arXiv Machine Learning June 16, 2026 By Anju Chhetri, Pratik Shrestha, Ramesh Rana, Prashnna Gyawali, Binod Bhattarai

When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations

Read the original on arXiv Machine Learning →

arXiv:2606. 16196v1 Announce Type: new Abstract: Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributional shifts poses a major obstacle to safe clinical deployment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

safety

arXiv AI

Jul 15

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

arXiv:2607. 12094v1 Announce Type: cross Abstract: Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models.

By Ayush Karmacharya (Purdue University), Luke Luschwitz (Purdue University), Lucia Romero (Purdue University), Yanan Niu (EPFL), Joseph Campbell (Purdue University)

benchmarks

arXiv AI

Sep 10

Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging

arXiv:2609.07803v1 Announce Type: new Abstract: Model pruning is widely used to compress deep neural networks, reducing memory and computational requirements with minimal impact on aggregate performa...

By Nazish Khalid, Tausifa Jan Saleem, Amal Saqib, Donald C. Wunsch II, Mohammad Yaqub

efficiency

arXiv Computer Vision

Sep 7

FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders

The paper introduces FailSAE, a method that uses Sparse Autoencoders to predict failures in vision‑language models (VLMs) such as CLIP. By treating failure prediction as a classification over sparse SAE latent activations and employing a three‑stage training pipeline, the approach yields higher prediction accuracy than existing confidence‑score or auxiliary‑classifier baselines. Analysis shows that the SAE captures class‑specific concepts and reveals a shift toward ambiguous or style‑related concepts during failures, offering insights for runtime failure recovery.

By Jie Ma, Zongxi Liu, Yi Zhu

llms rag multimodal safety

arXiv Machine Learning

Aug 12

Clarity: The Flexibility-Interpretability Trade-Off in Sparsity-aware Concept Bottleneck Models

arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.

By Konstantinos P. Panousis, Diego Marcos

computer-vision efficiency multimodal safety

arXiv Computer Vision

3d ago

Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs

arXiv:2609.38362v1 Announce Type: new Abstract: Generative vision-language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining dis...

By Hung-Jen Chen, Yu-Heng Ho, Ting-Yao Huang, Po-Hsiang Hsu, Li-Yu Chen, Chun-Yi Lee, Min Sun

llms multimodal benchmarks

arXiv Machine Learning

Aug 31

EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders

EXPOSE is a framework that applies Sparse Autoencoders to Vision Foundation Model embeddings in computational pathology, aiming to separate biological signals from domain‑specific noise. By training a sparse representation of VFM features and using a linear classifier to flag domain‑specific latent dimensions, the method masks these components before downstream relapse prediction, avoiding the need to retrain the backbone model. Experiments on a large prostate cancer dataset demonstrate that removing domain‑specific features improves cross‑domain performance and raises the Domain Robustness Index (DoRI).

By Anja Witte, Maximilian Lennartz, Jan Baumbach, Guido Sauter, Stefan Bonn, Patrick Fuhlert, Marina Zimmermann

rag diffusion