English
Related papers

Related papers: Interpreting CFD Surrogates through Sparse Autoenc…

200 papers

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

Diffusion kernels over graphs have been widely utilized as effective tools in various applications due to their ability to accurately model the flow of information through nodes and edges. However, there is a notable gap in the literature…

Numerical Analysis · Mathematics 2026-04-15 Giuseppe Alessio D'Inverno , Kylian Ajavon , Simone Brugiapaglia

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 (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

Deepfake detection models have achieved high accuracy in identifying synthetic media, but their decision processes remain largely opaque. In this paper we present a mechanistic interpretability framework for deepfake detection applied to a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Subramanyam Sahoo , Jared Junkin

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…

Scientific measurements are often bottlenecked by suboptimal conditions, whether that be noise, incomplete spatial coverage, or limited resolution, rendering accurate field reconstruction a difficult task. We introduce LatentPDE, a latent…

Machine Learning · Computer Science 2026-04-28 Valerie Tsao , Nathaniel Chaney , Manolis Veveakis

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This…

Sound · Computer Science 2026-03-03 Nikhil Singh , Manuel Cherep , Pattie Maes

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

RFdiffusion is a popular and well-established model for generation of protein structures. However, this generative process offers limited insight into its internal representations and how they contribute to the final protein structure.…

Quantitative Methods · Quantitative Biology 2025-12-01 Wojciech Zarzecki , Paulina Szymczak , Ewa Szczurek , Kamil Deja

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Mateusz Pach , Shyamgopal Karthik , Quentin Bouniot , Serge Belongie , Zeynep Akata

In chemical process engineering, surrogate models of complex systems are often necessary for tasks of domain exploration, sensitivity analysis of the design parameters, and optimization. A suite of computational fluid dynamics (CFD)…

Computational Engineering, Finance, and Science · Computer Science 2020-09-09 Gabriel F. N. Gonçalves , Assen Batchvarov , Yuyi Liu , Yuxin Liu , Lachlan Mason , Indranil Pan , Omar K. Matar

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

Machine Learning · Computer Science 2019-08-20 Marco Rudolph , Bastian Wandt , Bodo Rosenhahn

Numerical solutions of partial differential equations (PDEs) require expensive simulations, limiting their application in design optimization, model-based control, and large-scale inverse problems. Surrogate modeling techniques seek to…

Computational Physics · Physics 2022-05-18 James Duvall , Karthik Duraisamy , Shaowu Pan

A novel convolutional autoencoder neural ODE (CAE-NODE) framework is proposed for a reduced-order model (ROM) of transient 2D counterflow flames, as an extension of AE-NODE methods in homogeneous reactive systems to spatially resolved…

Surrogate strategies are used widely for uncertainty quantification of groundwater models in order to improve computational efficiency. However, their application to dynamic multiphase flow problems is hindered by the curse of…

Machine Learning · Statistics 2019-05-02 Shaoxing Mo , Yinhao Zhu , Nicholas Zabaras , Xiaoqing Shi , Jichun Wu

Numerical simulation of multi-phase fluid dynamics in porous media is critical for many energy and environmental applications in Earth's subsurface. Data-driven surrogate modeling provides computationally inexpensive alternatives to…

Computational Physics · Physics 2024-04-16 Jiamin Jiang , Bo Guo

Efficient surrogate modelling is a key requirement for uncertainty quantification in data-driven scenarios. In this work, a novel approach of using Sparse Random Features for surrogate modelling in combination with self-supervised…

Machine Learning · Computer Science 2023-01-02 Maternus Herold , Anna Veselovska , Jonas Jehle , Felix Krahmer

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

In recent years, data-driven deep learning models have gained significant interest in the analysis of turbulent dynamical systems. Within the context of reduced-order models (ROMs), convolutional autoencoders (CAEs) pose a universally…