Dense Slides: From Mixture of Experts to Mixture of Agents with Super Fast Inference - Daniel Kim & Daria Soboleva
Source Video
From Mixture of Experts to Mixture of Agents with Super Fast Inference - Daniel Kim & Daria Soboleva
Method
This deck is slide-only. The existing captured video frame set supplies candidate frames, then local OpenCV rejects sponsor/title/speaker-only frames, crops visible slide surfaces, deduplicates, and saves the cropped slide images.
Cropped Visible Slides
- Source scene image:
frame-00004.jpg - Crop:
visible-slide-crop[0, 37, 960, 503]score176.17 - Slide-only rule:
visual-bright-slide
- Source scene image:
frame-00005.jpg - Crop:
visible-slide-crop[0, 37, 960, 503]score177.61 - Slide-only rule:
visual-bright-slide
- Source scene image:
frame-00009.jpg - Crop:
visible-slide-crop[0, 37, 960, 503]score176.4 - Slide-only rule:
visual-bright-slide
- Source scene image:
frame-00052.jpg - Crop:
visible-slide-crop[0, 37, 960, 503]score176.01 - Slide-only rule:
visual-bright-slide
- Source scene image:
frame-00077.jpg - Crop:
visible-slide-crop[0, 37, 960, 503]score176.18 - Slide-only rule:
visual-bright-slide