behaviors with high accuracy and strong generalization.
Forget training LLMs to understand privacy policies – a specialized, expert-annotated dataset and hybrid framework can do it better, achieving superior readability and reliability.
LLMs under attack exhibit a tell-tale "Entropy Lull" – a period of abnormally low and stable token probability entropy – that can be exploited for highly accurate and efficient attack detection.
