Yongqi Xu (徐永祺)
ID Photo

I am an undergraduate student majoring in School of Computer Science and Technology, Guangdong University of Technology.

My research interests include but are not limited to Video Generation, Multimodal Large Language Models, Data Minning, Computer Vision and AI for Science.

Email  |  Google Scholar  |  GitHub

Selected Publications

ChronoMagic-Bench : A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

ChronoMagic-Bench : A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

Shenghai Yuan, Jinfa Huang, Yongqi Xu, YaoYang Liu, Shaofeng Zhang, Yujun Shi, Ruijie Zhu, Xinhua Cheng, Jiebo Luo, Li Yuan

Arxiv, 2024

Paper Code Page LeaderBoard Dataset_Pro Dataset_ProH

We present ChronoMagic-Bench, a benchmark for metamorphic evaluation of text-to-time-lapse video generation, can reflect the physical prior capacity of the T2V model.

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Shenghai Yuan*, Jinfa Huang*, Yujun Shi, Yongqi Xu, Ruijie Zhu, Bin Lin, Xinhua Cheng, Li Yuan, Jiebo Luo

Arxiv, 2024

Paper Code Page Dataset Poster

We are thrilled to present MagicTime, a metamorphic time-lapse video generation model and a new dataset ChronoMagic, support U-Net or DiT-based T2V frameworks.

LSROM: Learning Self-Refined Organizing Map for Fast Imbalanced Streaming Data Clustering

LSROM: Learning Self-Refined Organizing Map for Fast Imbalanced Streaming Data Clustering

Yongqi Xu, Yujian Lee, Rong Zou, Yiqun Zhang, Yiu-ming Cheung

IEEE Transactions on Neural Networks and Learning System (TNNLS), 2024, under review

Paper Code

We propose an efficient approach called Learning Self-Refined Organizing Map (LSROM) to handle the imbalanced streaming data clustering problem.

LHNet: A Low-cost Hybrid Network for Single Image Dehazing

Accelerating Frequency-Domain Convolutional Neural Networks Inference Using FPGAs

Yi Chen, Bosheng Liu, Yongqi Xu, Jigang Wu, Xiaoming Chen, Peng Liu, Qingguo Zhou, Yinhe Han

IEEE International Symposium on Circuits and Systems (ISCAS), 2024

We present an FPGA-based 8-bit inference accelerator that packs frequency-domain calculations into digital signal processing (DSP) blocks to fully utilize DSPs for performance boost.

LHNet: A Low-cost Hybrid Network for Single Image Dehazing

Bitwidth-aware Block Floating Point Quantization for Deep Neural Network Inference on Embedded Platforms

Yongqi Xu, Yujian Lee, Gao Yi, Bosheng Liu, Yikai Zhou, Xuandi Zeng, Peng Liu, Qingguo Zhou, Jigang Wu

ACM International Conference on Multimedia (ACM MM), 2024, under review

Code

We develop a BFP-based bitwidth-ware analytical modeling framework (called “BitQ”) for the best implementation of DNN inference on embedded platforms.

LHNet: A Low-cost Hybrid Network for Single Image Dehazing

Accelerating event-based deep neural networks via flexible data encoding

Yuanli Zhong, Yongqi Xu, Bosheng Liu, Yibing Tang, Jigang Wu

IEICE Electronics Express (IEICE), 2023

Paper

We provide a dataflow that enables flexible DNN data encodings based on the event data characteristic for energy saving.

LHNet: A Low-cost Hybrid Network for Single Image Dehazing

TENET: Triple-enhancement based graph neural network for cell-cell interaction network reconstruction from spatial transcriptomics

Yujian Lee, Yongqi Xu, Peng Gao, Jiaxing Chen

Journal of Molecular Biology (JMB), 2024

Paper

We propose Triple-Enhancement based Graph Neural Network (TENET), in which three progressive enhancement mechanisms build upon each other to create a cumulative effect.

Patents

FPGA-based mixed-precision data frequency domain convolution acceleration method and system

Yongqi Xu, Bosheng Liu, Yi Chen, Shenghai Yuan

YGZS231122AF332

Frequency domain convolution operation acceleration system for 8-bit frequency domain convolutional neural network

Yi Chen, Bosheng Liu, Yongqi Xu, Jigang Wu

YGZS2214229AF286

Awards