HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
Paper • 2606.13289 • Published • 29
zliang
youliang1233214
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 27 days ago
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers upvoted a paper about 2 months ago
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context liked a dataset 5 months ago
JackAILab/OpenUniOrganizations
None yet
upvoted a paper 27 days ago
upvoted a paper about 2 months ago
liked a
dataset 5 months ago
updated 2
models 5 months ago
authored 5
papers 5 months ago
SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation
Paper • 2507.09862 • Published • 52
UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
Paper • 2511.03334 • Published • 54
Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy
Paper • 2511.21579 • Published • 23
StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars
Paper • 2512.22065 • Published
Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars
Paper • 2602.01538 • Published • 15
updated a
model 5 months ago
commented a
paper 5 months ago
published a
model 5 months ago
updated a
model 5 months ago
upvoted a paper 5 months ago
published 2
models 5 months ago
liked a
model 5 months ago
updated a
model 5 months ago
published a
model 5 months ago