Liangyu Chen    陈亮宇

Hi! 👋 I am a research assistant at MMLab, Nanyang Technological University, advised by Prof. Ziwei Liu.

My research interest lies in generalizable and data-efficient machine learning frameworks for high-level visual recognition 👀 or reasoning 🤔. I develop data collection pipelines, representations, and models for interactive or assistive AI systems.

Previously, I worked with Prof. Alan Yuille and Dr. Zongwei Zhou at Johns Hopkins University, on self-supervised learning and human-in-the-loop machine learning. Before that, I also spent great time at ByteDance, Alibaba, NUS, and A*STAR Singapore. I obtained my Bachelor’s degree in Information Engineering & Media from Nanyang Technological University.

Email  /  Google Scholar  /  Semantic Scholar  /  Github  /  Linkedin

profile photo
Publications

Making Your First Choice: To Address Cold Start Problem in Vision Active Learning
Liangyu Chen, Yutong Bai, Siyu Huang, Yongyi Lu, Bihan Wen, Alan Yuille, Zongwei Zhou
NeurIPS Workshop on Human in the Loop Learning, 2022


Multi-task Graph Convolutional Neural Network for Calcification Morphology and Distribution Analysis in Mammograms
Hao Du, Melissa Min-Szu Yao, Liangyu Chen, Wing P. Chan, Mengling Feng
Tech report, 2021


Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning
Linsen Dong, Guanyu Gao, Xinyi Zhang, Liangyu Chen, Yonggang Wen
Tech report, 2020


Datasets and Benchmarks
  • CSVAL: Benchmarking Initial Queries in Vision Active Learning, NeurIPS'22 workshop.
  • OpenPSG: A Dataset and Benchmark for Panoptic Scene Graph Generation (PSG), ECCV'22. [🤗 Hugging Face Demo]
  • Baconian: Model-based Reinforcement Learning Framework. [Demo]

  • Service
  • Reviewer for The Visual Computer, IET Computer Vision, ICML 2022 Workshop.


  • I host virtual office hours for anyone who wants to share thoughts on CV/ML research, reading (either scientific or not), or any other topics of interest. Please schedule via my calendar.

    Last update: Jan 2023      Template