English
Related papers

Related papers: Interpreting the linear structure of vision-langua…

200 papers

Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment remain poorly understood. Following the LiMBeR framework, we…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Constantin Venhoff , Ashkan Khakzar , Sonia Joseph , Philip Torr , Neel Nanda

Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Qing Li , Jiahui Geng , Derui Zhu , Fengyu Cai , Chenyang Lyu , Fakhri Karray

Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to independent linear directions. However, a growing body of…

Learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Yang Liu , Mengyuan Liu , Shudong Huang , Jiancheng Lv

This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms the embedding space of pretrained vision models into the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Jungin Park , Jiyoung Lee , Kwanghoon Sohn

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

Computer Vision and Pattern Recognition · Computer Science 2017-06-06 Dong Li , Hsin-Ying Lee , Jia-Bin Huang , Shengjin Wang , Ming-Hsuan Yang

We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-existing vocabulary.…

Machine Learning · Computer Science 2024-01-12 Matthew Trager , Pramuditha Perera , Luca Zancato , Alessandro Achille , Parminder Bhatia , Stefano Soatto

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Machine Learning · Computer Science 2026-01-14 Minglai Yang , Xinyu Guo , Zhengliang Shi , Jinhe Bi , Steven Bethard , Mihai Surdeanu , Liangming Pan

Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs…

Neurons and Cognition · Quantitative Biology 2025-12-10 Omar Claflin

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Machine Learning · Computer Science 2025-07-30 Viktoria Schuster

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Leander Girrbach , Zeynep Akata

Radiological services are experiencing unprecedented demand, leading to increased interest in automating radiology report generation. Existing Vision-Language Models (VLMs) suffer from hallucinations, lack interpretability, and require…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Ahmed Abdulaal , Hugo Fry , Nina Montaña-Brown , Ayodeji Ijishakin , Jack Gao , Stephanie Hyland , Daniel C. Alexander , Daniel C. Castro

Sparse Autoencoders (SAEs) are widely used to interpret neural networks by identifying meaningful concepts from their representations. However, do SAEs truly uncover all concepts a model relies on, or are they inherently biased toward…

Machine Learning · Computer Science 2025-12-03 Sai Sumedh R. Hindupur , Ekdeep Singh Lubana , Thomas Fel , Demba Ba

Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Gerasimos Chatzoudis , Zhuowei Li , Gemma E. Moran , Hao Wang , Dimitris N. Metaxas

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 François Role , Sébastien Meyer , Victor Amblard

Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework…

The core of cross-modal matching is to accurately measure the similarity between different modalities in a unified representation space. However, compared to textual descriptions of a certain perspective, the visual modality has more…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Wenzhang Wei , Zhipeng Gui , Changguang Wu , Anqi Zhao , Dehua Peng , Huayi Wu

Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires learned features to be both interpretable and…

Machine Learning · Computer Science 2026-04-01 Akshay Kulkarni , Tsui-Wei Weng , Vivek Narayanaswamy , Shusen Liu , Wesam A. Sakla , Kowshik Thopalli

Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.…

Artificial Intelligence · Computer Science 2025-12-09 Alexandre Rocchi--Henry , Thomas Fel , Gianni Franchi

Vision-language co-embedding networks, such as CLIP, provide a latent embedding space with semantic information that is useful for downstream tasks. We hypothesize that the embedding space can be disentangled to separate the information on…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Zhi Li , Hau Phan , Matthew Emigh , Austin J. Brockmeier