Related papers: ProEval: Proactive Failure Discovery and Efficient…

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's…

Artificial Intelligence (AI) has burrowed into our lives in various aspects; however, without appropriate testing, deployed AI systems are often being criticized to fail in critical and embarrassing cases. Existing testing approaches mainly…

We present an adaptive approach to the construction of Gaussian process surrogates for Bayesian inference with expensive-to-evaluate forward models. Our method relies on the fully Bayesian approach to training Gaussian process models and…

Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited…

Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model uncertainty in the estimation of the model's discriminative…

The rapid advancement of generative AI has revolutionized image creation, enabling high-quality synthesis from text prompts while raising critical challenges for media authenticity. We present Ai-GenBench, a novel benchmark designed to…

Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood. In particular, it is commonly believed that Gaussian encoder/decoder…

Estimating an individual's counterfactual outcomes under interventions is a challenging task for traditional causal inference and supervised learning approaches when the outcome is high-dimensional (e.g. gene expressions, facial images) and…

Foundation model reliability assessment typically requires thousands of evaluation examples, making it computationally expensive and time-consuming for real-world deployment. We introduce microprobe, a novel approach that achieves…

Early Exiting (EE) is a promising technique for speeding up inference by adaptively allocating compute resources to data points based on their difficulty. The approach enables predictions to exit at earlier layers for simpler samples while…

Generative models are popular for medical imaging tasks such as anomaly detection, feature extraction, data visualization, or image generation. Since they are parameterized by deep learning models, they are often sensitive to distribution…

Recent breakthroughs in diffusion models, multimodal pretraining, and efficient finetuning have led to an explosion of text-to-image generative models. Given human evaluation is expensive and difficult to scale, automated methods are…

Inverse problems are ubiquitous in nature, arising in almost all areas of science and engineering ranging from geophysics and climate science to astrophysics and biomechanics. One of the central challenges in solving inverse problems is…

Unbiased assessment of the predictivity of models learnt by supervised machine-learning methods requires knowledge of the learned function over a reserved test set (not used by the learning algorithm). The quality of the assessment depends,…

The surging development of Artificial Intelligence-Generated Content (AIGC) marks a transformative era of the content creation and production. Edge servers promise attractive benefits, e.g., reduced service delay and backhaul traffic load,…

Belonging to the family of Bayesian nonparametrics, Gaussian process (GP) based approaches have well-documented merits not only in learning over a rich class of nonlinear functions, but also in quantifying the associated uncertainty.…

Many algorithms in computer vision and robotics make strong assumptions about uncertainty, and rely on the validity of these assumptions to produce accurate and consistent state estimates. In practice, dynamic environments may degrade…

Estimating causal quantities (CQs) typically requires large datasets, which can be expensive to obtain, especially when measuring individual outcomes is costly. This challenge highlights the importance of sample-efficient active learning…

In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), which leverages predictions from an existing machine learning model to guide sampling and experimentation. Specifically,…

Active learning selects the most informative samples to exploit limited annotation budgets. Existing work follows a cumbersome pipeline that repeats the time-consuming model training and batch data selection multiple times. In this paper,…