# AI-Generated Lecture Slides for Improving Slide Element Detection and Retrieval

arXiv: https://arxiv.org/abs/2506.23605 · HTML: https://mlsanity.com/paper/2506.23605/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval](https://mlsanity.com/paper/1906.04402/) (2019)
- [End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems](https://mlsanity.com/paper/2010.06028/) (2020)
- [Vision Grid Transformer for Document Layout Analysis](https://mlsanity.com/paper/2308.14978/) (2023)
- [Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images](https://mlsanity.com/paper/2405.20469/) (2024)
- [Fact-Enhanced Synthetic News Generation](https://mlsanity.com/paper/2012.04778/) (2020)
- [What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning](https://mlsanity.com/paper/1811.12181/) (2018)
- [Diffusion-based Document Layout Generation](https://mlsanity.com/paper/2303.10787/) (2023)
- [Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images](https://mlsanity.com/paper/2312.02253/) (2023)
- [Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides](https://mlsanity.com/paper/2208.08080/) (2022)
- [Large-Scale Query-by-Image Video Retrieval Using Bloom Filters](https://mlsanity.com/paper/1604.07939/) (2016)
- [Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data](https://mlsanity.com/paper/2407.12669/) (2024)
- [Classroom Slide Narration System](https://mlsanity.com/paper/2201.08574/) (2022)

## Abstract (arXiv)

Lecture slide element detection and retrieval are key problems in slide understanding. Training effective models for these tasks often depends on extensive manual annotation. However, annotating large volumes of lecture slides for supervised training is labor intensive and requires domain expertise. To address this, we propose a large language model (LLM)-guided synthetic lecture slide generation pipeline, SynLecSlideGen, which produces high-quality, coherent and realistic slides. We also create an evaluation benchmark, namely RealSlide by manually annotating 1,050 real lecture slides. To assess the utility of our synthetic slides, we perform few-shot transfer learning on real data using models pre-trained on them. Experimental results show that few-shot transfer learning with pretraining on synthetic slides significantly improves performance compared to training only on real data. This demonstrates that synthetic data can effectively compensate for limited labeled lecture slides. The code and resources of our work are publicly available on our project website: https://synslidegen.github.io/.