A gradient-attention explainability method produces sequence-level visual and textual saliency maps for free-form answers from large vision-language models, with stronger human-attention alignment and faithfulness than prior baselines.
On numerical solutions of the time-dependent Schr\"odinger equation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We review an explicit approach to obtaining numerical solutions of the Schr\"odinger equation that is conceptionally straightforward and capable of significant accuracy and efficiency. The method and its efficacy are illustrated with several examples. Because of its explicit nature, the algorithm can be readily extended to systems with a higher number of spatial dimensions. We show that the method also generalizes the staggered-time approach of Visscher and allows for the accurate calculation of the real and imaginary parts of the wave function separately.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
GLIMPSE: Holistic Cross-Modal Explainability for Large Vision-Language Models
A gradient-attention explainability method produces sequence-level visual and textual saliency maps for free-form answers from large vision-language models, with stronger human-attention alignment and faithfulness than prior baselines.