Related papers: Exemplar Partitioning for Mechanistic Interpretabi…

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

Expectation Propagation (EP) is a widely used message-passing algorithm that decomposes a global inference problem into multiple local ones. It approximates marginal distributions (beliefs) using intermediate functions (messages). While…

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

Learning a versatile language-image model is computationally prohibitive under a limited computing budget. This paper delves into the \emph{efficient language-image pre-training}, an area that has received relatively little attention…

Electroencephalography (EEG) recordings of brain activity taken while participants read or listen to language are widely used within the cognitive neuroscience and psycholinguistics communities as a tool to study language comprehension.…

Sparse autoencoders (SAEs) have been applied to large language models and protein language models, but not systematically to electronic health record (EHR) foundation models. We train TopK SAEs on FlatASCEND, a 14.5-million-parameter…

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations. We ask a further question based on the extracted…

Recent successes of Deep Neural Networks (DNNs) in a variety of research tasks, however, heavily rely on the large amounts of labeled samples. This may require considerable annotation cost in real-world applications. Fortunately, active…

When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. Those explanations are expensive to compute and…

Binary code similarity detection is a core task in reverse engineering. It supports malware analysis and vulnerability discovery by identifying semantically similar code in different contexts. Modern methods have progressed from manually…

Equilibrium Propagation (EP) is a powerful and more bio-plausible alternative to conventional learning frameworks such as backpropagation. The effectiveness of EP stems from the fact that it relies only on local computations and requires…

This work proposes a novel approach beyond supervised learning for effective pathological image analysis, addressing the challenge of limited robust labeled data. Pathological diagnosis of diseases like cancer has conventionally relied on…

In high-dimensional and high-stakes contexts, ensuring both rigorous statistical guarantees and interpretability in feature extraction from complex tabular data remains a formidable challenge. Traditional methods such as Principal Component…

Sparse autoencoders (SAEs) have emerged as a powerful technique for decomposing language model representations into interpretable features. Current interpretation methods infer feature semantics from activation patterns, but overlook that…

This paper presents a novel training-free framework for open-vocabulary image segmentation and object recognition (OVSR), which leverages EfficientNetB0, a convolutional neural network, for unsupervised segmentation and CLIP, a…

Decomposable tasks are complex and comprise of a hierarchy of sub-tasks. Spoken intent prediction, for example, combines automatic speech recognition and natural language understanding. Existing benchmarks, however, typically hold out…

Self-attention mechanism has been widely used for various tasks. It is designed to compute the representation of each position by a weighted sum of the features at all positions. Thus, it can capture long-range relations for computer vision…

Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enable mapping to human-interpretable concepts. The current practice for analyzing these features primarily relies on inspecting…

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…