Publications | Sheng Li

2026

Preprint

Temporal Aware Pruning for Efficient Diffusion-based Video Generation

Sheng Li, Yang Sui, Junhao Ran, Bo Yuan, Yue Dai, and Xulong Tang

arXiv preprint arXiv:2605.17837, 2026

@article{li2026tape,
  title = {Temporal Aware Pruning for Efficient Diffusion-based Video Generation},
  author = {Li, Sheng and Sui, Yang and Ran, Junhao and Yuan, Bo and Dai, Yue and Tang, Xulong},
  journal = {arXiv preprint arXiv:2605.17837},
  year = {2026}
}

Preprint

Accelerating 3D Gaussian Splatting using Tensor Cores

Sheng Li, Yang Sui, Yue Wu, Zhuoran Song, Bo Yuan, Xulong Tang, and Yue Dai

arXiv preprint arXiv:2605.17855, 2026

Bib HTML

@article{li2026tensorgs,
  title = {Accelerating 3D Gaussian Splatting using Tensor Cores},
  author = {Li, Sheng and Sui, Yang and Wu, Yue and Song, Zhuoran and Yuan, Bo and Tang, Xulong and Dai, Yue},
  journal = {arXiv preprint arXiv:2605.17855},
  year = {2026}
}

GLSVLSI

Rethinking the Potential of Layer Freezing for DNN Training Efficiency

Chence Yang, Ningxi Cheng, Ci Zhang, Lei Lu, Qitao Tan, Sheng Li, Ao Li, Xulong Tang, Shaoyi Huang, Jinzhen Wang, Guoming Li, Jundong Li, Xiaoming Zhai, Jin Lu, Jinhui Wang, and Geng Yuan

In Proceedings of the Great Lakes Symposium on VLSI 2026, 2026

Bib HTML

@inproceedings{yang2026rethinking,
  title = {Rethinking the Potential of Layer Freezing for DNN Training Efficiency},
  author = {Yang, Chence and Cheng, Ningxi and Zhang, Ci and Lu, Lei and Tan, Qitao and Li, Sheng and Li, Ao and Tang, Xulong and Huang, Shaoyi and Wang, Jinzhen and Li, Guoming and Li, Jundong and Zhai, Xiaoming and Lu, Jin and Wang, Jinhui and Yuan, Geng},
  booktitle = {Proceedings of the Great Lakes Symposium on VLSI 2026},
  pages = {772--778},
  year = {2026},
  publisher = {ACM},
  url = {https://dl.acm.org/doi/10.1145/3787109.3816394}
}

CVPR

Content-Aware Dynamic Patchification for Efficient Video Diffusion

Sheng Li, Connelly Barnes, Mamshad Nayeem Rizve, Hongwu Peng, Zhengang Li, Ohi Dibua, Alireza Ganjdanesh, Xulong Tang, Yan Kang, and Yifan Gong

In The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

Webpage Bib

@inproceedings{li2026content,
  title = {Content-Aware Dynamic Patchification for Efficient Video Diffusion},
  author = {Li, Sheng and Barnes, Connelly and Rizve, Mamshad Nayeem and Peng, Hongwu and Li, Zhengang and Dibua, Ohi and Ganjdanesh, Alireza and Tang, Xulong and Kang, Yan and Gong, Yifan},
  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Li_Content-Aware_Dynamic_Patchification_for_Efficient_Video_Diffusion_CVPR_2026_paper.html}
}

2025

ICLR

Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning

Sheng Li^*, Qitao Tan^*, Yue Dai, Zhenglun Kong, Tianyu Wang, Jun Liu, Ao Li, Ninghao Liu, Yufei Ding, Xulong Tang, and Geng Yuan

In The Thirteenth International Conference on Learning Representations, 2025

Webpage Bib

@inproceedings{li2025mutual,
  title = {Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning},
  author = {Li, Sheng and Tan, Qitao and Dai, Yue and Kong, Zhenglun and Wang, Tianyu and Liu, Jun and Li, Ao and Liu, Ninghao and Ding, Yufei and Tang, Xulong and Yuan, Geng},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  year = {2025},
  url = {https://openreview.net/forum?id=GTcEe5fayC}
}

