Pytorch

Ask about this topic

Momentum

9 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 64

All topics
CardsList

  1. KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

    Sep 24, 2026Aheli Poddar, Sanskar Prasad, Arindam Samanta +3Graphics Processing Unit KernelsPytorch

    Red Hat

  2. hyperbolix: Hyperbolic Deep Learning in JAX

    Sep 23, 2026Timo Klein, Thomas Lang, Yllka Velaj +1Hyperbolic LearningHyperbolic Space

    Faculty of Computer Science, University of Vienna, Vienna, Austria · UniVie Doctoral School Computer Science, University of Vienna, Vienna, Austria · ds:UniVie, University of Vienna, Vienna, Austria

  3. TNLearn: An Open Source Python Package for Task-based Neurons

    Sep 23, 2026Meng Wang, Tieyun Li, Juntong Fan +5NeuronsPytorch

    Shenzhen H&T Intelligent Control Co., Ltd., Shenzhen, China · School of Mathematics, Harbin Institute of Technology, Harbin, China · Department of Data Science, The City University of Hong Kong, Kowloon, Hong Kong +1

  4. Silent Failures Beyond the 32-Bit Index Range: A Differential Characterization of Large-Tensor Matrix Multiplication in PyTorch's MPS Backend

    Sep 19, 2026Junichiro NiimiMatrix MultiplicationPytorch

    Meijo University

  5. vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes

    Sep 16, 2026Congyue DengPytorchSpatio-Temporal Attention

    Massachusetts Institute of Technology

  6. woma: a real-time foundation model and its fine-tuned models for endoscopy

    Sep 14, 2026Thang Tran, Lan DangColonoscopyWireless Foundation Models

    CloudKites AI Lab · Monash Business School, Monash University

  7. AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization

    Sep 14, 2026Ji Liu, Saptarshi Majumder, Yiqing Huang +14CudaPytorch

    Advanced Micro Devices, Inc.

  8. When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variants

    Sep 12, 2026Rafiqul IslamVision-Language-Action FrameworkInference Latency

    Independent Researcher

  9. SeisBench DAS: A machine learning framework for Distributed Acoustic Sensing

    Sep 7, 2026Jannes Münchmeyer, Han Xiao, Frederik TilmannFull Waveform InversionForward-Looking Sonar

    GFZ Helmholtz Centre for Geosciences · Institute for Geological Sciences, Freie Universität Berlin, Berlin, Germany

  10. PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation

    Sep 1, 2026Lukas Zimmermann, Hermann Fuchs, Attila Simkó +1RadiotherapyDose

    Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria · Christian Doppler Laboratory for Image and Knowledge Driven Precision Radiation Oncology, Medical University of Vienna, Vienna, Austria · Department of Diagnostics and Intervention, Umeå University, Umeå, Sweden

  11. RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

    Aug 12, 2026Jinjun Huang, Zhongzhen Wen, Tongtong Xu +3CudaLarge Language Model Benchmarks

    College of Computer Science and Technology and the State Key Laboratory of Blockchain and Data Security, Zhejiang University · State Key Lab for Novel Software Technology, Nanjing University · Software Engineering Application Technology Laboratory, Huawei +1

  12. AlbumentationsX: One Augmentation Pipeline for Images and Related Annotations

    Aug 11, 2026Vladimir IglovikovData AugmentationAugmentation

    Albumentations LLC

  13. Memory-Efficient Activation Checkpointing with Sliding Window and Hirschberg's Algorithm for 0/1 Knapsack Solving in PyTorch

    Aug 9, 2026Jędrzej MaczanKnapsack ConstraintPytorch

    Cohere Labs Community Poland

  14. Tensor Network Kernel Machines: A JAX Framework for Machine Learning and Nonlinear System Identification

    Aug 7, 2026Albert Saiapin, Kim BatselierTensor NetworksNeural Tangent Kernel

    Delft Center for Systems and Control, TU Delft, Netherlands

  15. Contrast-invariant deep ptychography neural networks

    Aug 3, 2026Albert Vong, Steven Henke, Oliver Hoidn +6Neural ReconstructionParametric Physics-Informed Neural Network

    Argonne National Laboratory, Lemont, Illinois 60439, USA · SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA · Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, California 94720, USA

  16. Meganeura: Portable GPU Training and Inference through Vulkan and Metal

    Aug 3, 2026Dzmitry MalyshauPytorchInference Workloads

    Independent Researcher

  17. Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget

    Aug 2, 2026Zhichao Xu, Xueguang Ma, Shengyao Zhuang +5Large Language Model RerankingCross-Encoder Reranking

    University of Utah · University of Waterloo · The University of Queensland +2

  18. TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning

    Jul 30, 2026Brendan Kennedy, Tegan Emerson, Gregory Roek +2PytorchTopology

    Pacific Northwest National Laboratory · Pacific Northwest National Laboratory, University of Texas at El Paso · University of Texas at El Paso +1

  19. It's All Just Vectorization: einx, a Universal Notation for Tensor Operations

    Jul 30, 2026Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner +1VectorizationTensor Networks

