"training acceleration" Papers
13 papers found
Conference
Accelerating Training with Neuron Interaction and Nowcasting Networks
Boris Knyazev, Abhinav Moudgil, Guillaume Lajoie et al.
ICLR 2025arXiv:2409.04434
5
citations
Adaptive Non-Uniform Timestep Sampling for Accelerating Diffusion Model Training
Myunsoo Kim, Donghyeon Ki, Seong-Woong Shim et al.
CVPR 2025arXiv:2411.09998
5
citations
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
Zhihang Lin, Mingbao Lin, Yuan Xie et al.
NEURIPS 2025arXiv:2503.22342
56
citations
EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
Weixiang Zhang, Shuzhao Xie, Chengwei Ren et al.
CVPR 2025arXiv:2412.10153
6
citations
FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
Kanghyun Choi, Hyeyoon Lee, Sunjong Park et al.
NEURIPS 2025arXiv:2510.24061
MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
Da Chang, Ganzhao Yuan
NEURIPS 2025spotlight
REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
Ziqiao Wang, Wangbo Zhao, Yuhao Zhou et al.
NEURIPS 2025
8
citations
Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping
Weili Zeng, Ziyuan Huang, Kaixiang Ji et al.
ICCV 2025arXiv:2503.21817
6
citations
Diversified Batch Selection for Training Acceleration
Feng Hong, Yueming LYU, Jiangchao Yao et al.
ICML 2024arXiv:2406.04872
11
citations
Efficient Training with Denoised Neural Weights
Yifan Gong, Zheng Zhan, Yanyu Li et al.
ECCV 2024arXiv:2407.11966
5
citations
How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective
Keyan Miao, Konstantinos Gatsis
ICML 2024oral
Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration
Zhengyang Zhuge, Peisong Wang, Xingting Yao et al.
ICML 2024
When to Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks
Haihang Wu, Wei Wang, Tamasha Malepathirana et al.
AAAI 2024paperarXiv:2401.03104
2
citations