Lihao Liu Applied Scientist Amazon, USA

Biography  

I am an Applied Scientist at Amazon, USA. I obtain my Ph.D. degree from University of Cambridge, under the supervision of Carola-Bibiane Schönlieb and Angelica I. Aviles-Rivero, and Pietro Liò. Before that, I received my M.Phil. degree from Dept. of Computer Science and Engineering (CSE), The Chinese University of Hong Kong, under the supervision of Prof. Pheng-Ann Heng, and my B.Eng. degree from Dept. of Software Engineering, Chongqing University.

My research interests include LLM-based Agent and AI for Healthcare.

News

• [05/2025] Four papers are early accepted at MICCAI'2025. Big congrats to Jiyao, Junzhi, Huihui, and Wei.
• [02/2025] Two papers are accepted at CVPR'2025. Big congrats to Zhaohu and Jiuming.
• [10/2024] One paper is accepted at IEEE TITS.
• [08/2024] One paper is accepted at ACM MM'2024.
• [05/2024] Ph.D. thesis submitted! — I am now a Doctor, and I will be joining Amazon USA as an Applied Scientist!
[03/2024] We win 1st place in Phase 1, and 2nd place in Phase 2 of the DREAMING Challenge 2024.
[11/2023] Two papers are accepted at Medical Image Analysis (MIA).
[10/2023] Our paper on contrastive registration for unsupervised segmentation is accepted at IEEE TNNLS.
[02/2023] Our paper on video shadow detection is accepted at CVPR'2023!
[02/2023] Our paper on surgical video recognition is accepted at ICLR-TML4H’23.
[06/2022] Our challenge method paper is accepted at MIUA'2022, and win the Merit NVIDIA Paper Award!
[05/2022] Two papers are accepted on WBIR'2022.
[03/2022] We win the 4th place on the grand challenge CoNIC'2022.
[03/2021] I will join Microsoft Research Cambridge as an research intern.
[06/2020] I pass my M.Phil. thesis oral defense, and will join Cambridge Image Analysis group as a Ph.D. student!
[01/2020] Our paper on supervised 3d brain segmentation is accepted at IEEE Transactions on Medical Imaging (TMI).
[07/2019] Our extended paper on lung nodule analysis is accepted at IEEE Transactions on Medical Imaging (TMI).
[06/2019] Our paper on unsupervised 3d brain image registration is early accepted at MICCAI'2019!
[08/2018] Our paper on lung nodule analysis is accepted at MICCAI-DLMIA'2018.

Selected Publications

                                                            

