Patsorn Sangkloy
Patsorn is a researcher in Computer Vision/Machine Learning, currently working on something exciting!
See my Google Scholar page for publications
Patsorn recieved her PhD in Computer Science from Georgia Institute of Technology, advised by James Hays. She also received her Master degree in Computer Science from Brown University. In 2025, she was doing research at NYU's Immersive Computing Lab as a postdoctoral researcher with Qi Sun.
During her PhD, she did several summer internships at Adobe Research with Jingwan (Cynthia) Lu, and at Argo AI with James Hays. Her work at Adobe (Project Scribbler) led to a patent and was also showcased at Adobe Max 2017. At Argo AI, she co-led the release of the first Argoverse dataset for perception and prediction task in driving scenes.
Her research interests are in computer vision/machine learning, including sketch understanding, image retrieval/synthesis/editing.
She is a recipient of Adobe Research Fellowship award, and Royal Thai Government Scholarship.
News
| 2026.03 | Our paper submission: Cost-Aware Routing for Efficient Text-To-Image Generation has been accepted at TMLR 2026 | |
| 2025.11 | Our paper submission: GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts has been accepted at WACV 2026 | |
| 2024.09 | Organized Women in Computer Vision Workshop at ECCV 2024 in Milan, Italy. | |
| 2024.01 | Invited talk on the topic of Image Generation at Chulalongkorn Business School | |
| 2024.01 | Received Fundamental Fund research grant from Thailand Science Reseach And Innovation | |
| 2023.10 | Organized Women in Computer Vision Workshop at ICCV 2023 in Paris, France. | |
| 2023.08 | Organized the 2nd Machine Learning Research School in Bangkok, Thailand. | |
| 2023.05 | Our paper submission: StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer has been accepted at CVPR 2023 | |
| 2022.07 | Our paper submission: A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch has been accepted at ECCV 2022 |