Diffusion Image Editing via Asynchronous Token Decoding
ACMMM 2026 (CCF-A)
Undergraduate Student, School of Computer Science
Guangdong University of Technology
Computer Vision
I am an undergraduate student at Guangdong University of Technology (expected 2027), focused on Computer Vision.
I approach visual AI through the lens of Spatial Intelligence—transforming chaotic generative spaces into structured, navigable environments. My research explores image editing, vision-language reasoning, and graph learning, investigating how transport dynamics and topological priors can make visual generation both highly controllable and logically dependable. I collaborate closely on these topics with Liangsi Lu.
Two papers were accepted to ACMMM 2026.
ChordEdit received the CVPR 2026 Best Student Paper Honorable Mention.
One paper was accepted to SIGKDD 2026.
One paper was accepted to ICML 2026.
One paper was accepted to ACL 2026 Main.
One paper was accepted to CVPR 2026.
One paper was accepted to WWW 2026.
Received funding from the National College Students' Innovation and Entrepreneurship Program.
* Equal contribution · † Corresponding author
ACMMM 2026 (CCF-A)
Awarded for paper: ChordEdit: One-Step Low-Energy Transport for Image Editing