InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
Paper
•
2412.09596
•
Published
•
88
lza
l1ziang
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
10 days ago
LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
Organizations
