1 citations · 1 across the 6 of their papers we have counts for
7 papers
EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
Jiayi Song, Shijie Huang, Fangtai Wu +5
High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models remain constrained to resolutions below 1K due to quadratic at…
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
Bingnan Li, Haozhe Wang, Haozhong Xiong +5
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guida…
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
Fangtai Wu, Hailong Guo, Shijie Huang +7
Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number…
Patient-Level Multimodal Question Answering from Multi-Site Auscultation Recordings
Fan Wu, Tsai-Ning Wang, Nicolas Zumarraga +8
Auscultation is a vital diagnostic tool, yet its utility is often limited by subjective interpretation. While general-purpose Audio-Language Models (ALMs) excel in general domains,…
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Yubo Huang, Hailong Guo, Fangtai Wu +9
Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon dr…
DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generation
Fangtai Wu, Mushui Liu, Weijie He +2
The unified autoregressive (AR) model excels at multimodal understanding and generation. However, its full potential in the domain of customized image generation has yet to be full…
Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning
Mushui Liu, Fangtai Wu, Bozheng Li +3
Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited vi…