---
title: "Reconstructed Slides: [Full Workshop] Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel Han"
category: "slides"
video_id: "OkEGJ5G3foU"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: [Full Workshop] Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel Han

## Source Video
[(Full Workshop) Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel Han](https://www.youtube.com/watch?v=OkEGJ5G3foU)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/OkEGJ5G3foU/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.13`
![[assets/reconstructed-slides/OkEGJ5G3foU/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.5`
![[assets/reconstructed-slides/OkEGJ5G3foU/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.66`
![[assets/reconstructed-slides/OkEGJ5G3foU/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.92`
![[assets/reconstructed-slides/OkEGJ5G3foU/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.9`
![[assets/reconstructed-slides/OkEGJ5G3foU/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `167.08`
![[assets/reconstructed-slides/OkEGJ5G3foU/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `163.19`
## Dense Scene-Detected Slide Candidates
- [[youtube-OkEGJ5G3foU-dense-slides]]