Liang-Chieh (Jay) Chen- Home Page

jay photo 

Liang-Chieh Chen
Research Scientist, ByteDance, Los Angeles

Email: lcchen at cs dot ucla dot edu

[google-scholar] [semantic-scholar]

About Me

I am currently a Research Scientist at ByteDance / TikTok with a focus on Computer Vision and Deep Learning.

I am best known for my contributions to the DeepLab series (co-developed with George Papandreou): DeepLabv1, DeepLabv2, DeepLabv3, DeepLabv3+. Since December 2014, our introduced atrous convolution (also known as convolution with holes or dilated convolution) has been widely used for dense prediction tasks.

Influential DeepLab derivatives include Auto-DeepLab, Panoptic-DeepLab (winning method of the Mapillary Vistas Panoptic Segmentation track at ICCV 2019, and top performer on Cityscapes leaderboards), Axial-DeepLab, ViP-DeepLab, MaX-DeepLab, and kMaX-DeepLab. Additionally, I am known for my collaborative work on MobileNetv2 and MobileNetv3, which have set new benchmarks in neural network design and search for mobile devices.

Before joining ByteDance, I spent 7 years as a Research Scientist at Google in Los Angeles from 2016 to 2023. In 2015, I earned my Ph.D. in Computer Science from UCLA, where I was advised by Alan L. Yuille.

News

  • For motivated Ph.D. students looking for internships, feel free to contact me for details. Our team works on fundamental research on visual recognition, representation learning, and deep learning.

Activities

  • Area Chair for ICCV 2019, CVPR 2020, 2023, 2024, 2025, ECCV 2020, 2024, NeurIPS 2022, 2024.

Selected Recent Publications

MaskBit 

MaskBit: Embedding-free Image Generation via Bit Tokens
Mark Weber, Lijun Yu, Qihang Yu, Xueqing Deng, Xiaohui Shen, Daniel Cremers, Liang-Chieh Chen
Technical report
[preprint (arxiv: 2409.16211)] [project website]

DiMR 

Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models
Qihao Liu*, Zhanpeng Zeng*, Ju He*, Qihang Yu, Xiaohui Shen, Liang-Chieh Chen
(*equal contribution)
In Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 2024.
[preprint (arxiv: 2406.09416)] [project website] [code]

titok 

An Image is Worth 32 Tokens for Reconstruction and Generation
Qihang Yu*, Mark Weber*, Xueqing Deng, Xiaohui Shen, Daniel Cremers, Liang-Chieh Chen
(*equal contribution)
In Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 2024.
[preprint (arxiv: 2406.07550)] [project website] [code]

video-3dgs 

Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting
Inkyu Shin, Qihang Yu, Xiaohui Shen, In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen
Technical report
[preprint (arxiv: 2406.02541)] [project website]

coconut 

COCONut: Modernizing COCO Segmentation
Xueqing Deng, Qihang Yu, Peng Wang, Xiaohui Shen, Liang-Chieh Chen
In Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA, June 2024.
[preprint (arxiv: 2404.08639)] [project website] [code] [data (Kaggle)]

vitamin 

ViTamin: Designing Scalable Vision Models in the Vision-Language Era
Jieneng Chen, Qihang Yu, Xiaohui Shen, Alan Yuille, Liang-Chieh Chen
In Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA, June 2024.
[preprint (arxiv: 2404.02132)] [project website] [code] [HuggingFace]

maxtron 

MaXTron: Mask Transformer with Trajectory Attention for Video Panoptic Segmentation
Ju He, Qihang Yu, Inkyu Shin, Xueqing Deng, Xiaohui Shen, Alan Yuille, Liang-Chieh Chen
Transactions on Machine Learning Research (TMLR), June 2024.
[preprint (arxiv: 2311.18537)] [PyTorch code]