English
Related papers

Related papers: Concept-SAE: Active Causal Probing of Visual Model…

200 papers

The ImageNet hierarchy provides a structured taxonomy of object categories, offering a valuable lens through which to analyze the representations learned by deep vision models. In this work, we conduct a comprehensive analysis of how vision…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely activated networks, SAEs aim to recover complex superposed…

Machine Learning · Computer Science 2026-03-05 Jingyi Cui , Qi Zhang , Yifei Wang , Yisen Wang

Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoders (SAEs) may offer a potential method to interpret steering…

Machine Learning · Computer Science 2024-11-14 Harry Mayne , Yushi Yang , Adam Mahdi

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Machine Learning · Computer Science 2025-07-14 Stepan Shabalin , Ayush Panda , Dmitrii Kharlapenko , Abdur Raheem Ali , Yixiong Hao , Arthur Conmy

Learning individual-level causal effects from observational data, such as inferring the most effective medication for a specific patient, is a problem of growing importance for policy makers. The most important aspect of inferring causal…

Machine Learning · Statistics 2017-11-07 Christos Louizos , Uri Shalit , Joris Mooij , David Sontag , Richard Zemel , Max Welling

Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce. Addressing this issue, we introduce…

Machine Learning · Computer Science 2024-02-19 Mohammad Hossein Amani , Nicolas Mario Baldwin , Amin Mansouri , Martin Josifoski , Maxime Peyrard , Robert West

While traditional self-supervised learning methods improve performance and robustness across various medical tasks, they rely on single-vector embeddings that may not capture fine-grained concepts such as anatomical structures or organs.…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Costin F. Ciusdel , Alex Serban , Tiziano Passerini

Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and…

Robotics · Computer Science 2026-05-19 Xinchen Jin , Aditya Chatterjee , Pranav Kumar , Rohan Paleja

Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Farshad Sangari Abiz , Reshad Hosseini , Babak N. Araabi

Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network's latent representations into seemingly interpretable features. Despite recent excitement about their potential, research…

Existing zero-shot skeleton-based action recognition methods utilize projection networks to learn a shared latent space of skeleton features and semantic embeddings. The inherent imbalance in action recognition datasets, characterized by…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Sheng-Wei Li , Zi-Xiang Wei , Wei-Jie Chen , Yi-Hsin Yu , Chih-Yuan Yang , Jane Yung-jen Hsu

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior.…

Machine Learning · Computer Science 2026-02-06 Xu Wang , Bingqing Jiang , Yu Wan , Baosong Yang , Lingpeng Kong , Difan Zou

We present the first systematic study of Sparse Autoencoders (SAEs) on video representations. Standard SAEs decompose video into interpretable, monosemantic features but destroy temporal coherence: hard TopK selection produces unstable…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Atahan Dokme , Sriram Vishwanath

In disentangled representation learning, the goal is to achieve a compact representation that consists of all interpretable generative factors in the observational data. Learning disentangled representations for graphs becomes increasingly…

Machine Learning · Computer Science 2023-11-20 Jingyun Feng , Lin Zhang , Lili Yang

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Machine Learning · Computer Science 2025-07-14 Gonçalo Paulo , Nora Belrose

Text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images but also raise people's concerns about generating harmful or misleading content. While extensive approaches have been proposed to erase…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Zhihua Tian , Sirun Nan , Ming Xu , Shengfang Zhai , Wenjie Qu , Jian Liu , Ruoxi Jia , Jiaheng Zhang

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

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Machine Learning · Computer Science 2025-08-14 Charles O'Neill , Mudith Jayasekara , Max Kirkby

While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Sonia Joseph , Praneet Suresh , Ethan Goldfarb , Lorenz Hufe , Yossi Gandelsman , Robert Graham , Danilo Bzdok , Wojciech Samek , Blake Aaron Richards