English
Related papers

Related papers: SPARC: Concept-Aligned Sparse Autoencoders for Cro…

200 papers

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

Open-domain question answering can be formulated as a phrase retrieval problem, in which we can expect huge scalability and speed benefit but often suffer from low accuracy due to the limitation of existing phrase representation models. In…

Computation and Language · Computer Science 2020-05-04 Jinhyuk Lee , Minjoon Seo , Hannaneh Hajishirzi , Jaewoo Kang

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…

Machine Learning · Computer Science 2025-09-24 Dong Shu , Xuansheng Wu , Haiyan Zhao , Daking Rai , Ziyu Yao , Ninghao Liu , Mengnan Du

While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible. Towards a better understanding of this phenomenon, our work…

Machine Learning · Computer Science 2024-02-13 Valentino Maiorca , Luca Moschella , Antonio Norelli , Marco Fumero , Francesco Locatello , Emanuele Rodolà

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Ziteng Gao , Zhan Tong , Limin Wang , Mike Zheng Shou

Explainable AI (XAI) has become essential in computer vision to make the decision-making processes of deep learning models transparent. However, current visual explanation (XAI) methods face a critical trade-off between the high fidelity of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Gwanghee Lee , Sungyoon Jeong , Kyoungson Jhang

Automated unit test generation for C remains a formidable challenge due to the semantic gap between high-level program intent and the rigid syntactic constraints of pointer arithmetic and manual memory management. While Large Language…

Software Engineering · Computer Science 2026-02-19 Jaid Monwar Chowdhury , Chi-An Fu , Reyhaneh Jabbarvand

The classical sparse coding model represents visual stimuli as a linear combination of a handful of learned basis functions that are Gabor-like when trained on natural image data. However, the Gabor-like filters learned by classical sparse…

Artificial Intelligence · Computer Science 2023-02-23 Jonathan Huml , Abiy Tasissa , Demba Ba

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du

Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders…

Machine Learning · Computer Science 2024-06-07 Leo Gao , Tom Dupré la Tour , Henk Tillman , Gabriel Goh , Rajan Troll , Alec Radford , Ilya Sutskever , Jan Leike , Jeffrey Wu

Learning-based surrogate models have become a practical alternative to high-fidelity CFD solvers, but their latent representations remain opaque and hinder adoption in safety-critical or regulation-bound settings. This work introduces a…

Computational Engineering, Finance, and Science · Computer Science 2025-07-23 Yeping Hu , Shusen Liu

Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as…

Machine Learning · Computer Science 2026-01-26 Aaron J. Li , Suraj Srinivas , Usha Bhalla , Himabindu Lakkaraju

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Machine Learning · Computer Science 2025-01-31 Gonçalo Paulo , Nora Belrose

State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former - best represented by sparse coding techniques - strive to exploit intrinsic prior knowledge about the unknown…

Image and Video Processing · Electrical Eng. & Systems 2018-11-29 Fangfang Wu , Weisheng Dong , Guangming Shi , Xin Li

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

Machine Learning · Computer Science 2026-05-19 Michał Brzozowski , Neo Christopher Chung

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

Continual learning (CL) has remained a significant challenge for deep neural networks as learning new tasks erases previously acquired knowledge, either partially or completely. Existing solutions often rely on experience rehearsal or full…

Machine Learning · Computer Science 2025-05-29 Prashant Bhat , Laurens Niesten , Elahe Arani , Bahram Zonooz

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

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

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Machine Learning · Computer Science 2026-05-13 Hyeonjin Kim , Hangyeol Jung , Heechan Yun , Sungjun Yun , Dong-Jun Han