English
Related papers

Related papers: Compiling Diderot: From Tensor Calculus to C

200 papers

Efficient tensor computation is a cornerstone of modern deep learning (DL) workloads, yet existing approaches struggle to achieve flexible and performant design and implementation of tensor layouts -- mappings between logical tensors and…

This paper describes serial and parallel compositional models of multiple objects with part sharing. Objects are built by part-subpart compositions and expressed in terms of a hierarchical dictionary of object parts. These parts are…

Computer Vision and Pattern Recognition · Computer Science 2013-01-17 Alan L. Yuille , Roozbeh Mottaghi

Symmetric tensor decomposition is an important problem with applications in several areas for example signal processing, statistics, data analysis and computational neuroscience. It is equivalent to Waring's problem for homogeneous…

Symbolic Computation · Computer Science 2019-09-12 Matías Bender , Jean-Charles Faugère , Ludovic Perret , Elias Tsigaridas

Computer-Aided Design (CAD) powers modern engineering, yet producing high-quality parts still demands substantial expert effort. Many AI systems tackle CAD reverse engineering, but most are single-pass and miss fine geometric details. In…

Extracting context from visual representations is of utmost importance in the advancement of Computer Science. Representation of such a format in Natural Language has a huge variety of applications such as helping the visually impaired etc.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-25 Madhavan Seshadri , Malavika Srikanth , Mikhail Belov

Binary embedding of high-dimensional data requires long codes to preserve the discriminative power of the input space. Traditional binary coding methods often suffer from very high computation and storage costs in such a scenario. To…

Machine Learning · Statistics 2014-05-14 Felix X. Yu , Sanjiv Kumar , Yunchao Gong , Shih-Fu Chang

[abridged] Context: Multidimensional arrays are used by many different algorithms. As such, indexing and broadcasting complex operations over multidimensional arrays are ubiquitous tasks and can be performance limiting. Inquiry:…

Mathematical Software · Computer Science 2017-04-04 Florian Heyl , Oliver Serang

Stencil computations are a key part of many high-performance computing applications, such as image processing, convolutional neural networks, and finite-difference solvers for partial differential equations. Devito is a framework capable of…

Graphical tensor notation is a simple way of denoting linear operations on tensors, originating from physics. Modern deep learning consists almost entirely of operations on or between tensors, so easily understanding tensor operations is…

Machine Learning · Computer Science 2024-02-06 Jordan K. Taylor

Implicit Neural Representations (INRs) aim to parameterize discrete signals through implicit continuous functions. However, formulating each image with a separate neural network~(typically, a Multi-Layer Perceptron (MLP)) leads to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-20 Wenyong Zhou , Taiqiang Wu , Zhengwu Liu , Yuxin Cheng , Chen Zhang , Ngai Wong

We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to build a more accurate and thorough connection between image…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Zhicheng Huang , Zhaoyang Zeng , Bei Liu , Dongmei Fu , Jianlong Fu

Deep learning models rely on highly optimized tensor libraries for efficient inference on heterogeneous hardware. Current deep compilers typically predetermine layouts of tensors and then optimize loops of operators. However, such…

Machine Learning · Computer Science 2022-11-01 Zhiying Xu , Jiafan Xu , Hongding Peng , Wei Wang , Xiaoliang Wang , Haoran Wan , Haipeng Dai , Yixu Xu , Hao Cheng , Kun Wang , Guihai Chen

Reasoning Segmentation (RS) is a multimodal vision-text task that requires segmenting objects based on implicit text queries, demanding both precise visual perception and vision-text reasoning capabilities. Current RS approaches rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Yizhen Li , Dell Zhang , Xuelong Li , Yiqing Shen

Approximation of non-linear kernels using random feature maps has become a powerful technique for scaling kernel methods to large datasets. We propose $\textit{Tensor Sketch}$, an efficient random feature map for approximating polynomial…

Data Structures and Algorithms · Computer Science 2025-05-20 Ninh Pham , Rasmus Pagh

Edge detection serves as a critical foundation for numerous computer vision applications, including object detection, semantic segmentation, and image editing, by extracting essential structural cues that define object boundaries and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Yuanbin Fu , Liang Li , Xiaojie Guo

Motion planning and control problems are embedded and essential in almost all robotics applications. These problems are often formulated as stochastic optimal control problems and solved using dynamic programming algorithms. Unfortunately,…

Robotics · Computer Science 2018-01-12 Alex A. Gorodetsky , Sertac Karaman , Youssef M. Marzouk

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Computation and Language · Computer Science 2023-05-26 Francesco Fusco , Diego Antognini

Vision foundation models have shown great promise for open-set 3D object retrieval (3DOR) through efficient adaptation to multi-view images. Leveraging semantically aligned latent space, previous work typically adapts the CLIP encoder to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Xinwei He , Yansong Zheng , Qianru Han , Zhichuan Wang , Yuxuan Cai , Yang Zhou , Jingbo Xia , Yulong Wang , Jinhai Xiang , Xiang Bai

In this paper, we propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains under conditions of limited training data and significant visual differences. The main idea behind our…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yong Du , Jiahui Zhan , Xinzhe Li , Junyu Dong , Sheng Chen , Ming-Hsuan Yang , Shengfeng He

Probabilistic inference is fundamentally hard, yet many tasks require optimization on top of inference, which is even harder. We present a new optimization-via-compilation strategy to scalably solve a certain class of such problems. In…

Programming Languages · Computer Science 2025-04-11 Minsung Cho , John Gouwar , Steven Holtzen