Search papers, labs, and topics across Lattice.
University of North Carolina at Chapel Hill
5
0
11
13
Explicitly linking multimodal patient data to biomedical knowledge graphs unlocks significant gains for clinical LLMs, with performance plummeting when these crucial connections are removed.
A single verification prompt is insufficient; learning a reliability score from multiple, complementary perspectives unlocks robust self-verification for VLMs.
Rigid coarse-to-fine hierarchies cripple multi-scale anomaly detection: letting arbitrary patch granularities interact symmetrically via bidirectional cross-scale attention yields a 9%+ VUS-PR leap over 50 baselines across 530 time series benchmarks.
HarnessRisk reveals that up to 80.9% of adversarial attacks can succeed in agent harnesses, even when risk detection is high.
