Related papers: What could go wrong? Discovering and describing fa…

Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains. While the efficacy and pitfalls of such methods are well-studied in vision, there is a…

Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps. We argue that the most informative evaluation signal lies…

Embodied agents in safety-critical applications such as Vision-Language Navigation (VLN) rely on multiple interdependent capabilities (e.g., perception, memory, planning, decision), making failures difficult to localize and attribute.…

Robot failures in human-centered environments are inevitable. Therefore, the ability of robots to explain such failures is paramount for interacting with humans to increase trust and transparency. To achieve this skill, the main challenges…

The ability to navigate robots with natural language instructions in an unknown environment is a crucial step for achieving embodied artificial intelligence (AI). With the improving performance of deep neural models proposed in the field of…

Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain…

While language models are increasingly more proficient at code generation, they still frequently generate incorrect programs. Many of these programs are obviously wrong, but others are more subtle and pass weaker correctness checks such as…

Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is subject to human labeling bias. Similarly, there are multiple…

In this work, we study the challenge of providing human-understandable descriptions for failure modes in trained image classification models. Existing works address this problem by first identifying clusters (or directions) of incorrectly…

In the last two years, more than 200 papers have been written on how machine learning (ML) systems can fail because of adversarial attacks on the algorithms and data; this number balloons if we were to incorporate papers covering…

Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete…

Large language models (LLMs) demonstrate remarkable breadth of knowledge, yet their ability to reason about computational processes remains poorly understood. Closing this gap matters for practitioners who rely on LLMs to guide algorithm…

Image and video inpainting is a classic problem in computer vision and computer graphics, aiming to fill in the plausible and realistic content in the missing areas of images and videos. With the advance of deep learning, this problem has…

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in…

Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and transparency at deployment time. However, research in this area…

Automatically discovering failures in vision models under real-world settings remains an open challenge. This work demonstrates how off-the-shelf, large-scale, image-to-text and text-to-image models, trained on vast amounts of data, can be…

Security vulnerabilities present in a code that has been written in diverse programming languages are among the most critical yet complicated aspects of source code to detect. Static analysis tools based on rule-based patterns usually do…

Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation. In this work, we propose DECIDER (Debiasing Classifiers to Identify Errors Reliably), a novel approach that…

As robots acquire increasingly sophisticated skills and see increasingly complex and varied environments, the threat of an edge case or anomalous failure is ever present. For example, Tesla cars have seen interesting failure modes ranging…

Even as deep neural networks have become very effective for tasks in vision and perception, it remains difficult to explain and debug their behavior. In this paper, we present a programmatic and semantic approach to explaining,…