{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T05:10:19Z","timestamp":1756357819010,"version":"3.44.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,6]]},"DOI":"10.1109\/isvlsi65124.2025.11130214","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T18:20:15Z","timestamp":1756318815000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Hardware-Accelerated On-Device Learning: Training, Partitioning, and Compilation for Constrained Edge AI"],"prefix":"10.1109","author":[{"given":"Iuliia","family":"Topko","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"Alexey","family":"Serdyuk","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"Tanja","family":"Harbaum","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]},{"given":"J\u00fcrgen","family":"Becker","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Karlsruhe,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.actaastro.2024.04.012","article-title":"Review of machine learning in robotic grasping control in space application","volume":"220","author":"Jahanshahi","year":"2024","journal-title":"Acta Astronautica"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00859-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-70073-7"},{"journal-title":"GitHub repository","article-title":"commavq: a dataset of tokenized driving video and a GPT model","year":"2023","key":"ref4"},{"key":"ref5","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024","journal-title":"arXiv preprint arXiv:2410.23262"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"article-title":"Sharpening the Edge II: Diving Deeper into the LF Edge Taxonomy and Projects","volume-title":"Tech. Rep","year":"2022","key":"ref8"},{"key":"ref9","article-title":"ParameterEfficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","author":"Xu","year":"2023","journal-title":"arXiv:2312.12148 [cs]"},{"key":"ref10","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685 [cs]"},{"key":"ref11","article-title":"Qlora: Efficient finetuning of quantized llms","author":"Dettmers","year":"2023","journal-title":"arXiv preprint arXiv:2305.14314"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.eacl-main.239","article-title":"Dylora: Parameter efficient tuning of pre-trained models using dynamic search-free low-rank adaptation","author":"Valipour","year":"2023"},{"article-title":"Bayesian low-rank adaptation for large language models","year":"2024","author":"Yang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2187"},{"key":"ref15","article-title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","author":"Liu","year":"2021","journal-title":"arXiv:2102.01386 [cs]"},{"author":"Raghu","key":"ref16","article-title":"SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability"},{"key":"ref17","article-title":"torch.compiler-PyTorch 2.7 documentation"},{"key":"ref18","article-title":"TorchScript-PyTorch 2.7 documentation"},{"key":"ref19","article-title":"Operator Fusion in XLA: Analysis and Evaluation","author":"Snider","year":"2023","journal-title":"arXiv:2301.13062 [cs]"},{"key":"ref20","article-title":"On-Device Training with ONNX Runtime"},{"key":"ref21","article-title":"On-Device Training with LiteR"},{"key":"ref22","article-title":"ExecuTorch On-device Training"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/MM.2022.3178068","article-title":"Tinyiree: An ml execution environment for embedded systems from compilation to deployment","author":"Liu","year":"2022"},{"issue":"3","key":"ref24","doi-asserted-by":"crossref","first-page":"729","DOI":"10.3390\/ai4030039","article-title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","volume":"4","author":"Li","year":"2023","journal-title":"AI"},{"issue":"1","key":"ref25","first-page":"127","article-title":"Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks","volume-title":"Name: IEEE Journal of Solid-State Circuits","volume":"52","author":"Chen"},{"key":"ref26","article-title":"Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices","author":"Chen","year":"2019","journal-title":"arXiv:1807.07928 [cs]"},{"key":"ref27","article-title":"A Survey of Quantization Methods for Efficient Neural Network Inference","author":"Gholami","year":"2021","journal-title":"arXiv:2103.13630 [cs]"},{"key":"ref28","first-page":"142","article-title":"7.7 LNPU: A 25.3TFLOPS\/W Sparse Deep-Neural-Network Learning Processor with Fine-Grained Mixed Precision of FP8-FP16","volume-title":"2019 IEEE International Solid-State Circuits Conference-(ISSCC)","author":"Lee"},{"issue":"5","key":"ref29","doi-asserted-by":"crossref","first-page":"1630","DOI":"10.1109\/JSSC.2020.3042978","article-title":"DF-LNPU: A Pipelined Direct Feedback Alignment-Based Deep Neural Network Learning Processor for Fast Online Learning","volume":"56","author":"Han","year":"2021","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"ref30","article-title":"Direct Feedback Alignment Provides Learning in Deep Neural Networks","author":"N\u00f8kland","year":"2016","journal-title":"arXiv:1609.01596 [stat]"},{"key":"ref31","article-title":"Efficient Convolutional Neural Network Training with Direct Feedback Alignment","author":"Han","year":"2019","journal-title":"arXiv:1901.01986 [cs]"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"109759","DOI":"10.1016\/j.comnet.2023.109759","article-title":"CNNParted: An open source framework for efficient convolutional neural network inference partitioning in embedded systems","volume":"229","author":"Kre\u00df","year":"2023","journal-title":"Computer Networks"},{"volume-title":"Introduction to algorithms","year":"2022","author":"Cormen","key":"ref33"},{"key":"ref34","article-title":"Exploring network structure, dynamics, and function using networkx","volume":"1","author":"Hagberg","year":"2008"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1109\/ISVLSI61997.2024.00019","article-title":"Automated deep neural network inference partitioning for distributed embedded systems","author":"Kre\u00df","year":"2024"},{"issue":"3","key":"ref36","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/S0375-9601(97)00474-X","article-title":"Generalized simulated annealing algorithm and its application to the Thomson model","volume":"233","author":"Xiang","year":"1997","journal-title":"Physics Letters A"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00065"},{"key":"ref40","article-title":"Composable and Modular Code Generation in MLIR: A Structured and Retargetable Approach to Tensor Compiler Construction","author":"Vasilache","year":"2022","journal-title":"arXiv:2202.03293 [cs]"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2015","author":"Simonyan","key":"ref41"},{"key":"ref42","first-page":"2009","article-title":"Learning multiple layers of features from tiny images","volume-title":"Tech. Rep","author":"Krizhevsky"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00010"}],"event":{"name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","start":{"date-parts":[[2025,7,6]]},"location":"Kalamata, Greece","end":{"date-parts":[[2025,7,9]]}},"container-title":["2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11129697\/11130193\/11130214.pdf?arnumber=11130214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:31:11Z","timestamp":1756355471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/isvlsi65124.2025.11130214","relation":{},"subject":[],"published":{"date-parts":[[2025,7,6]]}}}