English
Related papers

Related papers: Continuous-Depth Field Theory for Transformer Patc…

200 papers

Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces…

Artificial Intelligence · Computer Science 2026-05-08 Ruben Fernandez-Boullon , David N. Olivieri

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

We perform an effective-theory analysis of forward-backward signal propagation in wide and deep Transformers, i.e., residual neural networks with multi-head self-attention blocks and multilayer perceptron blocks. This analysis suggests…

Machine Learning · Computer Science 2023-04-06 Emily Dinan , Sho Yaida , Susan Zhang

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing…

Machine Learning · Computer Science 2025-11-27 Matīss Kalnāre , Sofoklis Kitharidis , Thomas Bäck , Niki van Stein

Neural networks are growing more capable on their own, but we do not understand their neural mechanisms. Understanding these mechanisms' decision-making processes, or mechanistic interpretability, enables (1) accountability and control in…

Computation and Language · Computer Science 2026-03-02 Mason Kadem , Rong Zheng

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

The field of natural language processing has reached breakthroughs with the advent of transformers. They have remained state-of-the-art since then, and there also has been much research in analyzing, interpreting, and evaluating the…

Computation and Language · Computer Science 2023-12-12 Soniya Vijayakumar

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for…

Artificial Intelligence · Computer Science 2025-10-14 Daking Rai , Yilun Zhou , Shi Feng , Abulhair Saparov , Ziyu Yao

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

Mechanistic interpretability focuses on reverse engineering the internal mechanisms learned by neural networks. We extend our focus and propose to mechanistically forward engineer using our framework based on Concept Bottleneck Models. In…

Machine Learning · Computer Science 2025-12-01 Angela van Sprang , Erman Acar , Willem Zuidema

Retrosynthesis prediction is one of the fundamental challenges in organic synthesis. The task is to predict the reactants given a core product. With the advancement of machine learning, computer-aided synthesis planning has gained…

Chemical Physics · Physics 2022-02-01 Yue Wan , Benben Liao , Chang-Yu Hsieh , Shengyu Zhang

Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained…

High Energy Physics - Phenomenology · Physics 2026-05-12 Saurabh Rai , Sanmay Ganguly

Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a…

Machine Learning · Computer Science 2023-10-31 Arthur Conmy , Augustine N. Mavor-Parker , Aengus Lynch , Stefan Heimersheim , Adrià Garriga-Alonso

Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks. In order to visualize the parts of the image that led to a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Hila Chefer , Shir Gur , Lior Wolf

Residual networks have significantly better trainability and thus performance than feed-forward networks at large depth. Introducing skip connections facilitates signal propagation to deeper layers. In addition, previous works found that…

Disordered Systems and Neural Networks · Physics 2025-10-24 Kirsten Fischer , David Dahmen , Moritz Helias

Transition path theory (TPT) offers a powerful formalism for extracting the rate and mechanism of rare dynamical transitions between metastable states. Most applications of TPT either focus on systems with modestly sized state spaces or use…

Statistical Mechanics · Physics 2026-01-14 Nils E. Strand , Schuyler B. Nicholson , Hadrien Vroylandt , Todd R. Gingrich

Capturing the long-range dependencies has empirically proven to be effective on a wide range of computer vision tasks. The progressive advances on this topic have been made through the employment of the transformer framework with the help…

Computer Vision and Pattern Recognition · Computer Science 2022-09-21 Dong Zhang , Jinhui Tang , Kwang-Ting Cheng

Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on…

Machine Learning · Computer Science 2022-06-24 Ameen Ali , Thomas Schnake , Oliver Eberle , Grégoire Montavon , Klaus-Robert Müller , Lior Wolf

With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Boyi Liu , Qi Cai , Lingxiao Wang , Zhaoran Wang

In this report we investigate fundamental requirements for the application of classifier patching on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary…

Machine Learning · Computer Science 2019-01-17 Sebastian Kauschke , David Hermann Lehmann
‹ Prev 1 2 3 10 Next ›