Jun Du

5

Papers

10

Total Citations

Papers (5)

A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition

Latent Swap Joint Diffusion for 2D Long-Form Latent Generation

DocMamba: Efficient Document Pre-training with State Space Model

EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion

RFL: Simplifying Chemical Structure Recognition with Ring-Free Language