	Learning, Reasoning, Refinement: A Framework for Kahneman’s Dual-System Intelligence in GUI Agents Jinjie Wei, Jiyao Liu, Lihao Liu, Ming Hu, Junzhi Ning, Mingcheng Li, Weijie Yin, Junjun He, Xiao Liang, Chao Feng, Dingkang Yang Arxiv Tech Repor, 2025. [paper]
	Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine Zhaohu Xing, Lihao Liu, Yijun Yang, Hongqiu Wang, Tian Ye, Sixiang Chen, Wenxue Li, Guang Liu, and Lei Zhu Computer Vision and Pattern Recognition (CVPR), 2025. [paper]
	SCOTCH and SODA: A Transformer Video Shadow Detection Framework Lihao Liu, Jean Prost, Lei Zhu, Nicolas Papadakis, Pietro Liò, Carola-Bibiane Schönlieb, and Angelica I Aviles-Rivero. Computer Vision and Pattern Recognition (CVPR), 2023. [paper] [project]
	Contrastive Registration for Unsupervised Medical Image Segmentation Lihao Liu, Angelica I Aviles-Rivero, Carola-Bibiane Schönlieb. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022. [paper] [code]
	Multi-Task Deep Model with Margin Ranking Loss for Lung Nodule Analysis Lihao Liu, Qi Dou, Hao Chen, Jing Qin, and Pheng-Ann Heng. IEEE Transactions on Medical Imaging (TMI), 2019. [paper] [code]
	Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models Jiuming Liu, Jinru Han, Lihao Liu, Angelica I Aviles-Rivero, Chaokang Jiang, Zhe Liu, and Hesheng Wang Computer Vision and Pattern Recognition (CVPR), 2025. [paper][code]
	TrafficMOT: A Challenging Dataset for Multi-Object Tracking in Complex Traffic Scenarios Lihao Liu, Yanqi Cheng, Zhongying Deng, Shujun Wang, Dongdong Chen, Xiaowei Hu, Pietro Liò, Carola-Bibiane Schönlieb, and Angelica I Aviles-Rivero. ACM Multimedia (MM), 2024. [paper]
	Traffic Video Object Detection using Motion Prior Lihao Liu, Yanqi Cheng, Dongdong Chen, Jing He, Pietro Liò, Carola-Bibiane Schönlieb, and Angelica I Aviles-Rivero. Under Review at IEEE Transactions on Image Processing (TIP), 2024. [paper]
	TrafficCAM: A Versatile Dataset for Traffic Flow Segmentation Zhongying Deng, Yanqi Chen, Lihao Liu, Shujun Wang, Rihuan Ke, Carola-Bibiane Schonlieb, and Angelica I Aviles-Rivero. IEEE Transactions on Intelligent Transportation Systems (TITS), 2024. [paper] [project]
	Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness Yanqi Cheng, Lihao Liu, Shujun Wang, Yueming Jin, Carola-Bibiane Schönlieb, Angelica I. Aviles-Rivero. Trustworthy Machine Learning for Healthcare (ICLR-TML4H), 2023. [paper] [project]
	PC-SwinMorph: Patch Representation for Unsupervised Medical Image Registration and Segmentation Lihao Liu, Zhening Huang, Pietro Liò, Carola-Bibiane Schönlieb, and Angelica I Aviles-Rivero. Major Revision at Medical Image Analysis. (MIA), 2023. [paper]
	You Only Look at Patches: A Patch-wise Framework for 3D Unsupervised Medical Image Registration Lihao Liu, Zhening Huang, Pietro Liò, Carola-Bibiane Schönlieb, and Angelica I Aviles-Rivero. Biomedical Image Registration (WBIR), 2022. [paper]
	MammoDG: Generalisable Deep Learning for Cross-Domain Multi-Center Breast Cancer Screening Yijun Yang, Shujun Wang, Lihao Liu, Sarah Hickman, Fiona J Gilbert, Carola-Bibiane Schönlieb, Angelica I. Aviles-Rivero. Under Review at International Journal of Computer Vision (IJCV), 2023. [paper]
	CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting Simon Graham, Quoc Dang Vu, ..., Lihao Liu, Chengyang Hong, and et. al. Medical Image Analysis (MIA), 2023. [paper] [code] [project]
	Simultaneous Semantic and Instance Segmentation for Colon Nuclei Identification and Counting Lihao Liu, Chengyang Hong, Angelica I Aviles-Rivero, and Carola-Bibiane Schönlieb. Medical Image Understanding and Analysis (MIUA), 2022. [paper] [code] [algorithm] [Merit NVIDIA Paper Award!] [Ranking 4/373 in the CoNIC-2022!]
	Learning Homeomorphic Image Registration via Conformal-Invariant Hyperelastic Regularisation Jing Zou, Noémie Debroux, Lihao Liu, Jing Qin, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero. Medical Image Analysis (MIA), 2023. [paper]
	Deformable Lung CT Registration by Decomposing Large Deformation Jing Zou, Lihao Liu, Youyi Song, Kup-Sze Choi, Jing Qin. Biomedical Image Registration (WBIR), 2022. [paper]
	Ψ-Net: Stacking Densely Convolutional LSTMs for Sub-cortical Brain Structure Segmentation Lihao Liu, Xiaowei Hu, Lei Zhu, Chi-Wing Fu, Jing Qin, and Pheng-Ann Heng. IEEE Transactions on Medical Imaging (TMI), 2020. [paper] [code]
	Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration Lihao Liu, Xiaowei Hu, Lei Zhu, and Pheng-Ann Heng. Medical Image Computing and Computer Assisted Intervention (MICCAI), 2019. [paper] [code]
	MTMR-Net: Multi-Task Deep Learning with Margin Ranking Loss for Lung Nodule Analysis Lihao Liu, Qi Dou, Hao Chen, Iyiola E. Olatunji, Jing Qin, and Pheng-Ann Heng. Deep Learning in Medical Image Analysis (MICCAI-DLMIA), 2018. [paper] [code]

