Yen-Cheng Liu

I am a research scientist at Meta GenAI. My research interests span the areas of computer vision and machine learning. I am currently exploring media generation, with a particular focus on video and image generation. One of my recent projects is Meta Movie Gen, a cast of sophisticated foundation models designed for media generation (video, image, and audio).

Before this, I earned my PhD from Georgia Tech, where I had the opportunity to work with Prof. Zsolt Kira. My PhD research centers on enhancing the efficiency of model parameters, data, and label annotations in the training of large-scale machine learning models, which rely on substantial foundation models trained on vast datasets and labels.

[CV] [Google Scholar ]

ycliu93 [AT] meta [DOT] com

Selected Projects

Movie Gen: A Cast of Media Foundation Models

Movie Gen Team (core contributor)
[Project Page] [Paper]

Fast Trainable Projection for Robust Fine-tuning

Conference on Neural Information Processing Systems (NeurIPS), 2023
Junjiao Tian, Yen-Cheng Liu, James Seale Smith, Zsolt Kira.
[Paper] [Code]

Trainable Projected Gradient Method for Robust Fine-Tuning

Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Junjiao Tian, Xiaoliang Dai, Chih-Yao Ma, Zecheng He, Yen-Cheng Liu, Zsolt Kira
[Paper] [Code]

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

Conference on Neural Information Processing Systems (NeurIPS), 2022
Yen-Cheng Liu, Chih-Yao Ma, Junjiao Tian, Zijian He, Zsolt Kira
[Paper] [Project Page]

Open-set Semi-supervised Object Detection

European Conference on Computer Vision (ECCV), 2022
Yen-Cheng Liu, Chih-Yao Ma, Xiaoliang Dai, Junjiao Tian, Peter Vajda, Zijian He, Zsolt Kira
[Paper] [Project Page]

Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2022
Yen-Cheng Liu, Chih-Yao Ma, Zsolt Kira
[Paper] [Project Page] [Code]

Unbiased Teacher for Semi-Supervised Object Detection

International Conference on Learning Representations (ICLR), 2021
Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda
[Paper] [Project Page] [Code]

Posterior Re-calibration for Imbalanced Datasets

Conference on Neural Information Processing Systems (NeurIPS), 2020
Junjiao Tian, Yen-Cheng Liu, Nathaniel Glaser, Yen-Chang Hsu, Zsolt Kira
[Paper] [Code]

When2com: Multi-Agent Perception via Communication Graph Grouping

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Yen-Cheng Liu, Junjiao Tian*, Nathaniel Glaser*, Zsolt Kira (* indicates equal contribution)
[Project Page]

Who2com: Collaborative Perception via Learnable Handshake Communication

International Conference on Robotics and Automation (ICRA), 2020
Yen-Cheng Liu, Junjiao Tian, Chih-Yao Ma, Nathaniel Glaser, Chia-Wen Kuo, Zsolt Kira
[Paper] [Project Page]

UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation

International Conference on Robotics and Automation (ICRA), 2020
Junjiao Tian, Wesley Cheung, Nathan Glaser, Yen-Cheng Liu, Zsolt Kira
[Paper]

Towards Scene Understanding: Unsupervised Monocular Depth Estimation with Semantic-aware Representation

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Po-Yi Chen*, Alexander H. Liu*, Yen-Cheng Liu, Yu-Chiang Frank Wang (* indicates equal contribution)
[Paper]

A Closer Look at Few-shot Classification

International Conference on Learning Representations (ICLR), 2019
Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, Jia-Bin Huang
[Project Page][Paper] [Code]

A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation

Conference on Neural Information Processing Systems (NeurIPS), 2018
Alexendar Liu, Yen-Cheng Liu, Yu-Ying Yeh, Yu-Chiang Frank Wang
[Paper] [Code]

Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Yen-Cheng Liu, Yu-Ying Yeh, Tzu-Chien Fu, Sheng-De Wang, Wei-Chen Chiu, Yu-Chiang Frank Wang
[Paper] [Code]

Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines

Conference on Neural Information Processing Systems Workshops (NeurIPS Workshops), 2018
Yen-Chang Hsu, Yen-Cheng Liu, Anita Ramasamy, Zsolt Kira
[Paper] [Code]