# SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design

arXiv: https://arxiv.org/abs/2506.07964 · HTML: https://mlsanity.com/paper/2506.07964/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [OpenAGI: When LLM Meets Domain Experts](https://mlsanity.com/paper/2304.04370/) (2023)
- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [Understanding SSIM](https://mlsanity.com/paper/2006.13846/) (2020)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [AutoPresent: Designing Structured Visuals from Scratch](https://mlsanity.com/paper/2501.00912/) (2025)
- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation](https://mlsanity.com/paper/2506.06251/) (2025)
- [MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems](https://mlsanity.com/paper/2404.09486/) (2024)
- [SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities](https://mlsanity.com/paper/2404.13710/) (2024)
- [MRWeb: An Exploration of Generating Multi-Page Resource-Aware Web Code from UI Designs](https://mlsanity.com/paper/2412.15310/) (2024)
- [CodeV: Issue Resolving with Visual Data](https://mlsanity.com/paper/2412.17315/) (2024)
- [DynEx: Dynamic Code Synthesis with Structured Design Exploration for Accelerated Exploratory Programming](https://mlsanity.com/paper/2410.00400/) (2024)

## Built on by (most cited first, 24 of 24)

- [Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning](https://mlsanity.com/paper/2601.11109/) (2026)
- [DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editing](https://mlsanity.com/paper/2602.13318/) (2026)
- [AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards](https://mlsanity.com/paper/2604.22840/) (2026)
- [SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics](https://mlsanity.com/paper/2601.09487/) (2026)
- [EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection](https://mlsanity.com/paper/2603.00155/) (2026)
- [Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety](https://mlsanity.com/paper/2509.21782/) (2025)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation](https://mlsanity.com/paper/2509.12159/) (2025)
- [Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation](https://mlsanity.com/paper/2605.26451/) (2026)
- [Paper2Web: Let's Make Your Paper Alive!](https://mlsanity.com/paper/2510.15842/) (2025)
- [TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework](https://mlsanity.com/paper/2510.17163/) (2025)
- [VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection](https://mlsanity.com/paper/2605.09461/) (2026)
- [Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards](https://mlsanity.com/paper/2607.04727/) (2026)
- [PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs](https://mlsanity.com/paper/2608.02218/) (2026)
- [PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides](https://mlsanity.com/paper/2609.29718/) (2026)
- [Semantic-aware Graph-guided Behavior Sequences Generation with Large Language Models for Smart Homes](https://mlsanity.com/paper/2508.03484/) (2025)
- [DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization](https://mlsanity.com/paper/2605.11015/) (2026)
- [X+Slides: Benchmarking Audience-Conditioned Slide Generation](https://mlsanity.com/paper/2606.19256/) (2026)
- [Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising](https://mlsanity.com/paper/2607.00407/) (2026)
- [CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding](https://mlsanity.com/paper/2607.29637/) (2026)
- [ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation](https://mlsanity.com/paper/2608.24103/) (2026)
- [SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts](https://mlsanity.com/paper/2609.03109/) (2026)
- [SlideLab: Audience-Centered Scientific Slide Generation and Evaluation](https://mlsanity.com/paper/2609.30294/) (2026)
- [InfoAgent: Traceable Generation and Repair of Evidence-Grounded Infographics](https://mlsanity.com/paper/2609.39380/) (2026)

## Abstract (arXiv)

Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural nuances of slide designs. To address this, we formalize the Reference Image to Slide Generation task and propose Slide2Code, the first benchmark with difficulty-tiered samples based on a novel Slide Complexity Metric. We introduce SlideCoder, a layout-aware, retrieval-augmented framework for generating editable slides from reference images. SlideCoder integrates a Color Gradient-based Segmentation algorithm and a Hierarchical Retrieval-Augmented Generation method to decompose complex tasks and enhance code generation. We also release SlideMaster, a 7B open-source model fine-tuned with improved reverse-engineered data. Experiments show that SlideCoder outperforms state-of-the-art baselines by up to 40.5 points, demonstrating strong performance across layout fidelity, execution accuracy, and visual consistency. Our code is available at https://github.com/vinsontang1/SlideCoder.