Related papers: Representation Engineering: A Top-Down Approach to…

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind…

Machine learning systems are increasingly used to support public sector decision-making across a variety of sectors. Given concerns around accountability in these domains, and amidst accusations of intentional or unintentional bias, there…

In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized…

Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable…

Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Representation Alignment (REPA)-can substantially accelerate training and improve generation…

The security and privacy concerns along with the amount of data that is required to be processed on regular basis has pushed processing to the edge of the computing systems. Deploying advanced Neural Networks (NN), such as deep neural…

Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na\"ive exposure of such capabilities fundamentally undermines modern…

Artificial Intelligence (AI) is about making computers that do the sorts of things that minds can do, and as we progress towards this goal, we tend to increasingly delegate human tasks to machines. However, AI systems usually do these tasks…

Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization, inspiring many compression-based regularization methods.…

Deep learning research aims at discovering learning algorithms that discover multiple levels of distributed representations, with higher levels representing more abstract concepts. Although the study of deep learning has already led to…

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

Governance opacity over AI systems shifts in kind as capability asymmetry grows, and the strongest forms defeat the disclosure-based remedies governance ordinarily relies on. This paper applies a six-dimension framework from political…

Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data…

This study explores the integration of contextual explanations into AI-powered loan decision systems to enhance trust and usability. While traditional AI systems rely heavily on algorithmic transparency and technical accuracy, they often…

A common approach in neuroscience is to study neural representations as a means to understand a system -- increasingly, by relating the neural representations to the internal representations learned by computational models. However, a…

Stories about everyday situations are an essential part of human communication, motivating the need to develop AI agents that can reliably understand these stories. Despite the long list of supervised methods for story completion and…

Representation learning and unsupervised learning are two central topics of machine learning and signal processing. Deep learning is one of the most effective unsupervised representation learning approach. The main contributions of this…

Artificial Intelligence has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown same or better performance than clinicians in many tasks owing to the rapid…

Understanding AI systems' inner workings is critical for ensuring value alignment and safety. This review explores mechanistic interpretability: reverse engineering the computational mechanisms and representations learned by neural networks…

We propose that future AI transparency and accountability regulations are based on an open global standard for exchanging information about AI systems, which allows co-existence of potentially conflicting local regulations. Then, we discuss…