Related papers: nvTorchCam: An Open-source Library for Camera-Agno…
This paper presents a comprehensive comparative survey of TensorFlow and PyTorch, the two leading deep learning frameworks, focusing on their usability, performance, and deployment trade-offs. We review each framework's programming paradigm…
Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many "hard" primitives in these libraries such as thresholding, Boolean logic, discrete…
Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing open-source models often exhibit blind tool-use reasoning…
PyTorch has ascended as a premier machine learning framework, yet it lacks a native and comprehensive library for decision and control tasks suitable for large development teams dealing with complex real-world data and environments. To…
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed…
As robotic navigation techniques in perception and planning advance, mobile robots increasingly venture into off-road environments involving complex traversability. However, selecting suitable planning methods remains a challenge due to…
Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generative models, and reliable recurrent networks. Despite…
Deep learning techniques are becoming increasingly important to solve a number of image processing tasks. Among common algorithms, Convolutional Neural Networks and Recurrent Neural Networks based systems achieve state of the art results on…
This paper presents TorchNWP, a compilation library tool for the efficient coupling of artificial intelligence components and traditional numerical models. It aims to address the issues of poor cross-language compatibility, insufficient…
We design and implement a ready-to-use library in PyTorch for performing micro-batch pipeline parallelism with checkpointing proposed by GPipe (Huang et al., 2019). In particular, we develop a set of design components to enable…
We explore different approaches to integrating a simple convolutional neural network (CNN) with the Lucene search engine in a multi-stage ranking architecture. Our models are trained using the PyTorch deep learning toolkit, which is…
Python has become the de-facto language for training deep neural networks, coupling a large suite of scientific computing libraries with efficient libraries for tensor computation such as PyTorch or TensorFlow. However, when models are used…
Large Transformers have achieved state-of-the-art performance across many tasks. Most open-source libraries on scaling Transformers focus on improving training or inference with better parallelization. In this work, we present TorchScale,…
This paper documents Int2Int, an open source code base for using transformers on problems of mathematical research, with a focus on number theory and other problems involving integers. Int2Int is a complete PyTorch implementation of a…
fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and…
We present PyMoosh, a Python-based simulation library designed to provide a comprehensive set of numerical tools allowing to compute essentially all optical characteristics of multilayered structures, ranging from reflectance and…
Recent advancements in code completion models have primarily focused on local file contexts. However, these studies do not fully capture the complexity of real-world software development, which often requires the use of rapidly-evolving…
Emerging memory technologies have gained significant attention as a promising pathway to overcome the limitations of conventional computing architectures in deep learning applications. By enabling computation directly within memory, these…
We introduce CVNets, a high-performance open-source library for training deep neural networks for visual recognition tasks, including classification, detection, and segmentation. CVNets supports image and video understanding tools,…
Earth observation machine learning pipelines differ fundamentally from standard computer vision workflows. Imagery is typically delivered as large, georeferenced scenes, labels may be raster masks or vector geometries in distinct coordinate…