About
I am a Ph.D. student advised by Prof. Marc Niethammer at the University of North Carolina at Chapel Hill. Previously, I was advised by Prof. Dinggang Shen at Shanghai Jiao Tong University working on medical imaging.
Research Interests
My research interests lie in the development of human-centered machines that learn from human interactions and enhance human abilities, rather than replace humans. Particularly, I am interested in the following topics:
Human-AI Interaction: interactive visual object segmentation, controllable generation, instruction tuning
Human-centered AI: alignment, causality, explainability, healthcare applications
Foundation Model: vision transformer, quantized training, efficient sequence modeling, multi-modal learning
News
06/2024 Summer internship at Microsoft (remote), advised by Zhengyuan Yang and Jianfeng Wang.
06/2023 Summer internship at Amazon, advised by Manchen Wang and Zhenlin Xu.
04/2023 We maintain an up-to-date list of awesome foundation models. Welcome to contribute.
05/2022 Summer internship at UII America again.
05/2021 Summer internship at UII America, advised by Ziyan Wu and Terrence Chen.
08/2020 Joined UNC CS as a Ph.D. student.
Publications
[Preprint] Exploring Cycle Consistency Learning in Interactive Volume Segmentation
Qin Liu, Meng Zheng, Benjamin Planche, Zhongpai Gao, Terrence Chen, Marc Niethammer, Ziyan Wu. [Code/Models]
[CVPR'24] Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts
Qin Liu, Jaemin Cho, Mohit Bansal, Marc Niethammer. [Code/Models]
[ICCV'23] SimpleClick: Interactive Image Segmentation with Simple Vision Transformers
Qin Liu, Zhenlin Xu, Gedas Bertasius, Marc Niethammer. [Code/Models]
[ECCV'22] PseudoClick: Interactive Image Segmentation with Click Imitation
Qin Liu, Meng Zheng, Benjamin Planche, Srikrishna Karanam, Terrence Chen, Marc Niethammer, Ziyan Wu. [Supp]
[MICCAI'22] iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images
Qin Liu, Zhenlin Xu, Yining Jiao, Marc Niethammer. [Code/Models]
[MICCAI'19] Multi-class Gradient Harmonized Dice Loss with Application to Knee MR Image Segmentation (early accept)
Qin Liu*, XiongfengTang*, Deming Guo, Yanguo Qin, Pengfei Jia, Yiqiang Zhan, Xiang Zhou, Dijia Wu. (*equal contribution)
Hobbies
Marathon (certificates)
Reading, writing, and breakdancing (sport of 2024 Summer Olympics)