English
Related papers

Related papers: Dictionary Learning Improves Patch-Free Circuit Di…

200 papers

Many proposed applications of neural networks in machine learning, cognitive/brain science, and society hinge on the feasibility of inner interpretability via circuit discovery. This calls for empirical and theoretical explorations of…

Artificial Intelligence · Computer Science 2025-04-02 Federico Adolfi , Martina G. Vilas , Todd Wareham

Phaseless diffraction measurements recorded by a CCD detector are often affected by Poisson noise. In this paper, we propose a dictionary learning model by employing patches based sparsity to denoise Poisson phaseless measurement. The model…

Optimization and Control · Mathematics 2019-06-10 Huibin Chang , Stefano Marchesini

We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…

Machine Learning · Computer Science 2021-12-20 Omid Madani

Mechanistic interpretability seeks to understand the internal mechanisms of machine learning models, where localization -- identifying the important model components -- is a key step. Activation patching, also known as causal tracing or…

Machine Learning · Computer Science 2024-01-18 Fred Zhang , Neel Nanda

Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models. However, it remains unclear whether structural sparsity…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Siyu Zhang

Dictionary learning is the task of determining a data-dependent transform that yields a sparse representation of some observed data. The dictionary learning problem is non-convex, and usually solved via computationally complex iterative…

Machine Learning · Computer Science 2016-11-30 Cristian Rusu , Nuria Gonzalez-Prelcic , Robert Heath

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis --…

Computation and Language · Computer Science 2025-11-11 Giuseppe Birardi

Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Hugo Porta , Emanuele Dalsasso , Diego Marcos , Devis Tuia

Circuit discovery, which involves identifying sparse and task-relevant subnetworks in pre-trained language models, is a cornerstone of mechanistic interpretability. Automated Circuit Discovery (ACDC) has emerged as a pivotal methodology in…

Machine Learning · Computer Science 2025-10-28 Xinhai Wang , Shu Yang , Liangyu Wang , Lin Zhang , Huanyi Xie , Lijie Hu , Di Wang

Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activations. Specifically, recent studies have explored subspace…

Machine Learning · Computer Science 2023-12-07 Aleksandar Makelov , Georg Lange , Neel Nanda

This work addresses the problem of learning sparse representations of tensor data using structured dictionary learning. It proposes learning a mixture of separable dictionaries to better capture the structure of tensor data by generalizing…

Machine Learning · Computer Science 2020-06-16 Mohsen Ghassemi , Zahra Shakeri , Anand D. Sarwate , Waheed U. Bajwa

Partial discharge (PD) is a common indication of faults in power systems, such as generators, and cables. These PD can eventually result in costly repairs and substantial power outages. PD detection traditionally relies on hand-crafted…

Signal Processing · Electrical Eng. & Systems 2021-03-22 Gabriel Michau , Chi-Ching Hsu , Olga Fink

Underlying mechanisms of memorization in LLMs -- the verbatim reproduction of training data -- remain poorly understood. What exact part of the network decides to retrieve a token that we would consider as start of memorization sequence?…

Computation and Language · Computer Science 2026-02-04 Ilya Lasy , Peter Knees , Stefan Woltran

This paper introduces a novel Transitional Dictionary Learning (TDL) framework that can implicitly learn symbolic knowledge, such as visual parts and relations, by reconstructing the input as a combination of parts with implicit relations.…

Artificial Intelligence · Computer Science 2025-03-19 Junyan Cheng , Peter Chin

Sparse coding in learned dictionaries has been established as a successful approach for signal denoising, source separation and solving inverse problems in general. A dictionary learning method adapts an initial dictionary to a particular…

Machine Learning · Statistics 2012-10-18 Christian D. Sigg , Tomas Dikk , Joachim M. Buhmann

This paper presents an approach to parsing humans when there is significant occlusion. We model humans using a graphical model which has a tree structure building on recent work [32, 6] and exploit the connectivity prior that, even in…

Computer Vision and Pattern Recognition · Computer Science 2015-11-25 Xianjie Chen , Alan Yuille

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Computation and Language · Computer Science 2026-05-05 Or Shafran , Atticus Geiger , Mor Geva

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

Trajectory representation learning on a network enhances our understanding of vehicular traffic patterns and benefits numerous downstream applications. Existing approaches using classic machine learning or deep learning embed trajectories…

Machine Learning · Computer Science 2023-12-14 Yuanbo Tang , Zhiyuan Peng , Yang Li

While language models demonstrate sophisticated syntactic capabilities, the extent to which their internal mechanisms align with cross-constructional principles studied in linguistics remains poorly understood. This study investigates…

Computation and Language · Computer Science 2026-04-27 Ryoma Kumon , Hitomi Yanaka