Gongfan Fang

Research Scientist · NVIDIA

I'm Gongfan Fang, a Research Scientist at NVIDIA working on Efficient LLMs. My research focuses on Efficient Deep Learning. I am the creator of Torch-Pruning, a widely used open-source library for structural pruning of deep neural networks.

Before joining NVIDIA, I received my Ph.D. from the National University of Singapore, advised by Prof. Xinchao Wang. During my Ph.D., I was awarded the 2024 ByteDance Scholarship. Prior to that, I obtained my B.Eng. (2019) and M.Eng. (2022) from Zhejiang University, advised by Prof. Mingli Song.

News

Oct 2026
Stanford/Elsevier’s World’s Top 2% Scientists (2026)
Sep 2026
Three papers were accepted to NeurIPS’26.
May 2026
Four papers were accepted to ICML’26.
Feb 2026
Two papers were accepted to CVPR’26.
Jan 2026
Three papers dParallel, SparseD and Invisible Safety Threat (Oral) were accepted to ICLR’26.

Selected publications

Google Scholar

Thinkless: LLM Learns When to Think

Gongfan Fang, Xinyin Ma, and Xinchao Wang

NeurIPS 2025

arXiv Code

@article{fang2025thinkless,
  title = {Thinkless: LLM Learns When to Think},
  author = {Fang, Gongfan and Ma, Xinyin and Wang, Xinchao},
  journal = {Advances in Neural Information Processing Systems},
  year = {2025},
}

MaskLLM: Learnable Semi-structured Sparsity for Large Language Models

Gongfan Fang, Hongxu Yin, Saurav Muralidharan, Greg Heinrich, Jeff Pool, Jan Kautz, Pavlo Molchanov, and Xinchao Wang

NeurIPS 2024 Spotlight

arXiv Project Code

@article{fang2024maskllm,
  title = {MaskLLM: Learnable Semi-structured Sparsity for Large Language Models},
  author = {Fang, Gongfan and Yin, Hongxu and Muralidharan, Saurav and Heinrich, Greg and Pool, Jeff and Kautz, Jan and Molchanov, Pavlo and Wang, Xinchao},
  journal = {Advances in Neural Information Processing Systems},
  year = {2024},
}

DeepCache: Accelerating Diffusion Models for Free

Xinyin Ma, Gongfan Fang, and Xinchao Wang

CVPR 2024

arXiv Code

@inproceedings{ma2023deepcache,
  title = {DeepCache: Accelerating Diffusion Models for Free},
  author = {Ma, Xinyin and Fang, Gongfan and Wang, Xinchao},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2024},
}

DepGraph: Towards Any Structural Pruning

Gongfan Fang, Xinyin Ma, Mingli Song, Michael Bi Mi, and Xinchao Wang

CVPR 2023

arXiv PDF Code

@inproceedings{fang2023depgraph,
  title = {DepGraph: Towards Any Structural Pruning},
  author = {Fang, Gongfan and Ma, Xinyin and Song, Mingli and Mi, Michael Bi and Wang, Xinchao},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {16091--16101},
  year = {2023},
}