Search papers, labs, and topics across Lattice.
MaiNLP LMU
4
0
6
Can we trust AI models to reason reliably, or are they just exploiting shortcuts?
Achieving superior taxonomy induction across diverse text sources, this method enhances coherence and interpretability in knowledge organization.
Uncertainty estimation in clinical VLMs fails to signal when models are unreliable, but it can predict which predictions are likely to fail under stress.
BitResEdit achieves unprecedented text alignment in image editing while preserving background details, outperforming prior methods by a significant margin.