Experience

• Amazon, Pasadena, USA
  May. 2024 – Oct. 2024
  
  Applied Scientist Intern at AWS AI Computer Vision
  - I work on LLM-based agent for GUI navigation tasks.
• University of California, Los Angeles, USA
  Aug. 2023 – Jul. 2024
  
  Visiting Scholar at Stan's Group
  - I work with Prof. Stanley Osher on joint diffusion model and medical image registration.
• Microsoft Research, Cambridge, UK
  Jun. 2021 – Aug. 2021
  
  Research Intern at Healthcare Intelligence Group
  - I work with Dr. Ozan Oktay on joint multi-modality self-supervised learning for chest radiology applications.
• University of Cambridge, UK
  Feb. 2020 – Jul. 2020
  
  Visiting Student at Cambridge Image Anaylsis Group (CIA)
  - Designed a registration-based unsupervised segmentation architecture for brain images.
• Imsight Technology, Shenzhen, China
  Aug. 2017 – Oct. 2017
  
  Research Intern at AI for Imaging Group
  - Deployed the AI-based lung nodule analysis software to multiple hospitals in Beijing for clinical usage.
• The Chinese University of Hong Kong, Hong Kong
  Feb. 2017 – Jul. 2017
  
  Junior Research Assistant at Medical Imaging Lab (CUMed)
  - Developed a DeepLung software which integrated the deep learning based lung nodule analysis algorithms into ITK-SNAP.

Honors & Awards

• Cody Award, University of Cambridge, 2024

• BMVC Doctoral Consortium with Travel Award, Aberdeen, 2023

• University Travel Award, University of Cambridge, 2023

• Oracle Ph.D. Project Award, Oracle, 2023

• ICIAM FS1 Award, Tokyo, 2023

• Rouse Ball Award, University of Cambridge, 2023

• NoMADS Travel Award for UCLA Visting Graduate Researcher, NoMADS, 2023

• Merit NVIDIA Paper Award, MIUA, 2022

• Smith-Knight and Rayleigh-Knight Essay Prizes, University of Cambridge, 2022

• Ranking 4/373 in the Grand Challenge CoNIC, 2022

• GSK Ph.D. Fellowship, GlaxoSmithKline (GSK), 2020

• Girton College - Graduate Research Scholarship, University of Cambridge, 2020

• CUHK M.Phil. Student Scholarship, The Chinese University of Hong Kong, 2017

• Outstanding Student Award, Chongqing University, 2016

• Qiu Shi Scholarship, Chongqing University, 2014

Professional Activities

• Invited Talks:
  - SIAM Conference on Imaging Science, “Contrastive Registration for Unsupervised Image Segmentation”, March 2022.
  - Chongqing University, “How Registration can Help to Segment Medical Images without Ground Truths?”, November 2021.
  - Microsoft Research, “Multi-modal Contrastive Representation Learning for Chest X-ray Diagnosis.”, August 2021.
  - East China Normal University, "Deep Learning Application in Medical Image Anaylsis", November 2020.
  

• Memberships:
  MICCAI Student, IEEE Student

• Paper Reviews:
  MICCAI, TMI, MIA, CVPR, ICCV, ECCV, and IJCV

• Teaching Assistant:
  

  - 2019-2020	Spring	CSCI2100 Data Structures
  - 2018-2019	Fall	CSCI3160 Design and Analysis of Algorithms
  - 2017-2018	Fall	CSCI3160 Design and Analysis of Algorithms

• Volunteer Experience:
  - I am an in-person volunteer in GeoMedIA'22 workshop, and ICCV'23.
  - I am the webpage manager and event in-person volunteer in MIUA'22 conference and Women in MIUA workshop.