相关论文: MedSAE: Dissecting MedCLIP Representations with Sp…

While medical Vision-Language models (VLMs) achieve strong performance on tasks such as tumor or organ segmentation and diagnosis prediction, their opaque latent representations limit clinical trust and the ability to explain predictions.…

Word embeddings have found their way into a wide range of natural language processing tasks including those in the biomedical domain. While these vector representations successfully capture semantic and syntactic word relations, hidden…

The alignment of vision-language representations endows current Vision-Language Models (VLMs) with strong multi-modal reasoning capabilities. However, the interpretability of the alignment component remains uninvestigated due to the…

CLIP embeddings have demonstrated remarkable performance across a wide range of multimodal applications. However, these high-dimensional, dense vector representations are not easily interpretable, limiting our understanding of the rich…

Transformer-based CLIP models are widely used for text-image probing and feature extraction, making it relevant to understand the internal mechanisms behind their predictions. While recent works show that Sparse Autoencoders (SAEs) yield…

Despite remarkable advancements in pixel-level medical image perception, existing methods are either limited to specific tasks or heavily rely on accurate bounding boxes or text labels as input prompts. However, the medical knowledge…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the internal representations of large language models (LLMs), revealing latent latent features with semantical meaning. This interpretability has also…

Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the…

Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used to provide insight into learned concepts within large protein language models. Here, we employ TopK and Ordered SAEs to investigate autoregressive…

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Recent work on sparse autoencoders (SAEs) has shown promise in extracting interpretable features from neural networks and addressing challenges with polysemantic neurons caused by superposition. In this paper, we apply SAEs to the early…

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…

Wireless capsule endoscopy (WCE) enables non-invasive visual assessment of the small bowel, but its clinical utility is constrained by the large volume of frames generated per examination and the difficulty of recognising subtle…

As deep learning models gain attraction in medical data, ensuring transparent and trustworthy decision-making is essential. In skin cancer diagnosis, while advancements in lesion detection and classification have improved accuracy, the…

Sparse autoencoders (SAEs) decompose polysemantic neural representations, where neurons respond to multiple unrelated concepts, into monosemantic features that capture single, interpretable concepts. However, standard training objectives…

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretability of NAC representations is critical for understanding and…

Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of…