Derives closed-form posterior covariance for flow matching from divergence of velocity field, enabling post-hoc uncertainty on pre-trained models including one-step generators.
Eigenscore: Ood detection using covariance in diffusion models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
KLIP detects and localizes distribution shifts in inverse problems via KL-divergence between diffusion prior and posterior without calibration data.
SFM improves generalization under distribution shift for scientific imaging tasks while AVUQ supplies sample-efficient epistemic and aleatoric uncertainty estimates plus anomaly scores.
citing papers explorer
-
Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
Derives closed-form posterior covariance for flow matching from divergence of velocity field, enabling post-hoc uncertainty on pre-trained models including one-step generators.
-
KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
KLIP detects and localizes distribution shifts in inverse problems via KL-divergence between diffusion prior and posterior without calibration data.
-
Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging
SFM improves generalization under distribution shift for scientific imaging tasks while AVUQ supplies sample-efficient epistemic and aleatoric uncertainty estimates plus anomaly scores.