About Me

I am a Research Scientist at Canva CORE Research, working on computer vision and generative AI. My research broadly focuses on visual understanding and generation, particularly on how models understand, represent, and manipulate scenes and objects. My expertise includes generative image editing, image decomposition, amodal perception, structured visual representations, and controllable visual generation.

My work spans inference-time algorithms for visual understanding and generation, vision and generative models for downstream understanding and manipulation tasks, and the creation of high-quality structured visual data with supervision that is difficult or impossible to obtain from real-world data alone. This includes developing methods to improve the quality, controllability, and consistency of image generation and editing, building models for visual understanding and manipulation, and creating rich, structured visual supervision from natural images and fully controllable 3D environments. My research at Canva has contributed to multiple production capabilities and products.

I also actively collaborate with academic researchers on visual reasoning, multimodal learning, 3D/4D scene understanding and spatial intelligence, robot interaction, out-of-distribution detection, and visual reprogramming. I am open to research collaborations.

I received my PhD in Computer Vision from the University of Melbourne in 2025, supervised by Associate Professor Krista A. Ehinger and Dr Qiuhong Ke. My doctoral research focused on visual amodal completion, with an emphasis on understanding and reconstructing objects and scenes beyond directly visible image content.

📝 Publications

• Zizhao Li, Zhengkang Xiang, Jiayang Ao, Joseph West, Kourosh Khoshelham. Relative Energy Learning for LiDAR Out-of-Distribution Detection. ISPRS Journal of Photogrammetry and Remote Sensing 239, 334-346, 2026.
• Zizhao Li, Zhengkang Xiang, Jiayang Ao, Feng Liu, Joseph West, Kourosh Khoshelham. Neural Distribution Prior for LiDAR Out-of-Distribution Detection. 🌟CVPR Compute Gold Star. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026.
• Yunze Liu, Zifan Wang, Peiran Wu, Jiayang Ao. PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026.
• Lin Li, Youyang Qu, Jiayang Ao, Ming Ding, Chao Chen, Jun Zhang. Poster: The Art of Deception: Crafting Chimera Images for Covert and Robust Semantic Poisoning Attacks. In Proceedings of the ACM Conference on Computer and Communications Security (CCS) 2025.
• Yanbei Jiang, Yihao Ding, Chao Lei, Jiayang Ao, Jey Han Lau, Krista A. Ehinger. Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task. In Proceedings of the Association for Computational Linguistics (ACL) 2025 Findings.
• Jiayang Ao. Visual amodal completion. PhD thesis. 2025.
• Jiayang Ao, Yanbei Jiang, Qiuhong Ke, and Krista A Ehinger. Open-World Amodal Appearance Completion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025.
• Jiayang Ao, Qiuhong Ke, and Krista A Ehinger. Sequential Amodal Segmentation via Cumulative Occlusion Learning. In Proceedings of the 35th British Machine Vision Conference (BMVC), November 2024.
• Jiayang Ao, Qiuhong Ke, and Krista A. Ehinger. Amodal intra-class instance segmentation: Synthetic datasets and benchmark. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 281–290, January 2024.
• Jiayang Ao, Qiuhong Ke, and Krista A Ehinger. Image amodal completion: A survey. Computer Vision and Image Understanding, page 103661, 2023.

✍️ Manuscripts

• Jizhizi Li, Jiayang Ao, Danny Wicks, Petru-Daniel Tudosiu. SceneForge: Structured World Supervision from 3D Interventions . arXiv, 2026.
• Xueqi Ma, Shuo Yang, Yanbei Jiang, Shu Liu, Zhenzhen Liu, Jiayang Ao, Xingjun Ma, Sarah Monazam Erfani, James Bailey. Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning. arXiv, 2026.
• Hongxing Fan, Shuyu Zhao, Jiayang Ao, Lu Sheng. Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation. arXiv, 2025.

🔬 Professional Appointments

• Research Scientist, Canva CORE/Leonardo.Ai, 06/2025 - present
• Research Assistant (Postdoctoral), ArtCert, Faculty of Arts, University of Melbourne, 04/2025 – 06/2025

🏫 Teaching

• Lecturer & Course Developer, ISYS3466 Data-Driven Decision Making: Machine Learning for Business Professionals, the RMIT University, 07/2024- 12/2024
• Head tutor & Course Developer, COMP90086 Computer Vision, the University of Melbourne, 07/2021- 12/2024
• Head tutor, COMP90049 Introduction to Machine Learning, the University of Melbourne, 02/2022- 07/2024
• Head tutor, COMP30027 Machine Learning, the University of Melbourne, 02/2022- 06/2025

🏆 Scholarships, Awards & Funding

• [Jun 2025] CVPR Travel Support Award
• [Sep 2024] Human Annotation Fund, AI group, School of Computing and Information Systems, the University of Melbourne
• [Jan 2024] IEEE/CVF Winter Conference on Applications of Computer Vision Travel Grant
• [Nov 2023] Engineering and IT Conference Travel Scholarship
• [Nov 2023] Melbourne School of Engineering Travelling Scholarship (CIS)
• [Nov 2022] FEIT Excellence Award in Teaching and Learning for Tutors and Demonstrators
• [Aug 2021] Melbourne Research Scholarship (Fee offset and Allowance)
• [Jun 2019] Outstanding Graduates of Central South University
• [May 2018] Central China Hackathon Rank #2
• [May 2018] Innovation and Entrepreneurship Training Program for College Students, China National Projects
• [Jun 2017] China Top10 in ‘Her Startup’ Empowering Women Entrepreneurs Competition for College Students
• [Jan 2017] Interdisciplinary Contest In Modeling (Honorable Mention)

🏛️ SERVICES

Journal Reviewer

• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

  Conference Service

• Program Committee Member, AAAI Conference on Artificial Intelligence (AAAI)
• Reviewer, ACM Multimedia (MM)

  Outreach and Engagement

• Unimelb Open Day Demonstration 2024

🎓 Education

• 2021.10 - 2025.09, Doctor of Philosophy - Engineering and IT, The University of Melbourne
• 2019.07 - 2021.07, Master of Science (Computer Science) (with distinction), The University of Melbourne
• 2015.09 - 2019.06, Bachelor of Management (Information Management and Information Systems), Central South University