English
Related papers

Related papers: Concept Boundary Vectors

200 papers

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Machine Learning · Computer Science 2026-05-19 Katarzyna Filus , Kamil Faber , Roberto Corizzo , Christopher Kanan

We first observe a potential weakness of continuous vector representations of symbols in neural machine translation. That is, the continuous vector representation, or a word embedding vector, of a symbol encodes multiple dimensions of…

Computation and Language · Computer Science 2016-07-05 Heeyoul Choi , Kyunghyun Cho , Yoshua Bengio

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced…

Computer Vision and Pattern Recognition · Computer Science 2022-02-04 Chi Wang , Yunke Zhang , Miaomiao Cui , Peiran Ren , Yin Yang , Xuansong Xie , XianSheng Hua , Hujun Bao , Weiwei Xu

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Martina G. Vilas , Timothy Schaumlöffel , Gemma Roig

We introduce a recurrent neural network model of working memory combining short-term and long-term components. e short-term component is modelled using a gated reservoir model that is trained to hold a value from an input stream when a gate…

Neural and Evolutionary Computing · Computer Science 2020-03-27 Anthony Strock , Nicolas Rougier , Xavier Hinaut

We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-existing vocabulary.…

Machine Learning · Computer Science 2024-01-12 Matthew Trager , Pramuditha Perera , Luca Zancato , Alessandro Achille , Parminder Bhatia , Stefano Soatto

Concept-Based Models (CBMs) are a class of deep learning models that provide interpretability by explaining predictions through high-level concepts. These models first predict concepts and then use them to perform a downstream task.…

Machine Learning · Computer Science 2025-06-27 David Debot , Pietro Barbiero , Gabriele Dominici , Giuseppe Marra

In this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminative, combining distributional and lexical semantics in an…

Computation and Language · Computer Science 2020-10-08 Machel Reid , Edison Marrese-Taylor , Yutaka Matsuo

Large Language Models achieve next-token prediction by transporting a vectorized piece of text (prompt) across an accompanying embedding space under the action of successive transformer layers. The resulting high-dimensional trajectories…

Machine Learning · Computer Science 2025-02-17 Raphaël Sarfati , Toni J. B. Liu , Nicolas Boullé , Christopher J. Earls

Insights into the learned latent representations are imperative for verifying deep neural networks (DNNs) in critical computer vision (CV) tasks. Therefore, state-of-the-art supervised Concept-based eXplainable Artificial Intelligence…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Georgii Mikriukov , Gesina Schwalbe , Korinna Bade

Over the past years, distributed semantic representations have proved to be effective and flexible keepers of prior knowledge to be integrated into downstream applications. This survey focuses on the representation of meaning. We start from…

Computation and Language · Computer Science 2018-10-29 Jose Camacho-Collados , Mohammad Taher Pilehvar

The present paper reviews and discusses work from computer science that proposes to identify concepts in internal representations (hidden layers) of DNNs. It is examined, first, how existing methods actually identify concepts that are…

Machine Learning · Computer Science 2023-11-06 Tim Räz

Concept Bottleneck Models (CBMs) map the inputs onto a set of interpretable concepts (``the bottleneck'') and use the concepts to make predictions. A concept bottleneck enhances interpretability since it can be investigated to understand…

Machine Learning · Computer Science 2023-02-03 Mert Yuksekgonul , Maggie Wang , James Zou

Continual learning aims to update models under distribution shift without forgetting, yet many high-stakes deployments, such as healthcare, also require interpretability. In practice, models that adapt well (e.g., deep networks) are often…

Machine Learning · Computer Science 2026-04-21 Dongkyu Cho , Xiyue Li , Samrachana Adhikari , Rumi Chunara

The next-token prediction (NTP) objective has been foundational in the development of modern large language models (LLMs), driving advances in fluency and generalization. However, NTP operates at the \textit{token} level, treating…

Computation and Language · Computer Science 2026-01-23 Laya Iyer , Pranav Somani , Alice Guo , Dan Jurafsky , Chen Shani

We consider the problem of communicating a sequence of concepts, i.e., unknown and potentially stochastic maps, which can be observed only through examples, i.e., the mapping rules are unknown. The transmitter applies a learning algorithm…

Information Theory · Computer Science 2023-05-16 Francesco Pase , Szymon Kobus , Deniz Gunduz , Michele Zorzi

The visual representation of concepts or ideas through the use of simple shapes has always been explored in the history of Humanity, and it is believed to be the origin of writing. We focus on computational generation of visual symbols to…

Graphics · Computer Science 2017-08-01 João Miguel Cunha , Pedro Martins , Amílcar Cardoso , Penousal Machado

Topic models are frequently used in machine learning owing to their high interpretability and modular structure. However, extending a topic model to include a supervisory signal, to incorporate pre-trained word embedding vectors and to…

Machine Learning · Statistics 2019-09-17 Ryohei Hisano

Machine learning is a vital part of many real-world systems, but several concerns remain about the lack of interpretability, explainability and robustness of black-box AI systems. Concept Bottleneck Models (CBM) address some of these…

Machine Learning · Statistics 2025-10-24 Hidde Fokkema , Tim van Erven , Sara Magliacane

Deep latent variable models learn condensed representations of data that, hopefully, reflect the inner workings of the studied phenomena. Unfortunately, these latent representations are not statistically identifiable, meaning they cannot be…

Machine Learning · Statistics 2025-06-02 Stas Syrota , Yevgen Zainchkovskyy , Johnny Xi , Benjamin Bloem-Reddy , Søren Hauberg