Related papers: Kaolin: A PyTorch Library for Accelerating 3D Deep…
Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent research leverages Large Language Models (LLMs) to automatically convert PyTorch reference implementations to CUDA kernels,…
We present an open-source tensor network Python library for quantum many-body simulations. At its core is an abelian-symmetric tensor, implemented as a sparse block structure managed by logical layer on top of dense multi-dimensional array…
In this work we introduce a differential rendering module which allows neural networks to efficiently process cluttered data. The module is composed of continuous piecewise differentiable functions defined as a sensor array of cells…
PyOD is an open-source Python toolbox for performing scalable outlier detection on multivariate data. Uniquely, it provides access to a wide range of outlier detection algorithms, including established outlier ensembles and more recent…
The fast-paced development of machine learning (ML) methods coupled with its increasing adoption in research poses challenges for researchers without extensive training in ML. In neuroscience, for example, ML can help understand…
Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…
We introduce torchNTK, a python library to calculate the empirical neural tangent kernel (NTK) of neural network models in the PyTorch framework. We provide an efficient method to calculate the NTK of multilayer perceptrons. We compare the…
This paper introduces torchsom, an open-source Python library that provides a reference implementation of the Self-Organizing Map (SOM) in PyTorch. This package offers three main features: (i) dimensionality reduction, (ii) clustering, and…
Machine learning has emerged as a powerful solution to the modern challenges in accelerator physics. However, the limited availability of beam time, the computational cost of simulations, and the high-dimensionality of optimisation problems…
Even todays most advanced machine learning models are easily fooled by almost imperceptible perturbations of their inputs. Foolbox is a new Python package to generate such adversarial perturbations and to quantify and compare the robustness…
Reinforcement learning is increasingly finding success across domains where the problem can be represented as a Markov decision process. Evolutionary computation algorithms have also proven successful in this domain, exhibiting similar…
MatchingTools is a Python library for doing symbolic calculations in effective field theory. It provides the tools to construct general models by defining their field content and their interaction Lagrangian. Once a model is given, the…
Generative models for molecules have shown considerable promise for use in computational chemistry, but remain difficult to use for non-experts. For this reason, we introduce open-source infrastructure for easily building generative…
As the usage of deep learning becomes increasingly popular in mobile and embedded solutions, it is necessary to convert the framework-specific network representations into executable code for these embedded platforms. This paper consists of…
This paper introduces HyperNOs, a PyTorch library designed to streamline and automate the process of exploring neural operators, with a special focus on hyperparameter optimization for comprehensive and exhaustive exploration. Indeed,…
We present MXtalTools, a flexible Python package for the data-driven modelling of molecular crystals, facilitating machine learning studies of the molecular solid state. MXtalTools comprises several classes of utilities: (1) synthesis,…
There is growing interest in graph pattern mining (GPM) problems such as motif counting. GPM systems have been developed to provide unified interfaces for programming algorithms for these problems and for running them on parallel systems.…
A wide range of transformer-based language models have been proposed for information retrieval tasks. However, including transformer-based models in retrieval pipelines is often complex and requires substantial engineering effort. In this…
Deep learning (DL) has been a revolutionary technique in various domains. To facilitate the model development and deployment, many deep learning frameworks are proposed, among which PyTorch is one of the most popular solutions. The…
Deep learning technologies, particularly deep neural networks (DNNs), have demonstrated significant success across many domains. This success has been accompanied by substantial advancements and innovations in the algorithms behind the…