English
Related papers

Related papers: MedSAE: Dissecting MedCLIP Representations with Sp…

200 papers

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.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Md Rakibul Haque , KM Arefeen Sultan , Tushar Kataria , Shireen Elhabian

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…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Shufan Shen , Junshu Sun , Qingming Huang , Shuhui Wang

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…

Machine Learning · Computer Science 2024-11-05 Usha Bhalla , Alex Oesterling , Suraj Srinivas , Flavio P. Calmon , Himabindu Lakkaraju

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…

Machine Learning · Computer Science 2025-05-27 Maximilian Dreyer , Lorenz Hufe , Jim Berend , Thomas Wiegand , Sebastian Lapuschkin , Wojciech Samek

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…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Qinyue Tong , Ziqian Lu , Jun Liu , Yangming Zheng , Zheming Lu

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…

Other Quantitative Biology · Quantitative Biology 2025-07-11 Haoxiang Guan , Jiyan He , Jie Zhang

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…

Information Retrieval · Computer Science 2026-01-27 Jiayin Wang , Xiaoyu Zhang , Weizhi Ma , Zhiqiang Guo , Min Zhang

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…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

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…

Computation and Language · Computer Science 2025-11-11 Xinyuan Yan , Shusen Liu , Kowshik Thopalli , Bei Wang

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,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

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…

Machine Learning · Computer Science 2024-09-10 Liv Gorton

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…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Clément Cornet , Romaric Besançon , Hervé Le Borgne

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…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Haroon Wahab , Irfan Mehmood , Hassan Ugail

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…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Sadia Kamal , Tim Oates

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Ali Nasiri-Sarvi , Anh Tien Nguyen , Hassan Rivaz , Dimitris Samaras , Mahdi S. Hosseini

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…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Jacob Beattie , Tanya Berger-Wolf , Yu Su

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…

Image and Video Processing · Electrical Eng. & Systems 2020-04-30 Evan M. Yu , Juan Eugenio Iglesias , Adrian V. Dalca , Mert R. Sabuncu