ASP-DAC

A Computation and Energy Efficient Hardware Architecture for SSL Acceleration

Huidong Ji, Sheng Li, Yue Cao, Chen Ding, Jiawei Xu, Qitao Tan, Ao Li, Jun Liu, Xulong Tang, Lirong Zheng, Geng Yuan, and Zhuo Zou

In 30th Asia and South Pacific Design Automation Conference, 2025

Bib HTML

@inproceedings{ji2025acomp,
  title = {A Computation and Energy Efficient Hardware Architecture for SSL Acceleration},
  author = {Ji, Huidong and Li, Sheng and Cao, Yue and Ding, Chen and Xu, Jiawei and Tan, Qitao and Li, Ao and Liu, Jun and Tang, Xulong and Zheng, Lirong and Yuan, Geng and Zou, Zhuo},
  booktitle = {30th Asia and South Pacific Design Automation Conference},
  pages = {23--29},
  year = {2025},
  url = {https://dl.acm.org/doi/10.1145/3658617.3697548}
}

2024

ICLR

Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised Learning

Sheng Li, Chao Wu, Ao Li, Yanzhi Wang, Xulong Tang, and Geng Yuan

In The Twelfth International Conference on Learning Representations, 2024

Bib HTML

@inproceedings{li2024waxingandwaning,
  title = {Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised Learning},
  author = {Li, Sheng and Wu, Chao and Li, Ao and Wang, Yanzhi and Tang, Xulong and Yuan, Geng},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=TilcG5C8bN}
}

Preprint

EdgeOL: Efficient in-situ Online Learning on Edge Devices

Sheng Li, Geng Yuan, Yue Dai, Tianyu Wang, Yawen Wu, Alex K. Jones, Jingtong Hu, Tony (Tong) Geng, Yanzhi Wang, Bo Yuan, Yufei Ding, and Xulong Tang

arXiv preprint arXiv:2401.16694, 2024

Bib HTML

@article{li2024edgeol,
  title = {EdgeOL: Efficient in-situ Online Learning on Edge Devices},
  author = {Li, Sheng and Yuan, Geng and Dai, Yue and Wang, Tianyu and Wu, Yawen and Jones, Alex K. and Hu, Jingtong and Geng, Tony (Tong) and Wang, Yanzhi and Yuan, Bo and Ding, Yufei and Tang, Xulong},
  journal = {arXiv preprint arXiv:2401.16694},
  year = {2024}
}

Preprint

Improving GPU Multi-Tenancy Through Dynamic Multi-Instance GPU Reconfiguration

Tianyu Wang^*, Sheng Li^*, Bingyao Li, Yue Dai, Ao Li, Geng Yuan, Yufei Ding, Youtao Zhang, and Xulong Tang

arXiv preprint arXiv:2407.13126, 2024

Bib HTML

@article{wang2024improving,
  title = {Improving GPU Multi-Tenancy Through Dynamic Multi-Instance GPU Reconfiguration},
  author = {Wang, Tianyu and Li, Sheng and Li, Bingyao and Dai, Yue and Li, Ao and Yuan, Geng and Ding, Yufei and Zhang, Youtao and Tang, Xulong},
  journal = {arXiv preprint arXiv:2407.13126},
  year = {2024}
}

2023

ICLR

SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing

Sheng Li^*, Geng Yuan^*, Yue Dai^*, Youtao Zhang, Yanzhi Wang, and Xulong Tang

In The Eleventh International Conference on Learning Representations, 2023

Spotlight Bib HTML

@inproceedings{li2023smartfrz,
  title = {Smart{FRZ}: An Efficient Training Framework using Attention-Based Layer Freezing},
  author = {Li, Sheng and Yuan, Geng and Dai, Yue and Zhang, Youtao and Wang, Yanzhi and Tang, Xulong},
  booktitle = {The Eleventh International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=i9UlAr1T_xl}
}

