HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
Paper • 2606.13289 • Published • 30
Yufei Huang
Healthcliff-SAO
·
AI & ML interests
Generative Model, 3D Generation, Interactive Generation
I like to solve practical challenges through theoretic insights
Recent Activity
upvoted a paper about 2 months ago
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers liked a model over 1 year ago
stabilityai/stable-video-diffusion-img2vid-xt upvoted a paper over 1 year ago
AniDoc: Animation Creation Made EasierOrganizations
None yet
