English
Related papers

Related papers: SAE-FD: Sparse Autoencoder Feature Distillation fo…

200 papers

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Zhe Li , Sarah Cechnicka , Cheng Ouyang , Katharina Breininger , Peter Schüffler , Bernhard Kainz

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Machine Learning · Computer Science 2025-01-31 Charles O'Neill , Alim Gumran , David Klindt

Sparse auto-encoders (SAEs) have become a prevalent tool for interpreting language models' inner workings. However, it is unknown how tightly SAE features correspond to computationally important directions in the model. This work…

Machine Learning · Computer Science 2025-02-25 Thomas Dooms , Daniel Wilhelm

Learning versatile, fine-grained representations from irregular event streams is pivotal yet nontrivial, primarily due to the heavy annotation that hinders scalability in dataset size, semantic richness, and application scope. To mitigate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Zhiwen Chen , Junhui Hou , Zhiyu Zhu , Jinjian Wu , Guangming Shi

The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…

Machine Learning · Computer Science 2026-01-29 Chiraag Kaushik , Davis Barch , Andrea Fanelli

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…

Computation and Language · Computer Science 2025-10-20 Jessy Lin , Luke Zettlemoyer , Gargi Ghosh , Wen-Tau Yih , Aram Markosyan , Vincent-Pierre Berges , Barlas Oğuz

Continual learning focuses on incrementally training a model on a sequence of tasks with the aim of learning new tasks while minimizing performance drop on previous tasks. Existing approaches at the intersection of Continual Learning and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Malvina Nikandrou , Georgios Pantazopoulos , Ioannis Konstas , Alessandro Suglia

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made…

Computer Vision and Pattern Recognition · Computer Science 2021-11-25 Umberto Michieli , Pietro Zanuttigh

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

Computation and Language · Computer Science 2025-06-02 Xu Wang , Zihao Li , Benyou Wang , Yan Hu , Difan Zou

Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both Large Language Models (LLMs) and Vision Transformers (ViTs). By decomposing polysemantic…

Machine Learning · Computer Science 2026-05-11 Jakub Stępień , Marcin Mazur , Jacek Tabor , Przemysław Spurek

Large pre-trained transformers have revolutionized artificial intelligence across various domains, and fine-tuning remains the dominant approach for adapting these models to downstream tasks due to the cost of training from scratch.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Wei Chen , Jingxi Yu , Zichen Miao , Qiang Qiu

In Sequential Recommenders (SR), encoding and utilizing modalities in an end-to-end manner is costly in terms of modality encoder sizes. Two-stage approaches can mitigate such concerns, but they suffer from poor performance due to modality…

Information Retrieval · Computer Science 2024-01-17 Hengchang Hu , Qijiong Liu , Chuang Li , Min-Yen Kan

Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Jisu Han , Jaemin Na , Wonjun Hwang

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

Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification. However, in general, supervised learning needs a large number of labelled samples per…

Computer Vision and Pattern Recognition · Computer Science 2020-09-15 Khanh-Hung Tran , Fred-Maurice Ngole-Mboula , Jean-Luc Starck , Vincent Prost

Dataset distillation aims to compress large datasets into compact yet highly informative subsets that preserve the training behavior of the original data. While this concept has gained traction in classification, its potential for image…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Tobias Dietz , Brian B. Moser , Tobias Nauen , Federico Raue , Stanislav Frolov , Andreas Dengel

Although larger datasets are crucial for training large deep models, the rapid growth of dataset size has brought a significant challenge in terms of considerable training costs, which even results in prohibitive computational expenses.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Sheng-Feng Yu , Jia-Jiun Yao , Wei-Chen Chiu

Understanding the internal machinations of deep Transformer-based NLP models is more crucial than ever as these models see widespread use in various domains that affect the public at large, such as industry, academia, finance, health. While…

Computation and Language · Computer Science 2026-05-13 Dan Pluth , Zachary Nicholas Houghton , Yu Zhou , Vijay K. Gurbani

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Machine Learning · Computer Science 2026-05-19 Katarzyna Filus , Kamil Faber , Roberto Corizzo , Christopher Kanan

Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number of features in the SAE, hierarchical features tend to split…

Computation and Language · Computer Science 2025-11-18 David Chanin , James Wilken-Smith , Tomáš Dulka , Hardik Bhatnagar , Satvik Golechha , Joseph Bloom