相关论文: Tree-Based Leakage Inspection and Control in Conce…

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks by understanding input information and predicting corresponding outputs. However, the internal mechanisms by which LLMs comprehend input and…

Behavior Cloning (BC) is a widely adopted visual imitation learning method in robot manipulation. Current BC approaches often enhance generalization by leveraging large datasets and incorporating additional visual and textual modalities to…

Coreset Selection (CS) aims to identify a subset of the training dataset that achieves model performance comparable to using the entire dataset. Many state-of-the-art CS methods select coresets using scores whose computation requires…

Deep reinforcement learning has recently shown many impressive successes. However, one major obstacle towards applying such methods to real-world problems is their lack of data-efficiency. To this end, we propose the Bottleneck Simulator: a…

Models based on human-understandable concepts have received extensive attention to improve model interpretability for trustworthy artificial intelligence in the field of medical image analysis. These methods can provide convincing…

Various studies among side-channel attacks have tried to extract information through leakages from electronic devices to reach the instruction flow of some appliances. However, previous methods highly depend on the resolution of traced…

Concept bottleneck models have been successfully used for explainable machine learning by encoding information within the model with a set of human-defined concepts. In the context of human-assisted or autonomous driving, explainability…

We are concerned with the challenge of reliably classifying and assessing intracranial aneurysms using deep learning without compromising clinical transparency. While traditional black-box models achieve high predictive accuracy, their lack…

Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…

We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), which embeds aggregate analyst consensus as a structural bottleneck, treating professional beliefs as a sufficient statistic for the market's high-dimensional information…

Large Language Models (LLMs) are increasingly applied in recommendation scenarios due to their strong natural language understanding and generation capabilities. However, they are trained on vast corpora whose contents are not publicly…

Explainable AI seeks to bring light to the decision-making processes of black-box models. Traditional saliency-based methods, while highlighting influential data segments, often lack semantic understanding. Recent advancements, such as…

Large Language Models (LLMs) have become indispensable tools in science, technology, and society, enabling transformative advances across diverse fields. However, errors or outdated information within these models can undermine their…

Semantic leakage is a phenomenon recently introduced by Gonen et al. (2024). It refers to a situation in which associations learnt from the training data emerge in language model generations in an unexpected and sometimes undesired way.…

Recent work has shown that probing model internals can reveal a wealth of information not apparent from the model generations. This poses the risk of unintentional or malicious information leakage, where model users are able to learn…

Concept-based Models are a class of inherently explainable networks that improve upon standard Deep Neural Networks by providing a rationale behind their predictions using human-understandable `concepts'. With these models being highly…

Knowledge Tracing (KT) aims to predict a student's future performance based on their sequence of interactions with learning content. Many KT models rely on knowledge concepts (KCs), which represent the skills required for each item.…

In this work, a multi-stage Machine Learning (ML) pipeline is proposed for pipe leakage detection in an industrial environment. As opposed to other industrial and urban environments, the environment under study includes many interfering…

Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rely on implicit pooling, which overloads the hidden state of a standard vocabulary token…

Given a set of deep learning models, it can be hard to find models appropriate to a task, understand the models, and characterize how models are different one from another. Currently, practitioners rely on manually-written documentation to…