Generative AI (GenAI) represents a shift from AI's ability to “recognize” to its ability to
“generate” solutions for a wide range of tasks. As generated solutions and applications grow …

Bayesian neural networks (BNNs) provide a formalism to quantify and calibrate uncertainty
in deep learning. Current inference approaches for BNNs often resort to few-sample …

In this paper, we propose a test-time resource-efficient neural architecture for image
classification. Building on MSDNet [12], our multi-exit architecture excels in both anytime …

Early-exiting has recently provided an ideal solution for accelerating activity inference by
attaching internal classifiers to deep neural networks. It allows easy activity samples to be …

The rising interest in Bayesian deep learning (BDL) has led to a plethora of methods for
estimating the posterior distribution. However, efficient computation of inferences, such as …

Early-exit neural networks (EENNs) facilitate adaptive inference by producing predictions at
multiple stages of the forward pass. In safety-critical applications, these predictions are only …

Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success
in classification, retrieval, and generative tasks. For this, VLMs deterministically map images …

Due to the vast testing space, the increasing demand for effective and efficient testing of
deep neural networks (DNNs) has led to the development of various DNN test case …

Scaling machine learning models significantly improves their performance. However, such
gains come at the cost of inference being slow and resource-intensive. Early-exit neural …

Distinguishing epistemic from aleatoric uncertainty is a central idea to out-of-distribution
(OOD) detection. By interpreting adversarial and OOD inputs from this perspective, we can …