Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator
Paper • 2604.08121 • Published • 36
GONG JIA
gong97
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator submitted a paper about 3 hours ago
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator upvoted a paper about 1 month ago
Beyond Language Modeling: An Exploration of Multimodal PretrainingOrganizations
None yet
submitted a
paper to Daily Papers about 3 hours ago
authored 5
papers 7 months ago
LLMs are Good Sign Language Translators
Paper • 2404.00925 • Published • 1
Omni-Video: Democratizing Unified Video Understanding and Generation
Paper • 2507.06119 • Published • 2
Distribution-Aligned Diffusion for Human Mesh Recovery
Paper • 2308.13369 • Published
Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision
Paper • 2508.05606 • Published
DiffPose: Toward More Reliable 3D Pose Estimation
Paper • 2211.16940 • Published