Xiuyu Li

I am a Ph.D. student affiliated with Berkeley AI Research (BAIR) at UC Berkeley, advised by Prof. Kurt Keutzer. Previously, I received a B.A. in Computer Science and Math from Cornell University. During my undergrad years, I was fortunate to work with Prof. Zhiru Zhang, Prof. Vitaly Shmatikov, and Prof. Song Han.

Email: xiuyu [at] berkeley [dot] edu

   /      /      /      


My research focuses on efficient deep learning algorithms and systems, particularly for Large Language Models and Generative AI. I am committed to leveraging AI to develop reliable real-world applications.



(* indicates equal contribution)
Q-Diffusion: Quantizing Diffusion Models
Xiuyu Li, Yijiang Liu, Long Lian, Huanrui Yang, Zhen Dong, Daniel Kang, Shanghang Zhang, Kurt Keutzer
International Conference on Computer Vision (ICCV), 2023
[abs]  [paper]  [code]  [website]

SqueezeLLM: Dense-and-Sparse Quantization
Sehoon Kim*, Coleman Hooper*, Amir Gholami*, Zhen Dong, Xiuyu Li, Sheng Shen, Michael W. Mahoney, Kurt Keutzer
Preprint, 2023
[abs]  [paper]  [code
Press: Marktechpost

TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
Haotian Tang*, Shang Yang*, Zhijian Liu, Ke Hong, Zhongming Yu, Xiuyu Li, Guohao Dai, Yu Wang, Song Han
International Symposium on Microarchitecture (MICRO), 2023
[abs]  [paper]  [workshop paper]  [code]  [website]

TorchSparse: Efficient Point Cloud Inference Engine
Haotian Tang*, Zhijian Liu*, Xiuyu Li*, Yujun Lin, Song Han
Conference on Machine Learning and Systems (MLSys), 2022
[abs]  [paper [code]  [website]

Data Isotopes for Data Provenance in DNNs
Emily Wenger, Xiuyu Li, Ben Y. Zhao, Vitaly Shmatikov
Privacy Enhancing Technologies Symposium (PETS), 2024
[abs]  [paper

The ArtBench Dataset: Benchmarking Generative Models with Artworks
Peiyuan Liao*, Xiuyu Li*, Xihui Liu, Kurt Keutzer
Preprint, 2022
[abs]  [paper [code]

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Derek Lim*, Felix Hohne*, Xiuyu Li*, Sijia Linda Huang, Vaishnavi Gupta, Omkar Bhalerao, Ser-Nam Lim
Advances in Neural Information Processing Systems (NeurIPS), 2021
Previous version: New Benchmarks for Learning on Non-Homophilous Graphs
The Web Conference (WWW) Workshop on Graph Learning Benchmarks, 2021
[workshop paper]  [workshop pdf]  [workshop code & datasets]

[abs]  [paper [code & datasets]

GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks
Chenhui Deng, Xiuyu Li, Zhuo Feng, Zhiru Zhang
Learning on Graphs Conference (LoG), 2022, Spotlight
[abs]  [paper [code]