arXiv:2607. 21542v1 Announce Type: new Abstract: We propose a new approach to two-sample testing for deciding whether two sets of samples are drawn from the same distribution.
arXiv:2606. 04009v1 Announce Type: cross Abstract: Two-sample testing is a fundamental tool for detecting distributional differences across scientific domains, but classical tests (including kernel-based tests) can be ineffective on high-dimensional structured data such as images.
arXiv:2606. 16941v1 Announce Type: cross Abstract: Detecting distributional differences between two independent samples is a fundamental problem in statistics and machine learning.
arXiv:2608.29395v1 Announce Type: new Abstract: Vision-language models such as CLIP and SigLIP provide strong zero-shot recognition, but their predictions can degrade when deployed on target data tha...
ALICE is a foundation model that estimates mutual information (MI) without per‑distribution training. Trained only on synthetic distributions, it acts as an in‑context estimator of rectified‑flow velocity fields, producing MI via a fixed identity that integrates squared differences between joint and conditional fields. The authors validate ALICE on a challenging benchmark and demonstrate its applicability to unseen data in biology, genetics, and neuroscience, achieving performance comparable to neural estimators trained separately for each distribution.
arXiv:2605.06272v2 Announce Type: replace Abstract: While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation fr...
The paper introduces UnInfo, a test‑time adaptation method for vision‑language models like CLIP that addresses image corruption—a realistic distribution shift caused by sensor conditions. UnInfo leverages uniformity‑aware confidence maximization, information‑aware loss balancing, and knowledge distillation from an EMA teacher to preserve embedding uniformity and improve zero‑shot classification accuracy. Experiments show that UnInfo outperforms existing TTA methods on corrupted image datasets.
arXiv:2409. 10094v3 Announce Type: replace-cross Abstract: Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.
arXiv:2606. 08460v1 Announce Type: cross Abstract: Data-adaptive two-sample testing assesses if two samples come from the same distribution, using a discrepancy learned from the data (e.
arXiv:2608. 07953v1 Announce Type: new Abstract: Distribution shift poses a significant challenge to the robustness of machine learning models, but the current solutions only aim to detect out-of-distribution (OOD) samples and predict uncertainty levels.
ProtoDCS introduces a robust open‑set test‑time adaptation framework for vision‑language models, addressing the challenge of simultaneously handling covariate‑shifted in‑distribution (csID) and out‑of‑distribution (csOOD) data. It replaces brittle thresholding with a double‑check separation using a probabilistic Gaussian Mixture Model and employs an evidence‑driven adaptation strategy that updates prototypes efficiently, reducing overconfidence and computational cost. Experiments on CIFAR‑10/100‑C and Tiny‑ImageNet‑C show state‑of‑the‑art performance, improving both known‑class accuracy and OOD detection metrics.
arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specif...
arXiv:2602. 19946v5 Announce Type: replace-cross Abstract: Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following.