Running
README
⚡
Computer Vision
RIVER: A Real-Time Interaction Benchmark for Video LLMs
InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision
Display web content in a Streamlit app
Hierarchical Compression for Long-Context Video Modeling
Chat with AI using text and images, get instant analysis
Submit and view model evaluation results in a leaderboard format
Upload a video to chat about its contents
Display maintenance message
Identify actions and objects in videos and images
Display a web page in an iframe