Efficient Generative AI · MLSys

I am an M.Phil. student at HKUST(GZ), advised by Prof. Zeke Xie. I am currently a research intern at NVIDIA Research supervised by Dr. Enze Xie and Prof. Song Han. I was once very fortunate to be a visiting student at Westlake University, advised by Prof. Huan Wang. My research focuses on Efficient Generative AI and MLSys.

Publications

Technical Report

Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation

Yitong Li, Junsong Chen, Haopeng Li, Haozhe Liu, Jincheng Yu, Ligeng Zhu, Ping Luo, Song Han, Enze Xie

Technical Report

ArXiv Code

Technical Report

MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model

Catnip AI Team (including Haopeng Li)

Technical Report

ArXiv Code

ICLR 2026

Autoregressive Image Generation with Randomized Parallel Decoding

Haopeng Li, Jinyue Yang, Guoqi Li, Huan Wang

The 14th International Conference on Learning Representations (ICLR 2026)

Paper Website Code

Preprint

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

Haopeng Li, Shitong Shao, Wenliang Zhong, Zikai Zhou, Lichen Bai, Hui Xiong, Zeke Xie

Under Review

ArXiv Code

ICML 2026

LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention

Shitong Shao, Zikai Zhou, Haopeng Li, Yingwei Song, Wenliang Zhong, Lichen Bai, Zeke Xie

The 43rd International Conference on Machine Learning (ICML 2026)

ArXiv Code

Preprint

Scalable Autoregressive Image Generation with Mamba

Haopeng Li, Jinyue Yang, Kexin Wang, Xuerui Qiu, Yuhong Chou, Xin Li, Guoqi Li

Preprint

ArXiv Code

NeurIPS 2024

Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models

Xin Li, Weize Chen, Qizhi Chu, Haopeng Li, Zhaojun Sun, Ran Li, Chen Qian, Yiwei Wei, Zhiyuan Liu, Chuan Shi, Maosong Sun, Cheng Yang

The 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

Paper Code

Projects

FLA

Flash Bidirectional Linear Attention

Haopeng Li

A Triton-Based Library for Efficient Implementations of Bidirectional Linear Attention.

Code

Awards

2025.09 Postgraduate StudentshipHKUST(GZ)

2021.10 National ScholarshipMinistry of Education