SpecPL introduces spectral decomposition via frozen VAE and counterfactual high-frequency permutation to bridge modality asymmetry in VLM prompt learning, reaching 81.51% harmonic-mean accuracy on 11 benchmarks.
European conference on computer vision , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
SpecPL: Disentangling Spectral Granularity for Prompt Learning
SpecPL introduces spectral decomposition via frozen VAE and counterfactual high-frequency permutation to bridge modality asymmetry in VLM prompt learning, reaching 81.51% harmonic-mean accuracy on 11 benchmarks.
- Possibilistic Predictive Uncertainty for Deep Learning