Search papers, labs, and topics across Lattice.
Affiliation:
4
0
8
0
Intent-targeted tools reveal that LLMs often signal harmful intentions before executing risky actions, enabling real-time intervention strategies.
AERIS achieves a 29.3% boost in multi-UAV ISAC performance without the risks of trial-and-error learning.
A content-agnostic leakage gauge can reliably detect context-leakage risks in LLMs, achieving near-perfect accuracy across diverse models and attack scenarios.
SCOUT achieves a remarkable 16.85% improvement in spatial reasoning benchmarks, setting a new standard for Vision-Language Models.
