Related papers: SCENIC: A JAX Library for Computer Vision Research…
In this work, we tackle the problems of efficiency and scalability for predictive coding networks (PCNs) in machine learning. To do so, we propose a library, called PCX, that focuses on performance and simplicity, and use it to implement a…
We describe SynthPix, a synthetic image generator for Particle Image Velocimetry (PIV) with a focus on performance and parallelism on accelerators, implemented in JAX. SynthPix produces PIV image pairs from prescribed flow fields while…
The ability to efficiently search for images is essential for improving the user experiences across various products. Incorporating user feedback, via multi-modal inputs, to navigate visual search can help tailor retrieved results to…
Deep learning-based vision is characterized by intricate frameworks that often necessitate a profound understanding, presenting a barrier to newcomers and limiting broad adoption. With many researchers grappling with the constraints of…
We introduce the Unity Perception package which aims to simplify and accelerate the process of generating synthetic datasets for computer vision tasks by offering an easy-to-use and highly customizable toolset. This open-source package…
We analyze the grounded SCAN (gSCAN) benchmark, which was recently proposed to study systematic generalization for grounded language understanding. First, we study which aspects of the original benchmark can be solved by commonly used…
Ensuring the functional correctness and safety of autonomous vehicles is a major challenge for the automotive industry. However, exhaustive physical test drives are not feasible, as billions of driven kilometers would be required to obtain…
The field of human-centered computing has known a major progress these past few years. It is admitted that this field is multidisciplinary and that the human is the core of the system. It shows two matters of concern: multidisciplinary and…
Much of today's machine learning research involves interpreting, modifying or visualizing models after they are trained. I present Penzai, a neural network library designed to simplify model manipulation by representing models as simple…
Research-computing continues to play an ever increasing role in academia. Access to computing resources, however, varies greatly between institutions. Sustaining the growing need for computing skills and access to advanced…
Seglearn is an open-source python package for machine learning time series or sequences using a sliding window segmentation approach. The implementation provides a flexible pipeline for tackling classification, regression, and forecasting…
Many applications in important problem domains such as machine learning and computer vision are streaming applications that take a sequence of inputs over time. It is challenging to find knob settings that optimize the run-time performance…
While world models are increasingly positioned as a pathway to overcoming data scarcity in domains such as robotics, open training infrastructure for world modeling remains nascent. We introduce Jasmine, a performant JAX-based world…
Deep learning has become popular because of its potential to achieve high accuracy in prediction tasks. However, accuracy is not always the only goal of statistical modelling, especially for models developed as part of scientific research.…
Story Visualization is an advanced task of computed vision that targets sequential image synthesis, where the generated samples need to be realistic, faithful to their conditioning and sequentially consistent. Our work proposes a novel…
Natural language instructions for visual navigation often use scene descriptions (e.g., "bedroom") and object references (e.g., "green chairs") to provide a breadcrumb trail to a goal location. This work presents a transformer-based…
Draco introduced a constraint-based framework to model visualization design in an extensible and testable form. It provides a way to abstract design guidelines from theoretical and empirical studies and applies the knowledge in automated…
We present the Seismic Laboratory for Imaging and Modeling/Monitoring (SLIM) open-source software framework for computational geophysics and, more generally, inverse problems involving the wave-equation (e.g., seismic and medical…
Transformer models have shown great potential in computer vision, following their success in language tasks. Swin Transformer is one of them that outperforms convolution-based architectures in terms of accuracy, while improving efficiency…
We present scg-cli, a~command line tool facilitating software comprehension. The tool extracts semantic information about code structure and dependencies from the Java and Scala projects, and structures it as a~Semantic Code Graph (SCG), an…