English
Related papers

Related papers: Decomposing multimodal embedding spaces with group…

200 papers

This work proposes a unified self-supervised pre-training framework for transferable multi-modal perception representation learning via masked multi-modal reconstruction in Neural Radiance Field (NeRF), namely NeRF-Supervised Masked…

Computer Vision and Pattern Recognition · Computer Science 2023-12-07 Xiaohao Xu

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

Machine Learning · Computer Science 2025-04-01 Adam Karvonen

The central question in representation learning is what constitutes a good or meaningful representation. In this work we argue that if we consider data with inherent cluster structures, where clusters can be characterized through different…

Machine Learning · Computer Science 2022-12-05 Pascal Mattia Esser , Satyaki Mukherjee , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar

Spectral Embedding (SE) has often been used to map data points from non-linear manifolds to linear subspaces for the purpose of classification and clustering. Despite significant advantages, the subspace structure of data in the original…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Hira Yaseen , Arif Mahmood

One of the key challenges in learning joint embeddings of multiple modalities, e.g. of images and text, is to ensure coherent cross-modal semantics that generalize across datasets. We propose to address this through joint Gaussian…

Computer Vision and Pattern Recognition · Computer Science 2019-09-17 Shweta Mahajan , Teresa Botschen , Iryna Gurevych , Stefan Roth

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

Machine Learning · Computer Science 2025-05-26 Wei Shi , Sihang Li , Tao Liang , Mingyang Wan , Guojun Ma , Xiang Wang , Xiangnan He

We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fixed-dimensional Euclidean representations. We formalize the functional representation hypothesis,…

Machine Learning · Computer Science 2026-05-11 Bahareh Tolooshams , Ailsa Shen , Anima Anandkumar

Standard Sparse Autoencoders (SAEs) excel at discovering a dictionary of a model's learned features, offering a powerful observational lens. However, the ambiguous and ungrounded nature of these features makes them unreliable instruments…

Machine Learning · Computer Science 2025-09-29 Jianrong Ding , Muxi Chen , Chenchen Zhao , Qiang Xu

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept -…

Machine Learning · Computer Science 2025-12-23 Dana Arad , Aaron Mueller , Yonatan Belinkov

Deep learning is a kind of feature learning method with strong nonliear feature transformation and becomes more and more important in many fields of artificial intelligence. Deep autoencoder is one representative method of the deep learning…

Machine Learning · Computer Science 2020-02-18 Yongming Li , Yan Lei , Pin Wang , Yuchuan Liu

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Information Retrieval · Computer Science 2026-02-18 Anton Klenitskiy , Konstantin Polev , Daria Denisova , Alexey Vasilev , Dmitry Simakov , Gleb Gusev

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

This work presents an approach for image reconstruction in clinical low-dose tomography that combines principles from sparse signal processing with ideas from deep learning. First, we describe sparse signal representation in terms of…

Machine Learning · Statistics 2023-11-27 Jevgenija Rudzusika , Thomas Koehler , Ozan Öktem

Acoustic word embeddings --- fixed-dimensional vector representations of arbitrary-length words --- have attracted increasing interest in query-by-example spoken term detection. Recently, on the fact that the orthography of text labels…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-02 Myunghun Jung , Hyungjun Lim , Jahyun Goo , Youngmoon Jung , Hoirin Kim

Sparse Autoencoders (SAEs) can efficiently identify candidate monosemantic features from pretrained neural networks for galaxy morphology. We demonstrate this on Euclid Q1 images using both supervised (Zoobot) and new self-supervised (MAE)…

Instrumentation and Methods for Astrophysics · Physics 2025-11-13 John F. Wu , Michael Walmsley

Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Grégoire Dhimoïla , Thomas Fel , Victor Boutin , Agustin Picard

Multimodal fusion breaks through the boundaries between diverse modalities and has already achieved notable performances. However, in many specialized fields, it is struggling to obtain sufficient alignment data for training, which…

Machine Learning · Computer Science 2024-09-24 Zijia Song , Zelin Zang , Yelin Wang , Guozheng Yang , Kaicheng yu , Wanyu Chen , Miaoyu Wang , Stan Z. Li

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

Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Zhihong Chen , Yuhao Du , Jinpeng Hu , Yang Liu , Guanbin Li , Xiang Wan , Tsung-Hui Chang