11 datasets found

The dataset used in this paper is a low-rank matrix M, which can be decomposed into a low-rank component L∗ and a sparse error matrix S∗. The authors use this dataset to test...

The Shifts Dataset: a large, standardized dataset for evaluation of uncertainty estimates and robustness to realistic, curated distributional shift.

Buffer of Thoughts is a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs).

The dataset used in this paper is a binary classification dataset, where the goal is to train a classifier that can robustly classify data points in the presence of adversarial...

A robustness and generalizability study of deepfake detection using diffusion models.

A general framework for learning perturbation sets from data when the perturbation cannot be mathematically-defined.

The MultiLexNorm dataset is used to evaluate the robustness of MT models to lexical normalization.

The MTNT dataset is used to evaluate the robustness of MT models to noisy text.

3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these...

The dataset used in the paper is the ImageNet-C dataset, which is a dataset of images corrupted with various types of noise and occlusions.

The dataset used in this paper is a reinforcement learning dataset, specifically the SimpleQuestion dataset, which contains questions answerable using Wikidata as the knowledge...