English
Related papers

Related papers: Hey Pentti, We Did It!: A Fully Vector-Symbolic Li…

200 papers

Lip Reading, or Visual Automatic Speech Recognition (V-ASR), is a complex task requiring the interpretation of spoken language exclusively from visual cues, primarily lip movements and facial expressions. This task is especially challenging…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Marshall Thomas , Edward Fish , Richard Bowden

Classic grammars and regular expressions can be used for a variety of purposes, including parsing, intent detection, and matching. However, the comparisons are performed at a structural level, with constituent elements (words or characters)…

Computation and Language · Computer Science 2018-08-16 David Wingate , William Myers , Nancy Fulda , Tyler Etchart

We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs. Relative to traditional word representation models that have independent vectors for each word type, our model requires…

Computation and Language · Computer Science 2016-05-25 Wang Ling , Tiago Luís , Luís Marujo , Ramón Fernandez Astudillo , Silvio Amir , Chris Dyer , Alan W. Black , Isabel Trancoso

\textsc{Lara} is a key-value algebra that aims at unifying linear and relational algebra with three types of operation abstraction. The study of \textsc{Lara}'s expressive ability reports that it can represent relational algebra and most…

Databases · Computer Science 2023-07-18 Hongxiao Li , Wanling Gao , Lei Wang , Jianfeng Zhan

Algebraic lambda-calculi have been studied in various ways, but their semantics remain mostly untouched. In this paper we propose a semantic analysis of a general simply-typed lambda-calculus endowed with a structure of vector space. We…

Logic in Computer Science · Computer Science 2010-06-09 Benoît Valiron

Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level open-vocabulary semantic segmentation without additional…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Lin Sun , Jiale Cao , Jin Xie , Xiaoheng Jiang , Yanwei Pang

We over-approximate reachability sets in string rewriting by languages defined by admissible factors, called tiles. A sparse set of tiles contains only those that are reachable in derivations, and is constructed by completing an automaton.…

Logic in Computer Science · Computer Science 2020-03-04 Alfons Geser , Dieter Hofbauer , Johannes Waldmann

Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, represent images and texts as dense embeddings and calculate…

Computer Vision and Pattern Recognition · Computer Science 2023-02-09 Chen Chen , Bowen Zhang , Liangliang Cao , Jiguang Shen , Tom Gunter , Albin Madappally Jose , Alexander Toshev , Jonathon Shlens , Ruoming Pang , Yinfei Yang

In machine lip-reading, which is identification of speech from visual-only information, there is evidence to show that visual speech is highly dependent upon the speaker [1]. Here, we use a phoneme-clustering method to form new…

Computer Vision and Pattern Recognition · Computer Science 2018-04-26 Helen L. Bear , Stephen J. Cox , Richard W. Harvey

A famous result of Lieb establishes that the map $(A,B) \mapsto \text{tr}\left[K^* A^{1-t} K B^t\right]$ is jointly concave in the pair $(A,B)$ of positive definite matrices, where $K$ is a fixed matrix and $t \in [0,1]$. In this paper we…

Optimization and Control · Mathematics 2020-04-14 Hamza Fawzi , James Saunderson

Some of the most important compartmental systems, such as irreversible catenary, mamillary and circular systems are symbolically simplified by the method of exact linear lumping. A few symbolically unmanageable systems are numerically…

Classical Analysis and ODEs · Mathematics 2008-02-21 E. Egri , J. Tóth , C. Brochot , F. Y. Bois

Vectorization is a compiler optimization that replaces multiple operations on scalar values with a single operation on vector values. Although common in traditional compilers such as rustc, clang, and gcc, vectorization is not common in the…

The architecture of multimodal large language models (MLLMs) commonly connects a vision encoder, often based on CLIP-ViT, to a large language model. While CLIP-ViT works well for capturing global image features, it struggles to model local…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Haoran Lou , Chunxiao Fan , Ziyan Liu , Yuexin Wu , Xinliang Wang

Transformer-based language models display impressive reasoning-like behavior, yet remain brittle on tasks that require stable symbolic manipulation. This paper develops a unified perspective on these phenomena by interpreting self-attention…

Artificial Intelligence · Computer Science 2025-12-18 Sahil Rajesh Dhayalkar

We present a semi-unified sparse dictionary learning framework that bridges the gap between classical sparse models and modern deep architectures. Specifically, the method integrates strict Top-$K$ LISTA and its convex FISTA-based variant…

Machine Learning · Computer Science 2025-11-14 Fengsheng Lin , Shengyi Yan , Trac Duy Tran

We address a problem connected to the unfolding semantics of functional programming languages: give a useful characterization of those infinite lambda-terms that are lambda_{letrec}-expressible in the sense that they arise as infinite…

Programming Languages · Computer Science 2013-05-28 Clemens Grabmayer , Jan Rochel

Representation learning and \emph{de novo} generation of proteins are pivotal computational biology tasks. Whilst natural language processing (NLP) techniques have proven highly effective for protein sequence modelling, structure modelling…

Quantitative Methods · Quantitative Biology 2025-01-08 Benoit Gaujac , Jérémie Donà , Liviu Copoiu , Timothy Atkinson , Thomas Pierrot , Thomas D. Barrett

Graphical languages, like quantum circuits or ZX-calculus, have been successfully designed to represent (memoryless) quantum computations acting on a finite number of qubits. Meanwhile, delayed traces have been used as a graphical way to…

Quantum Physics · Physics 2021-04-29 Titouan Carette , Marc de Visme , Simon Perdrix

Current distributed representations of words show little resemblance to theories of lexical semantics. The former are dense and uninterpretable, the latter largely based on familiar, discrete classes (e.g., supersenses) and relations (e.g.,…

Computation and Language · Computer Science 2015-06-08 Manaal Faruqui , Yulia Tsvetkov , Dani Yogatama , Chris Dyer , Noah Smith

Saliency maps can explain a neural model's predictions by identifying important input features. They are difficult to interpret for laypeople, especially for instances with many features. In order to make them more accessible, we formalize…

Computation and Language · Computer Science 2023-06-08 Nils Feldhus , Leonhard Hennig , Maximilian Dustin Nasert , Christopher Ebert , Robert Schwarzenberg , Sebastian Möller