Research
For a more comprehensive view of my research interests and explorations, please visit my Academic Paper & Note Archive—a regularly updated collection of papers I’ve studied and research notes.
(* denotes equal contribution)
Follow-Your-Shape / EditAnyShape: Shape-Aware Image Editing via Trajectory-Guided Region Control
Controllable Generation Image Editing
HKUST & UIUC & SJTU
Zeqian Long*, Mingzhe Zheng*, Kunyu Feng*, Xinhua Zhang, Hongyu Liu, Harry Yang, Linfeng Zhang, Qifeng Chen, Yue Ma
The Fourteenth International Conference on Learning Representations (ICLR 2026) | arXiv | Github
Controllable Generation Image Editing
HKUST & UIUC & SJTU
Zeqian Long*, Mingzhe Zheng*, Kunyu Feng*, Xinhua Zhang, Hongyu Liu, Harry Yang, Linfeng Zhang, Qifeng Chen, Yue Ma
The Fourteenth International Conference on Learning Representations (ICLR 2026) | arXiv | Github
A training-free, mask-free image editing framework that can be applied to flow-based image generative models, enabling large-scale, precise, and flexible shape editing.