Hongfan Gao | East China Normal University

About Me

I am currently a third year Ph.D. student at Decision Intelligence Lab, School of Data Science and Engineering (DaSE), East China Normal University (ECNU), supervised by Prof.Jilin Hu.

My research focuses on achieving end-to-end lightweight machine learning and deep learning pipelines to support practical deployment on resource-constrained and edge devices and its applications to time series. I am also interested in related topics such as generative models, inference acceleration and model compression.

Education

Ph.D., School of Data Science and Engineering, East China Normal University, 2023-Present
M.S., Software Engineering Insititue, East China Normal University, 2020-2023
B.S., School of Information Science and Technology, East China Normal University, 2014-2018
Liaoning Province Shiyan High School, 2011-2014

Research Interests

Linear Attention: linear attention for LLMs
Lightweight AI: dataset distillation, inference acceleration, model compression, lightweight module design
Generative AI: diffusion models, flow-based models and its acceleration
LLMs: compression and acceleration for LLMs

News

[Jan. 2026] Our paper about diffusion models and imputation is accepted to WWW 2026.
[Mar. 2025] Our paper about state space models for diffusion models is accepted to SIGKDD 2025.
[Mar. 2025] Our paper about probabilistic time series forecasting is accepted to ICML 2025 (Spotlight).

Publications

FSDI: Frequency-Shaped Diffusion For Time-Series Imputation

Wangmeng Shen, Hongfan Gao, Qingsong Zhong, Dingli Xu, Jilin Hu*

The World Wide Web Conference, 2026

SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputation

Hongfan Gao, Wangmeng Shen, Xiangfei Qiu, Ronghui Xu, Bin Yang, Jilin Hu*

ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025

PDF Code

$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting

Xingjian Wu, Xiangfei Qiu, Hongfan Gao, Jilin Hu, Bin Yang*, Chenjuan Guo

International Conference on Machine Learning, 2025

PDF spotlight

MM-Path: Multi-modal, Multi-granularity Path Representation Learning

Ronghui Xu, Hanyin Cheng, Chenjuan Guo, Hongfan Gao, Jilin Hu, Sean Bin Yang, Bin Yang*

ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025

PDF

Path-LLM: A Multi-Modal Path Representation Learning by Aligning and Fusing with Large Language Models

Yongfu Wei, Yan Lin, Hongfan Gao, Ronghui Xu, Sean Bin Yang, Jilin Hu*

The World Wide Web Conference, 2025

PDF

Enhancing real-time super resolution with partial convolution and efficient variance attention

Zhou Zhou, Jiahao Chao, Jiali Gong, Hongfan Gao, Zhenbing Zeng, Zhengfeng Yang*

ACM Multimedia, 2023

PDF

A novel learnable interpolation approach for scale-arbitrary image super-resolution

Jiahao Chao, Zhou Zhou, Hongfan Gao, Jiali Gong, Zhenbing Zeng, Zhengfeng Yang*

International Joint Conference on Artificial Intelligence, 2023

PDF

Equivalent transformation and dual stream network construction for mobile image super-resolution

Jiahao Chao, Zhou Zhou, Hongfan Gao, Jiali Gong, Zhenbing Zeng, Zhengfeng Yang*, Lydia Dehbi

IEEE Conference on Computer Vision and Pattern Recognition, 2023

PDF

Kernel estimation and deconvolution for blind image super-resolution

Jiali Gong, Hongfan Gao, Jiahao Chao, Zhou Zhou, Zhengfeng Yang*, Zhenbing Zeng

IEEE International Conference on Acoustics, Speech and Signal Processing, 2023

PDF

Services

Conference Reviewers

Journal Reviewers

Knowledge-Based Systems (KBS)

Teaching Experiences

Teaching Assistant, Data Platform, Fall 2023,2024, Spring 2024,2025 Prof. Jilin Hu