    Fraunhofer IOSB

  20. Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

    Jul 22, 2026Jian Hu, Huiying Li, Hao Zhang +8Agentic Reinforcement LearningMixture-Of-Agents

    NVIDIA

  21. How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF

    Jul 22, 2026Venkata Naga Sai Vishnu Rohit Pulipaka, Anish Katta, Deva Rohit Reddy PeddireddyDestination-Only ScoringFast Inference

  22. Benchmarking NACTI Species Recognition in Long-Tailed Regimes

    Jul 20, 2026Zehua Liu, Tilo BurghardtSpecies IdentificationRoadside Cameras

    School of Computer Science, University of Bristol, MVB Woodland Rd, BS8 1UB, Bristol, UK

  23. FlashPDE: A Drop-In Fused Triton Operator Library for Neural PDE Solvers

    Jul 20, 2026Peiyu Zang, Bosen Xie, Ruoxiang Xu +1Neural Partial Differential Equation SolversPytorch

    School of Mathematical Sciences, Beijing Normal University · 2Beijing University of Posts and Telecommunications

  24. OpenLanguageModel: Readable and Composable Small-Language-Model Pretraining for Education and Research

    Jul 18, 2026Tavish Mankash, Vardhaman Kalloli, Keshava Prasad +1Pytorch

    FAIRC · Plaksha University

  25. Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent

    Jul 16, 2026Lingyun Yang, Yuxiao Wang, Shenghao Liang +8Graphics Processing Unit KernelsAgentic Optimization

    ATREX Team†, Alibaba Group

  26. Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification

    Jun 21, 2026Mickael Rouvier, Pierre Michel BousquetAutomatic Speaker VerificationSpeaker

    1Avignon University, LIA, UPR 4128, France

  27. KANLib -- A Modular, Extensible and Fast Kolmogorov-Arnold Network Implementation

    Jun 16, 2026Julian Hoever, Gregor SchieleKolmogorov-Arnold NetworksMultilayer Perceptrons

    Intelligent Embedded Systems University of Duisburg-Essen Duisburg, Germany

  28. Agentic Framework for Deep Learning workload migration via In-Context Learning

    Jun 14, 2026Qiyue Liang, Steven Ingram, George Vanica +4PytorchAgentic Framework

    Google, Sunnyvale, CA · 2Google, Kirkland, WA · 1Google, Sunnyvale, CA +2

  29. Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks

    Jun 13, 2026Abdeladhim TahimiParametric Physics-Informed Neural NetworkImplicit Differentiation

    CECA, Universidade Federal de Alagoas (UFAL), Rio Largo, Alagoas, 57100-000, Brazil

  30. ANEForge: Python for direct computation on the Apple Neural Engine

    Jun 12, 2026Spencer H. BryngelsonPytorchPython

    School of Computational Science & Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA · Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA · George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA

  31. A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting

    Jun 9, 2026Matthew Cong, Francis Williams, Jonathan Swartz +3Cpu-Gpu Hybrid DesignsNeural Reconstruction

    1NVIDIA · University of Toronto · 3Vector Institute

  32. Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search

    Jun 8, 2026Haolin Pan, Lianghong Huang, Xvlin Zhou +2PytorchLatent Dynamics

    Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China · Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China

  33. AgentCompile: An LLM-Guided Compiler for Direct CUDA Inference

    Jun 4, 2026Xuanzhe Li, Ziyan Weng, Zhiyu Zhu +1CudaPytorch

    City University of Hong Kong (Dongguan) · City University of Hong Kong

  34. nnAudio 2: Overcoming Dynamic Compilation Barriers and Transform Inconsistencies

    Jun 3, 2026Abhinaba Roy, Junyi Liang, Dorien HerremansNeural Audio CodecsPytorch

    Singapore University of Technology and Design

  35. Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning

    May 29, 2026Yue Wang, Yanran Xu, Wenbo Wu +2Rigid-Body DynamicsPytorch

    University of Southampton, Southampton, SO17 1BJ, UK

  36. Fuzzy PyTorch: Rapid Numerical Variability Evaluation for Deep Learning Models

    May 25, 2026Inés Gonzalez-Pepe, Hiba Akhaddar, Tristan Glatard +1PytorchDeep Learning

    Department of Computer Science and Software Engineering Concordia University Montreal, Canada · Krembil Centre for Neuroinformatics Centre for Addiction and Mental Health Toronto, Canada

  37. The Neural Compiler: Program-to-Network Translation for Hybrid Scientific Machine Learning

    May 21, 2026Lucas ShenemanPytorchNeural Network

    Institute for Interdisciplinary Data Sciences University of Idaho

  38. Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)

    May 21, 2026Hisashi MiyashitaSingular Value DecompositionSubspace

    Mgnite Inc.

