English
Related papers

Related papers: Mechanistic Interpretability of EEG Foundation Mod…

200 papers

Clinical electroencephalogram (EEG) analysis rests on a hand-crafted feature catalog refined over decades, \emph{e.g.,} band power, connectivity, complexity, and more. Modern EEG foundation models bypass this catalog, learn directly from…

Artificial Intelligence · Computer Science 2026-05-15 Ling Tang , Qian Chen , Jilin Mei , Houshi Xu , Quanshi Zhang , Jing Shao , Na Zou , Xia Hu , Dongrui Liu

Sparse Autoencoders (SAEs) have emerged as a powerful paradigm for disentangling feature superposition in transformer-based architectures, enabling precise control via activation steering. However, the theoretical foundations of…

Machine Learning · Computer Science 2026-05-08 Yunpeng Zhou

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

Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been…

Machine Learning · Computer Science 2024-05-27 Dan Braun , Jordan Taylor , Nicholas Goldowsky-Dill , Lee Sharkey

Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover interpretable…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Vladimir Zaigrajew , Hubert Baniecki , Przemyslaw Biecek

Sparse autoencoders (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically identified in isolation. However, broad evidence suggests that LLMs capture the…

Artificial Intelligence · Computer Science 2026-02-13 Yifan Luo , Yang Zhan , Jiedong Jiang , Tianyang Liu , Mingrui Wu , Zhennan Zhou , Bin Dong

Although the Segment Anything Model (SAM) has advanced medical image segmentation, its Bayesian adaptation for uncertainty-aware segmentation remains hindered by three key issues: (1) instability in Bayesian fine-tuning of large pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Bin Huang , Zhong Liu , Huiying Wen , Bingsheng Huang , Xin Chen , Shuo Li

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

Mechanistic interpretability aims to decompose neural networks into interpretable features and map their connecting circuits. The standard approach trains sparse autoencoders (SAEs) on each layer's activations. However, SAEs trained in…

Machine Learning · Computer Science 2025-11-12 Sean P. Fillingham , Andrew Gordon , Peter Lai , Xavier Poncini , David Quarel , Stefan Heimersheim

Sparse Autoencoders (SAEs) have emerged as a useful tool for interpreting the internal representations of neural networks. However, naively optimising SAEs for reconstruction loss and sparsity results in a preference for SAEs that are…

Machine Learning · Computer Science 2024-10-16 Kola Ayonrinde , Michael T. Pearce , Lee Sharkey

Sparse autoencoders (SAEs) decompose neural activations into interpretable features. A widely adopted variant, the TopK SAE, reconstructs each token from its K most active latents. However, this approach is inefficient, as some tokens carry…

Machine Learning · Computer Science 2025-09-01 Narmeen Oozeer , Nirmalendu Prakash , Michael Lan , Alice Rigg , Amirali Abdullah

Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the…

Information Retrieval · Computer Science 2026-01-27 Jiayin Wang , Xiaoyu Zhang , Weizhi Ma , Zhiqiang Guo , Min Zhang

Large-scale text-to-image diffusion models have become the backbone of modern image editing, yet text prompts alone do not offer adequate control over the editing process. Two properties are especially desirable: disentanglement, where…

Graphics · Computer Science 2025-10-07 Ronen Kamenetsky , Sara Dorfman , Daniel Garibi , Roni Paiss , Or Patashnik , Daniel Cohen-Or

Sparse autoencoders (SAEs) are widely used to extract sparse, interpretable latents from transformer activations. We test whether commonly used SAE quality metrics and automatic explanation pipelines can distinguish trained transformers…

Machine Learning · Computer Science 2026-01-28 Thomas Heap , Tim Lawson , Lucy Farnik , Laurence Aitchison

Electrocardiogram (ECG) delineation, the segmentation of meaningful waveform features, is critical for clinical diagnosis. Despite recent advances using deep learning, progress has been limited by the scarcity of publicly available…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Minje Park , Jeonghwa Lim , Taehyung Yu , Sunghoon Joo

Electroencephalography foundation models (EEG-FMs) have advanced brain signal analysis, but the lack of standardized evaluation benchmarks impedes model comparison and scientific progress. Current evaluations rely on inconsistent protocols…

Signal Processing · Electrical Eng. & Systems 2026-02-16 Wei Xiong , Jiangtong Li , Jie Li , Kun Zhu , Changjun Jiang

Sparse autoencoders (SAEs) are used to disentangle the dense, polysemantic internal representations of large language models (LLMs) into interpretable, monosemantic concepts. However, standard $\ell_1$-regularized SAEs suffer from feature…

Machine Learning · Computer Science 2026-05-08 Faris Chaudhry , Keisuke Yano , Anthea Monod

The electroencephalogram (EEG) is a powerful method to understand how the brain processes speech. Linear models have recently been replaced for this purpose with deep neural networks and yield promising results. In related EEG…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-25 Lies Bollens , Tom Francart , Hugo Van Hamme

Electroencephalography provides a non-invasive window into brain activity, offering valuable insights for neurological research, brain-computer interfaces, and clinical diagnostics. However, the development of robust machine learning models…

Signal Processing · Electrical Eng. & Systems 2025-02-26 Chi-Sheng Chen , Ying-Jung Chen , Aidan Hung-Wen Tsai

Riemannian tangent space methods offer state-of-the-art performance in magnetoencephalography (MEG) and electroencephalography (EEG) based applications such as brain-computer interfaces and biomarker development. One limitation,…

‹ Prev 1 8 9 10 Next ›