Jianzong Wu

6

Papers

46

Total Citations

Papers (6)

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

DreamRelation: Bridging Customization and Relation Generation

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language

Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation