Jianzong Wu

Latest

• Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation
• Vmoba: Mixture-of-block attention for video diffusion models
• Muddit: Liberating generation beyond text-to-image with a unified discrete diffusion model
• Decouple and track: Benchmarking and improving video diffusion transformers for motion transfer
• DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
• DreamRelation: Bridging Customization and Relation Generation
• Motionbooth: Motion-aware customized text-to-video generation
• Towards robust referring image segmentation
• Towards open vocabulary learning: A survey
• Towards language-driven video inpainting via multimodal large language models
• Betrayed by captions: Joint caption grounding and generation for open vocabulary instance segmentation