Tootfinder

torchsom: The Reference PyTorch Library for Self-Organizing Maps
Louis Berthier, Ahmed Shokry, Maxime Moreaud, Guillaume Ramelet, Eric Moulines
https://arxiv.org/abs/2510.11147 …

torchsom: The Reference PyTorch Library for Self-Organizing Maps
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 (iii) friendly data visualization. It relies on a PyTorch backend, enabling (i) fast and efficient training of SOMs through GPU acceleration, and (ii) easy and scalable integrations with PyTorch ecosystem. Moreover, torchsom follows the scikit-learn API for e…

Tensor Logic: The Language of AI
Pedro Domingos
https://arxiv.org/abs/2510.12269 https://arxiv.org/pdf/2510.12269…

Tensor Logic: The Language of AI
Progress in AI is hindered by the lack of a programming language with all the requisite features. Libraries like PyTorch and TensorFlow provide automatic differentiation and efficient GPU implementation, but are additions to Python, which was never intended for AI. Their lack of support for automated reasoning and knowledge acquisition has led to a long and costly series of hacky attempts to tack them on. On the other hand, AI languages like LISP an Prolog lack scalability and support for learn…

TorchCor: High-Performance Cardiac Electrophysiology Simulations with the Finite Element Method on GPUs
Bei Zhou, Maximilian Balmus, Cesare Corrado, Ludovica Cicci, Shuang Qian, Steven A. Niederer
https://arxiv.org/abs/2510.12011

TorchCor: High-Performance Cardiac Electrophysiology Simulations with the Finite Element Method on GPUs
Cardiac electrophysiology (CEP) simulations are increasingly used for understanding cardiac arrhythmias and guiding clinical decisions. However, these simulations typically require high-performance computing resources with numerous CPU cores, which are often inaccessible to many research groups and clinicians. To address this, we present TorchCor, a high-performance Python library for CEP simulations using the finite element method on general-purpose GPUs. Built on PyTorch, TorchCor significant…

JND-Guided Light-Weight Neural Pre-Filter for Perceptual Image Coding
Chenlong He, Zijing Dong, Min Li, Zhijian Hao, Leilei Huang, Xiaoyang Zeng, Yibo Fan
https://arxiv.org/abs/2510.10648

JND-Guided Light-Weight Neural Pre-Filter for Perceptual Image Coding
Just Noticeable Distortion (JND)-guided pre-filter is a promising technique for improving the perceptual compression efficiency of image coding. However, existing methods are often computationally expensive, and the field lacks standardized benchmarks for fair comparison. To address these challenges, this paper introduces a twofold contribution. First, we develop and open-source FJNDF-Pytorch, a unified benchmark for frequency-domain JND-Guided pre-filters. Second, leveraging this platform, we …

Constraint-Guided Unit Test Generation for Machine Learning Libraries
Lukas Krodinger, Altin Hajdari, Stephan Lukasczyk, Gordon Fraser
https://arxiv.org/abs/2510.09108 https://

Constraint-Guided Unit Test Generation for Machine Learning Libraries
Machine learning (ML) libraries such as PyTorch and TensorFlow are essential for a wide range of modern applications. Ensuring the correctness of ML libraries through testing is crucial. However, ML APIs often impose strict input constraints involving complex data structures such as tensors. Automated test generation tools such as Pynguin are not aware of these constraints and often create non-compliant inputs. This leads to early test failures and limited code coverage. Prior work has investig…

Soumith Chintala, who co-created the PyTorch ML framework at Meta and left the company this month, has joined Mira Murati's Thinking Machines Lab (Pranav Dixit/Business Insider)
https://www.businessinsider.com/meta-soumith-chinta…

A top Meta AI researcher has joined Mira Murati's hot new startup, Thinking Machines Lab
Thinking Machines Lab, led by Mira Murati, hires Meta AI veteran Soumith Chintala as it rapidly expands its team and prepares for major funding.

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2
Savini Kashmira, Jayanaka Dantanarayana, Thamirawaran Sathiyalogeswaran, Yichao Yuan, Nishil Talati, Krisztian Flautner, Lingjia Tang, Jason Mars
https://arxiv.org/abs/2509.16248

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2
This paper presents GraphMend, a high-level compiler that eliminates FX graph breaks in PyTorch 2 programs. Although PyTorch 2 introduced TorchDynamo and TorchInductor to enable just-in-time graph compilation, unresolved dynamic control flow and unsupported Python constructs often fragment models into multiple FX graphs. These fragments force frequent fallbacks to eager mode, incur costly CPU-to-GPU synchronizations, and reduce optimization opportunities. GraphMend addresses this limitation by …

Comparative Analysis of YOLOv5, Faster R-CNN, SSD, and RetinaNet for Motorbike Detection in Kigali Autonomous Driving Context
Ngeyen Yinkfu, Sunday Nwovu, Jonathan Kayizzi, Angelique Uwamahoro
https://arxiv.org/abs/2510.04912

Comparative Analysis of YOLOv5, Faster R-CNN, SSD, and RetinaNet for Motorbike Detection in Kigali Autonomous Driving Context
In Kigali, Rwanda, motorcycle taxis are a primary mode of transportation, often navigating unpredictably and disregarding traffic rules, posing significant challenges for autonomous driving systems. This study compares four object detection models--YOLOv5, Faster R-CNN, SSD, and RetinaNet--for motorbike detection using a custom dataset of 198 images collected in Kigali. Implemented in PyTorch with transfer learning, the models were evaluated for accuracy, localization, and inference speed to as…

humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems
Andrii Kliachkin, Jana Lep\v{s}ov\'a, Gilles Bareilles, Jakub Mare\v{c}ek
https://arxiv.org/abs/2509.21254

humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems
There has been a considerable interest in constrained training of deep neural networks (DNNs) recently for applications such as fairness and safety. Several toolkits have been proposed for this task, yet there is still no industry standard. We present humancompatible.train (https://github.com/humancompatible/train), an easily-extendable PyTorch-based Python package for training DNNs with stochastic constraints. We implement multiple previously unimplemented algorithms for stochastically constra…

CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution
Milan Straka
https://arxiv.org/abs/2509.17858 https://arxiv.…

CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution
We present CorPipe 25, the winning entry to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. This fourth iteration of the shared task introduces a new LLM track alongside the original unconstrained track, features reduced development and test sets to lower computational requirements, and includes additional datasets. CorPipe 25 represents a complete reimplementation of our previous systems, migrating from TensorFlow to PyTorch. Our system significantly outperforms all other sub…

RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models
Hua Zong, Qingtao Zeng, Zhengxiong Zhou, Zhihua Han, Zhensong Yan, Mingjie Liu, Hechen Sun, Jiawei Liu, Yiwen Hu, Qi Wang, YiHan Xian, Wenjie Guo, Houyuan Xiang, Zhiyuan Zeng, Xiangrong Sheng, Bencheng Yan, Nan Hu, Yuheng Huang, Jinqing Lian, Ziru Xu, Yan Zhang, Ju Huang, Siran Yang, Huimin Yi, Jiamang Wang, Pengjie Wang, Han Zhu, Jian Wu, Dan Ou, Jian Xu, Haihong Tang, Yuning Jiang, Bo Zheng, Lin Qu

RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models
In this paper, we propose RecIS, a unified Sparse-Dense training framework designed to achieve two primary goals: 1. Unified Framework To create a Unified sparse-dense training framework based on the PyTorch ecosystem that meets the training needs of industrial-grade recommendation models that integrated with large models. 2.System Optimization To optimize the sparse component, offering superior efficiency over the TensorFlow-based recommendation models. The dense component, meanwhile, leverage…

MinatoLoader: Accelerating Machine Learning Training Through Efficient Data Preprocessing
Rahma Nouaji, Stella Bitchebe, Ricardo Macedo, Oana Balmau
https://arxiv.org/abs/2509.10712

MinatoLoader: Accelerating Machine Learning Training Through Efficient Data Preprocessing
Data loaders are used by Machine Learning (ML) frameworks like PyTorch and TensorFlow to apply transformations to data before feeding it into the accelerator. This operation is called data preprocessing. Data preprocessing plays an important role in the ML training workflow because if it is inefficiently pipelined with the training, it can yield high GPU idleness, resulting in important training delays. Unfortunately, existing data loaders turn out to waste GPU resources, with $76\%$ GPU idlene…

The Syntax and Semantics of einsum
Maurice Wenig, Paul G. Rump, Mark Blacher, Joachim Giesen
https://arxiv.org/abs/2509.20020 https://arxiv.org/pdf/2509.20…

The Syntax and Semantics of einsum
In 2011, einsum was introduced to NumPy as a practical and convenient notation for tensor expressions in machine learning, quantum circuit simulation, and other fields. It has since been implemented in additional Python frameworks such as PyTorch and TensorFlow, as well as in other programming languages such as Julia. Despite its practical success, the einsum notation still lacks a solid theoretical basis, and is not unified across the different frameworks, limiting opportunities for formal rea…

Exploring the Relationship between Brain Hemisphere States and Frequency Bands through Deep Learning Optimization Techniques
Robiul Islam, Dmitry I. Ignatov, Karl Kaberg, Roman Nabatchikov
https://arxiv.org/abs/2509.14078

Exploring the Relationship between Brain Hemisphere States and Frequency Bands through Deep Learning Optimization Techniques
This study investigates classifier performance across EEG frequency bands using various optimizers and evaluates efficient class prediction for the left and right hemispheres. Three neural network architectures - a deep dense network, a shallow three-layer network, and a convolutional neural network (CNN) - are implemented and compared using the TensorFlow and PyTorch frameworks. Results indicate that the Adagrad and RMSprop optimizers consistently perform well across different frequency bands,…

Evaluating the Effectiveness of Coverage-Guided Fuzzing for Testing Deep Learning Library APIs
Feiran Qin, M. M. Abid Naziri, Hengyu Ai, Saikat Dutta, Marcelo d'Amorim
https://arxiv.org/abs/2509.14626

Evaluating the Effectiveness of Coverage-Guided Fuzzing for Testing Deep Learning Library APIs
Deep Learning (DL) libraries such as PyTorch provide the core components to build major AI-enabled applications. Finding bugs in these libraries is important and challenging. Prior approaches have tackled this by performing either API-level fuzzing or model-level fuzzing, but they do not use coverage guidance, which limits their effectiveness and efficiency. This raises an intriguing question: can coverage guided fuzzing (CGF), in particular frameworks like LibFuzzer, be effectively applied to …