antgroup/HumanSense_Omni_Reasoning
Video-Text-to-Text
•
9B
•
Updated
•
17
•
6
AI & ML interests
None defined yet.
Papers
Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
Update pipeline tag and add library name
1
#1 opened 2 months ago
by
nielsr
digital-avatar
updated
a
model
2 months ago
digital-avatar
updated
a
dataset
2 months ago
digital-avatar
published
a
dataset
2 months ago
digital-avatar
published
a
model
2 months ago
where is the metadata?
1
#2 opened 3 months ago
by
agent4bc