2022

IEEE Micro

Sustainable AI processing at the edge

Sébastien Ollivier, Sheng Li, Yue Tang, Stephen Cahoon, Ryan Caginalp, Chayanika Chaudhuri, Peipei Zhou, Xulong Tang, Jingtong Hu, and Alex K Jones

IEEE Micro, 2022

Bib HTML

@article{ollivier2022sustainable,
  title = {Sustainable AI processing at the edge},
  author = {Ollivier, S{\'e}bastien and Li, Sheng and Tang, Yue and Cahoon, Stephen and Caginalp, Ryan and Chaudhuri, Chayanika and Zhou, Peipei and Tang, Xulong and Hu, Jingtong and Jones, Alex K},
  journal = {IEEE Micro},
  volume = {43},
  number = {1},
  pages = {19--28},
  year = {2022},
  publisher = {IEEE}
}

NeurIPS

Layer freezing & data sieving: missing pieces of a generic framework for sparse training

Geng Yuan^*, Yanyu Li^*, Sheng Li, Zhenglun Kong, Sergey Tulyakov, Xulong Tang, Yanzhi Wang, and Jian Ren

Advances in Neural Information Processing Systems, 2022

Bib HTML

@article{yuan2022layer,
  title = {Layer freezing \&amp; data sieving: missing pieces of a generic framework for sparse training},
  author = {Yuan, Geng and Li, Yanyu and Li, Sheng and Kong, Zhenglun and Tulyakov, Sergey and Tang, Xulong and Wang, Yanzhi and Ren, Jian},
  journal = {Advances in Neural Information Processing Systems},
  volume = {35},
  pages = {19061--19074},
  year = {2022},
  url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/794a425a2e47e05d29d30f79b79a692d-Paper-Conference.pdf}
}

WWW workshop

Optimizing Data Layout for Training Deep Neural Networks

Bingyao Li, Qi Xue, Geng Yuan, Sheng Li, Xiaolong Ma, Yanzhi Wang, and Xulong Tang

In Companion Proceedings of the Web Conference, 2022

Bib HTML

@inproceedings{li2022optimizing,
  title = {Optimizing Data Layout for Training Deep Neural Networks},
  author = {Li, Bingyao and Xue, Qi and Yuan, Geng and Li, Sheng and Ma, Xiaolong and Wang, Yanzhi and Tang, Xulong},
  booktitle = {Companion Proceedings of the Web Conference},
  pages = {548--554},
  year = {2022}
}

Multimed Tools Appl

An adaptive regression based single-image super-resolution

Mingzheng Hou, Ziliang Feng, Haobo Wang, Zhiwei Shen, and Sheng Li

Multimedia Tools and Applications, 2022

Bib HTML

@article{hou2022adaptive,
  title = {An adaptive regression based single-image super-resolution},
  author = {Hou, Mingzheng and Feng, Ziliang and Wang, Haobo and Shen, Zhiwei and Li, Sheng},
  journal = {Multimedia Tools and Applications},
  volume = {81},
  number = {20},
  pages = {28231--28248},
  year = {2022},
  publisher = {Springer}
}

2019

IHMSC

A neural network-based teaching style analysis model

Sheng Li, Zanhan Ding, and Honglv Chen

In 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2019

Bib HTML

@inproceedings{li2019neural,
  title = {A neural network-based teaching style analysis model},
  author = {Li, Sheng and Ding, Zanhan and Chen, Honglv},
  booktitle = {2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)},
  volume = {2},
  pages = {154--157},
  year = {2019},
  organization = {IEEE}
}

CISCE

EEG signal classification method based on feature priority analysis and CNN

Sheng Li, and Hanxin Feng

In 2019 international conference on communications, information system and computer engineering (CISCE), 2019

Bib HTML

@inproceedings{li2019eeg,
  title = {EEG signal classification method based on feature priority analysis and CNN},
  author = {Li, Sheng and Feng, Hanxin},
  booktitle = {2019 international conference on communications, information system and computer engineering (CISCE)},
  pages = {403--406},
  year = {2019},
  organization = {IEEE}
}