  39. torchtune: PyTorch native post-training library

    May 20, 2026Mark Obozov, Maxime Griot, Joseph Cummings +8PytorchModel Fine-Tuning

    Work done at PyTorch, Meta · Stanford · Meta-FAIR

  40. Sutra: Tensor-Op RNNs as a Compilation Target for Vector Symbolic Architectures

    May 20, 2026Emma LeonhartPytorchTensor Networks

  41. An End-to-End PyTorch Interface for Differentiable PDE Solvers: A RANS Model-Correction Study

    May 19, 2026Luca Saverio, Michele Alessandro Bucci, Gianmarco Farro +2Neural Partial Differential Equation SolversPartial Differential Equations

    MONHADE · Digital Sciences & Technologies Department, Safran Tech, Magny-Les-Hameaux, 78114, France. · DAAA, ONERA, Institut Polytechnique de Paris, Meudon, 92190, France. +1

  42. Lightweight Gaussian Process Inference in C++ on Metal and CUDA

    May 18, 2026Yu-Hsueh FangGaussian ProcessCpu-Gpu Hybrid Designs

    Department of Information Management, National Taiwan University · 2H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology

  43. Venom: A PyTorch Generative Modeling Toolkit

    May 17, 2026Liang YanGenerative ModelsPytorch

    Paul G. Allen School of Computer Science & Engineering University of Washington

  44. MiniGPT: Rebuilding GPT from First Principles

    May 17, 2026Jibin JosephAutoregressive Language ModelsGenerative Pretrained Transformers

    Department of Computer Science The University of Texas at Austin Austin, TX 78712

  45. AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents

    May 16, 2026Sharareh Younesian, Wenwen Ouyang, Sina Rafati +11Graphics Processing Unit KernelsAgentic Optimization

    AMD

  46. DeepLog: A Software Framework for Modular Neurosymbolic AI

    May 11, 2026Robin Manhaeve, Stefano Colamonaco, Vincent Derkinderen +4Neuro-Symbolic FrameworkDeep Learning Framework

    Department of Computer Science and Leuven.AI KU Leuven, Belgium

  47. jNO: A JAX Library for Neural Operator and Foundation Model Training

    May 11, 2026Leon Armbruster, Rathan Ramesh, Georg Kruse +1Neural OperatorsJacobian

    Fraunhofer Institute for Integrated Systems and Device Technology IISB, Germany

  48. Single-Thread JPEG Decoder Benchmarks Mis-Evaluate ML Data Loaders

    May 9, 2026Vladimir Iglovikov, Dmitry KosarevskyPytorchImagenet

    Ternaus · Independent Researcher

  49. Structured Recurrent Mixers for Massively Parallelized Sequence Generation

    May 9, 2026Benjamin L. BadgerAsymmetric Grouped-Attention Variate MixerRecurrent Model

    IBM

  50. ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device

    May 5, 2026Mergen Nachin, Digant Desai, Sicheng Stephen Jia +36PytorchEdge Devices

    Meta · Work done while at Meta.

  51. Tile-Level Activation Overlap for Efficient LLM Inference

    May 5, 2026Abhinav Jangda, Tyler Sorensen, Sebastian Burckhardt +3PytorchMultilayer Perceptrons

    Microsoft Research · Microsoft

  52. Differentiable Kernel Ridge Regression for Deep Learning Pipelines

    May 4, 2026Jean-Marc Mercier, Gabriele SantinKernel Ridge RegressionKernel Method

    1MPG-Partners, Paris, France · Department of Environmental Sciences, Informatics and Statistics, Ca’ Foscari University of Venice, Italy

  53. A PyTorch Library of Turing-Complete Neural Networks

    May 3, 2026Jonathan BatesPytorchNeural Network

  54. VkSplat: High-Performance 3DGS Training in Vulkan Compute

    Apr 30, 2026Jingxiang Chen, Mohamed Ibrahim, Yang LiuPytorch

    Huawei Canada

  55. HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models

    Apr 24, 2026Abhinaba BasuTransformer AttentionSequence Modeling

    National Institute of Electronics and Information Technology (NIELIT)

  56. mlr3torch: A Deep Learning Framework in R based on mlr3 and torch

    Apr 20, 2026Sebastian Fischer, Lukas Burk, Carson Zhang +2Deep Learning FrameworkPytorch

    LMU Munich · MCML · Leibniz Institute for Prevention Research and Epidemiology - BIPS University of Bremen

  57. Dispatch-Aware Ragged Attention for Pruned Vision Transformers

    Apr 16, 2026Seifeldin Abdellatif, Ahmad AlmasriVisual Token PruningBlock Sparse Flash Attention

    College of Engineering Al Ain University Abu Dhabi, United Arab Emirates

  58. NewsTorch: A PyTorch-based Toolkit for Learner-oriented News Recommendation

    Apr 16, 2026Rongyao Wang, Veronica Liesaputra, Zhiyi HuangHeadlinesPytorch

    School of Computing, University of Otago, Dunedin 9016, New Zealand

  59. KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models

    Mar 2, 2026Songming Zhang, Xue Zhang, Tong Zhang +3Knowledge DistillationDataset Distillation

    School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China · Key Laboratory of Big Data & Artificial Intelligence in Transportation, (Beijing Jiaotong University), Ministry of Education · Weixin AI

  60. DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce

    Feb 9, 2026Wenchen Han, Shay Vargaftik, Michael Mitzenmacher +1Gradient QuantizationPytorch

    University College London · VMware Research by Broadcom · Harvard University +1