Our paper Object-AVEdit submitted to ICLR 2026

Excited to share that our paper “Object-AVEdit: An Object-level Audio-Visual Editing Model” has been submitted to ICLR 2026!

This work proposes a novel approach for audio-visual editing at the object level, building on extensive research of diffusion-based generation and editing techniques. I’m honored to contribute as co-first author alongside Youquan Fu.

Links:

• arXiv preprint
• Project Page

This research was conducted during my internship at GeWu-Lab, Renmin University of China, under the supervision of Prof. Di Hu.