Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
Paper • 2610.36671 • Published • 117
jeong
jaeseok
AI & ML interests
computer vision, image editing, generative models, diffusion models
Recent Activity
upvoted a paper 11 days ago
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs authored a paper 14 days ago
Visual Style Prompting with Swapping Self-Attention authored a paper 14 days ago
TTS-CtrlNet: Time varying emotion aligned text-to-speech generation with
ControlNetOrganizations
None yet
upvoted a paper 11 days ago
authored 3
papers 14 days ago
Visual Style Prompting with Swapping Self-Attention
Paper • 2402.12974 • Published
TTS-CtrlNet: Time varying emotion aligned text-to-speech generation with ControlNet
Paper • 2507.04349 • Published
StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance
Paper • 2510.06827 • Published
authored a
paper 15 days ago
upvoted a paper about 1 year ago
upvoted a paper over 1 year ago
liked a
Space over 2 years ago
updated 2
Spaces almost 4 years ago