Jierun CHEN (陈捷润)

I am currently a researcher at Huawei Noah's Ark Lab (Hong Kong). I obtained my Ph.D. degree from CSE Department, HKUST, advised by Prof. Shueng-Han Gary Chan. I interned at Snap Research working on efficient text-to-image models, with Jian Ren and Anil Kag. I also interned at MSRA, working with Fangyun Wei on multimodal large language models (MLLM). I received my B.Eng. in Electrical Engineering from Edison Experimental Class, Zhejiang University.

My research topics include Efficient Foundation Models and Multi-modal Modeling.

Email: jierunchen@gmail.com  /  Google Scholar  /  LinkedIn  /  Github

Publications
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
Jierun Chen*, Dongting Hu*, Xijie Huang*, Huseyin Coskun, Arpit Sahni, Aarush Gupta, Anujraaj Goyal, Dishani Lahiri, Rajesh Singh, Yerlan Idelbayev, Junli Cao, Yanyu Li, Kwang-Ting Cheng, S.-H. Gary Chan, Mingming Gong, Sergey Tulyakov, Anil Kag, Yanwu Xu, Jian Ren
CVPR 2025 (Highlight)
project / pdf/ Snap Newsroom/ TechCrunch

We propose SnapGen, the first text-to-image model (379M) that can synthesize high-resolution images (1024x1024) on mobile devices in 1.4s, and achieve 0.66 on GenEval metric.

Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models
Jierun Chen*, Fangyun Wei*, Jinjing Zhao, Sizhe Song, Bohuai Wu, Zhuoxuan Peng, S.-H. Gary Chan, Hongyang Zhang
CVPR Workshop BEAM 2025
pdf / code / dataset

We clean the widely-adopted RefCOCO,+,g benchmarks and introduce Ref-L4, a New REC benchmark in the LMM Era.

AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
Anil Kag, Huseyin Coskun, Jierun Chen, Junli Cao, Willi Menapace, Aliaksandr Siarohin, Sergey Tulyakov, Jian Ren
NeurIPs 2024
project / pdf

We introduce AsCAN, a hybrid neural network with asymmetric convolutional and transformer blocks, offering superior performance and efficiency across image recognition and generation tasks.

Target-agnostic Source-free Domain Adaptation for Regression Tasks
Tianlang He, Zhiqiu Xia, Jierun Chen, Haoliang Li, S.-H. Gary Chan
ICDE 2024
pdf

We propose TASFAR, a novel target-agnostic source-free domain adaptation method for regression tasks.

Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Jierun Chen, Shiu-hong Kao, Hao He, Weipeng Zhuo, Song Wen, Chul-Ho Lee, S.-H. Gary Chan
CVPR 2023
pdf / code

We propose a simple yet fast and effective partial convolution (PConv), as well as a latency-efficient family of architectures called FasterNet.

Semi-supervised Learning with Network Embedding on Ambient RF Signals for Geofencing Services
Weipeng Zhuo, Ka Ho Chiu, Jierun Chen, Jiajie Tan, Edmund Sumpena, Sangtae Ha, S.-H. Gary Chan, Chul-Ho Lee
ICDE 2023
pdf / code

We develop a practical geofencing system, solely based on ambient radio frequency (RF) signals, to enable applications like elderly care, dementia antiwandering, pandemic control, etc.

StableKD: Breaking Inter-block Optimization Entanglement for Stable Knowledge Distillation
Shiu-hong Kao*, Jierun Chen*, S.-H. Gary Chan
Preprint 2023
pdf

We propose StableKD, a simple and efficient Knowledge Distillation framework that attains higher accuracy using fewer training epochs and less data.

CP-NeRF: Conditionally Parameterized Neural Radiance Fields for Cross-scene Novel View Synthesis
Hao He, Yixun Liang, Shishi Xiao, Jierun Chen, Yingcong Chen
Pacific Graphics 2023
pdf

We propose CP-NeRF to enable training a one-for-all NeRF across diverse scenes.

FIS-ONE: Floor Identification System with One Label for Crowdsourced RF Signals
Weipeng Zhuo, Ka Ho Chiu, Jierun Chen, Ziqi Zhao, S.-H. Gary Chan, Sangtae Ha, Chul-Ho Lee
ICDCS 2023
pdf / code

We design a floor identification system for crowdsourced RF signals in a building using only one labeled data sample from the bottom floor.

TVConv: Efficient Translation Variant Convolution for Layout-Aware Visual Processing
Jierun Chen, Tianlang He, Weipeng Zhuo, Li Ma, Sangtae Ha, S.-H. Gary Chan
CVPR 2022
pdf / video / code

TVConv works more computation-efficient than regular convolution when dealing with layout-specific tasks, e.g., face recognition.

Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
Jierun Chen, Song Wen, S.-H. Gary Chan
AAAI 2021
pdf / video

We consider the ground truth uncertainty for joint demosaicking and denoising in the wild, which provides better restoration result and interpretability.

Misc

Teaching Assistant

  • COMP 2012H Honors Object-Oriented Programming and Data Structures, Fall 2022
  • COMP 4911/6613D/ENTR4911 IT Entrepreneurship, Fall 2021
  • COMP 4021 Internet Computing, Fall 2020
  • COMP 4611 Design and Analysis of Computer Architectures, Spring 2020

Reviewer

  • Conference: ICLR, CVPR, ICCV, ECCV, UbiComp, INFOCOM, BMVC, ACCV
  • Journal: IJCV, TIM

Selected Awards

  • RedBird Academic Excellence Award, HKUST, 2022
  • Postgraduate Scholarship, HKUST, 2019-2023
  • Outstanding Graduate, ZJU, 2018
  • Scholarship for Excellence in Research and Innovation, ZJU, 2017
  • 1st prize in Nanjiang Lebo Cup Provincial Robot Competition (ranked 1/62), 2017
  • 1st prize in National Undergraduate Electronic Design Contest (ranked 3/109 in Zhejiang Division), 2017
  • Scholarship for Outstanding Merits, ZJU, 2015, 2017
  • Excellent Student Awards, ZJU, 2015, 2017