English
Related papers

Related papers: HyperDAS: Towards Automating Mechanistic Interpret…

200 papers

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

Effective policy learning for robotic manipulation requires scene representations that selectively capture task-relevant environmental features. Current approaches typically employ task-agnostic representation extraction, failing to emulate…

Robotics · Computer Science 2025-09-23 Li Sun , Jiefeng Wu , Feng Chen , Ruizhe Liu , Yanchao Yang

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Machine Learning · Computer Science 2025-03-04 David Klindt , Charles O'Neill , Patrik Reizinger , Harald Maurer , Nina Miolane

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

Machine Learning · Computer Science 2023-07-17 Mara Graziani , Laura O' Mahony , An-Phi Nguyen , Henning Müller , Vincent Andrearczyk

Effective human-robot interaction, such as in robot learning from human demonstration, requires the learning agent to be able to ground abstract concepts (such as those contained within instructions) in a corresponding high-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2018-10-03 Yordan Hristov , Alex Lascarides , Subramanian Ramamoorthy

We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and…

Machine Learning · Computer Science 2020-12-10 Sercan O. Arik , Tomas Pfister

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

Machine Learning · Computer Science 2019-10-08 Yulong Wang , Xiaolin Hu , Hang Su

Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features. To address this limitation, we propose ConceptHash, a novel method that achieves…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Kam Woh Ng , Xiatian Zhu , Yi-Zhe Song , Tao Xiang

Locating and editing knowledge in large language models (LLMs) is crucial for enhancing their accuracy, safety, and inference rationale. We introduce ``concept editing'', an innovative variation of knowledge editing that uncovers…

Computation and Language · Computer Science 2024-08-23 Nura Aljaafari , Danilo S. Carvalho , André Freitas

Differentiable architecture search (DAS) has made great progress in searching for high-performance architectures with reduced computational cost. However, DAS-based methods mainly focus on searching for a repeatable cell structure, which is…

Computer Vision and Pattern Recognition · Computer Science 2021-01-13 Guanting Liu , Yujie Zhong , Sheng Guo , Matthew R. Scott , Weilin Huang

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

Machine Learning · Computer Science 2020-08-27 Darius Afchar , Romain Hennequin

Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown. Existing global explainability methods, such as Network…

Machine Learning · Computer Science 2024-01-19 Kirill Bykov , Laura Kopf , Shinichi Nakajima , Marius Kloft , Marina M. -C. Höhne

Focus in Explainable AI is shifting from explanations defined in terms of low-level elements, such as input features, to explanations encoded in terms of interpretable concepts learned from data. How to reliably acquire such concepts is,…

Machine Learning · Computer Science 2023-09-15 Emanuele Marconato , Andrea Passerini , Stefano Teso

Deep Learning of neural networks has gained prominence in multiple life-critical applications like medical diagnoses and autonomous vehicle accident investigations. However, concerns about model transparency and biases persist. Explainable…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Pedro Valois , Koichiro Niinuma , Kazuhiro Fukui

Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods…

Machine Learning · Computer Science 2024-02-20 Moritz Lange , Raphael C. Engelhardt , Wolfgang Konen , Laurenz Wiskott

Deep neural networks (DNNs) have shown exceptional performances in a wide range of tasks and have become the go-to method for problems requiring high-level predictive power. There has been extensive research on how DNNs arrive at their…

Machine Learning · Computer Science 2023-02-21 Mattias Luber , Anton Thielmann , Benjamin Säfken

Recent advances in text recognition led to a paradigm shift for page-level recognition, from multi-step segmentation-based approaches to end-to-end attention-based ones. However, the na\"ive character-level autoregressive decoding process…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Denis Coquenet

We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for automating the generation of deep neural networks that incorporates user-provided formal knowledge to improve learning from data. We provide formal semantics that…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Karan Sikka , Andrew Silberfarb , John Byrnes , Indranil Sur , Ed Chow , Ajay Divakaran , Richard Rohwer

Neural network-based semantic segmentation has achieved remarkable results when large amounts of annotated data are available, that is, in the supervised case. However, such data is expensive to collect and so methods have been developed to…

Computer Vision and Pattern Recognition · Computer Science 2021-06-25 Xueqing Deng , Yi Zhu , Yuxin Tian , Shawn Newsam

Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities. Although effective, most of these models solely rely on fixed relation representations…

Computation and Language · Computer Science 2021-04-02 Xu Wang , Shuai Zhao , Bo Cheng , Jiale Han , Yingting Li , Hao Yang , Ivan Sekulic , Guoshun Nan