Suchergebnisse - "ML: Learning on the Edge & Model Compression"

Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training

Autoren: Cheng, Xi Gao, Chang Wang, Zuowen et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence, 38 (10) ; AAAI-24 Technical Tracks 10

Schlagwörter: ML: Learning on the Edge & Model Compression

Relation: info:eu-repo/semantics/altIdentifier/isbn/978-1-57735-887-9; info:eu-repo/semantics/altIdentifier/wos/001241513600073; http://hdl.handle.net/20.500.11850/668713

Verfügbarkeit: https://hdl.handle.net/20.500.11850/668713

ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference

Autoren: Zeng, Ziqian Hong, Yihuai Dai, Hongliang et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 17: AAAI-24 Technical Tracks 17; 19506-19514 ; 2374-3468 ; 2159-5399

Schlagwörter: NLP: (Large) Language Models, ML: Learning on the Edge & Model Compression

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29922/31612; https://ojs.aaai.org/index.php/AAAI/article/view/29922

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29922
https://doi.org/10.1609/aaai.v38i17.29922

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

Autoren: Zhang, Rongyu Luo, Yulin Liu, Jiaming et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 15: AAAI-24 Technical Tracks 15; 16812-16820 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, CV: Applications, CV: Low Level & Physics-based Vision, CV: Representation Learning for Vision

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29622/31055; https://ojs.aaai.org/index.php/AAAI/article/view/29622/31056; https://ojs.aaai.org/index.php/AAAI/article/view/29622

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29622
https://doi.org/10.1609/aaai.v38i15.29622

PTMQ: Post-training Multi-Bit Quantization of Neural Networks

Autoren: Xu, Ke Li, Zhongcheng Wang, Shanshan et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 14: AAAI-24 Technical Tracks 14; 16193-16201 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, CV: Learning & Optimization for CV

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29553/30925; https://ojs.aaai.org/index.php/AAAI/article/view/29553/30926; https://ojs.aaai.org/index.php/AAAI/article/view/29553

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29553
https://doi.org/10.1609/aaai.v38i14.29553

BVT-IMA: Binary Vision Transformer with Information-Modified Attention

Autoren: Wang, Zhenyu Luo, Hao Xie, Xuemei et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 14: AAAI-24 Technical Tracks 14; 15761-15769 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, ML: Classification and Regression, ML: Deep Neural Architectures and Foundation Models

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29505/30837; https://ojs.aaai.org/index.php/AAAI/article/view/29505/30838; https://ojs.aaai.org/index.php/AAAI/article/view/29505

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29505
https://doi.org/10.1609/aaai.v38i14.29505

AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries

Autoren: Wang, Runqi Sun, Huixin Yang, Linlin et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 14: AAAI-24 Technical Tracks 14; 15598-15606 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, CV: Object Detection & Categorization

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29487/30803; https://ojs.aaai.org/index.php/AAAI/article/view/29487/30804; https://ojs.aaai.org/index.php/AAAI/article/view/29487

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29487
https://doi.org/10.1609/aaai.v38i14.29487

Generative Model-Based Feature Knowledge Distillation for Action Recognition

Autoren: Wang, Guiqin Zhao, Peng Shi, Yanjiang et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 14: AAAI-24 Technical Tracks 14; 15474-15482 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, CV: Applications, CV: Other Foundations of Computer Vision, CV: Video Understanding & Activity Analysis, KRR: Applications, ML: Applications

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29473/30776; https://ojs.aaai.org/index.php/AAAI/article/view/29473/30777; https://ojs.aaai.org/index.php/AAAI/article/view/29473

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29473
https://doi.org/10.1609/aaai.v38i14.29473

DSD²: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?

Autoren: Quétu, Victor Tartaglione, Enzo

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 13: AAAI-24 Technical Tracks 13; 14749-14757 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Deep Learning Algorithms, ML: Learning on the Edge & Model Compression

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29393/30631; https://ojs.aaai.org/index.php/AAAI/article/view/29393/30632; https://ojs.aaai.org/index.php/AAAI/article/view/29393

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29393
https://doi.org/10.1609/aaai.v38i13.29393

REPrune: Channel Pruning via Kernel Representative Selection

Autoren: Park, Mincheol Kim, Dongjin Park, Cheonjun et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 13: AAAI-24 Technical Tracks 13; 14545-14553 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, ML: Auto ML and Hyperparameter Tuning

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29370/30586; https://ojs.aaai.org/index.php/AAAI/article/view/29370/30587; https://ojs.aaai.org/index.php/AAAI/article/view/29370

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29370
https://doi.org/10.1609/aaai.v38i13.29370

Simple Weak Coresets for Non-decomposable Classification Measures

Autoren: Malaviya, Jayesh Dasgupta, Anirban Chhaya, Rachit

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 13: AAAI-24 Technical Tracks 13; 14289-14296 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Evaluation and Analysis, ML: Classification and Regression, ML: Dimensionality Reduction/Feature Selection, ML: Scalability of ML Systems, ML: Learning Theory, ML: Optimization, ML: Learning on the Edge & Model Compression, SO: Sampling/Simulation-based Search

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29341/30531; https://ojs.aaai.org/index.php/AAAI/article/view/29341/30532; https://ojs.aaai.org/index.php/AAAI/article/view/29341

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29341
https://doi.org/10.1609/aaai.v38i13.29341

OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models

Autoren: Lee, Changhun Jin, Jungyu Kim, Taesu et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 12: AAAI-24 Technical Tracks 12; 13355-13364 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, NLP: (Large) Language Models, NLP: Learning & Optimization for NLP

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29237/30335; https://ojs.aaai.org/index.php/AAAI/article/view/29237/30336; https://ojs.aaai.org/index.php/AAAI/article/view/29237

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29237
https://doi.org/10.1609/aaai.v38i12.29237

FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing

Autoren: Jia, Yongzhe Zhang, Xuyun Beheshti, Amin et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 11: AAAI-24 Technical Tracks 11; 12848-12856 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, APP: Internet of Things, Sensor Networks & Smart Cities, ML: Transfer, Domain Adaptation, Multi-Task Learning, ML: Representation Learning

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29181/30234; https://ojs.aaai.org/index.php/AAAI/article/view/29181/30235; https://ojs.aaai.org/index.php/AAAI/article/view/29181

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29181
https://doi.org/10.1609/aaai.v38i11.29181

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes

Autoren: Gong, Ruihao Yong, Yang Wang, Zining et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 11: AAAI-24 Technical Tracks 11; 12190-12198 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, CV: Applications

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29108/30095; https://ojs.aaai.org/index.php/AAAI/article/view/29108/30096; https://ojs.aaai.org/index.php/AAAI/article/view/29108

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29108
https://doi.org/10.1609/aaai.v38i11.29108

Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold

Autoren: Ganjdanesh, Alireza Gao, Shangqian Alipanah, Hirad et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 11: AAAI-24 Technical Tracks 11; 12118-12126 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, ML: Deep Generative Models & Autoencoders, ML: Deep Neural Architectures and Foundation Models

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29100/30079; https://ojs.aaai.org/index.php/AAAI/article/view/29100/30080; https://ojs.aaai.org/index.php/AAAI/article/view/29100

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29100
https://doi.org/10.1609/aaai.v38i11.29100

Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

Autoren: Fan, Yunqian Wei, Xiuying Gong, Ruihao et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 11: AAAI-24 Technical Tracks 11; 11936-11943 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, CV: Applications

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29080/30043; https://ojs.aaai.org/index.php/AAAI/article/view/29080/30044; https://ojs.aaai.org/index.php/AAAI/article/view/29080

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29080
https://doi.org/10.1609/aaai.v38i11.29080

Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training

Autoren: Chen, Xi Gao, Chang Wang, Zuowen et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 10: AAAI-24 Technical Tracks 10; 11399-11406 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29020/29935; https://ojs.aaai.org/index.php/AAAI/article/view/29020/29936; https://ojs.aaai.org/index.php/AAAI/article/view/29020

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29020
https://doi.org/10.1609/aaai.v38i10.29020

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression

Autoren: Chen, Dong Liu, Ning Zhu, Yichen et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 10: AAAI-24 Technical Tracks 10; 11258-11266 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, CV: Applications, CV: Learning & Optimization for CV, ML: Classification and Regression, ML: Deep Learning Algorithms, ML: Multi-class/Multi-label Learning & Extreme Classification, ML: Optimization

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/29004/29906; https://ojs.aaai.org/index.php/AAAI/article/view/29004

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/29004
https://doi.org/10.1609/aaai.v38i10.29004

Multi-Criterion Client Selection for Efficient Federated Learning

Autoren: Tahir, Mehreen Ali, Muhammad Intizar

Quelle: Proceedings of the AAAI Symposium Series; Vol. 3 No. 1: Proceedings of the 2024 AAAI Spring Symposium Series; 318-322 ; 2994-4317

Schlagwörter: ML: Distributed Machine Learning & Federated Learning, ML: Optimization, ML: Learning On The Edge & Model Compression, ML: Evaluation And Analysis (Machine Learning)

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI-SS/article/view/31227/33387

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI-SS/article/view/31227
https://doi.org/10.1609/aaaiss.v3i1.31227

Robustness-Guided Image Synthesis for Data-Free Quantization

Autoren: Bai, Jianhong Yang, Yuchen Chu, Huanpeng et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 10: AAAI-24 Technical Tracks 10; 10971-10979 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, ML: Classification and Regression, ML: Deep Learning Algorithms

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/28972/29848; https://ojs.aaai.org/index.php/AAAI/article/view/28972/29849; https://ojs.aaai.org/index.php/AAAI/article/view/28972

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/28972
https://doi.org/10.1609/aaai.v38i10.28972

Fluctuation-Based Adaptive Structured Pruning for Large Language Models

Autoren: An, Yongqi Zhao, Xu Yu, Tao et al.

Quelle: Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38 No. 10: AAAI-24 Technical Tracks 10; 10865-10873 ; 2374-3468 ; 2159-5399

Schlagwörter: ML: Learning on the Edge & Model Compression, NLP: (Large) Language Models

Dateibeschreibung: application/pdf

Relation: https://ojs.aaai.org/index.php/AAAI/article/view/28960/29826; https://ojs.aaai.org/index.php/AAAI/article/view/28960/29827; https://ojs.aaai.org/index.php/AAAI/article/view/28960

Verfügbarkeit: https://ojs.aaai.org/index.php/AAAI/article/view/28960
https://doi.org/10.1609/aaai.v38i10.28960