# Representation-driven Endoscopic Visual Embedding Alignment for Latent Generation

arXiv: https://arxiv.org/abs/2608.07176 · HTML: https://mlsanity.com/paper/2608.07176/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers](https://mlsanity.com/paper/2504.10483/) (2025)
- [What matters for Representation Alignment: Global Information or Spatial Structure?](https://mlsanity.com/paper/2512.10794/) (2025)
- [Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train](https://mlsanity.com/paper/2306.16741/) (2023)
- [Endora: Video Generation Models as Endoscopy Simulators](https://mlsanity.com/paper/2403.11050/) (2024)
- [Smoothness and Stability in GANs](https://mlsanity.com/paper/2002.04185/) (2020)
- [MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss](https://mlsanity.com/paper/2508.05772/) (2025)
- [Gradpaint: Gradient-Guided Inpainting with Diffusion Models](https://mlsanity.com/paper/2309.09614/) (2023)
- [Mask-conditioned latent diffusion for generating gastrointestinal polyp images](https://mlsanity.com/paper/2304.05233/) (2023)
- [LanPaint: Training-Free Diffusion Inpainting with Asymptotically Exact and Fast Conditional Sampling](https://mlsanity.com/paper/2502.03491/) (2025)
- [EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training](https://mlsanity.com/paper/2502.19090/) (2025)
- [This Intestine Does Not Exist: Multiscale Residual Variational Autoencoder for Realistic Wireless Capsule Endoscopy Image Generation](https://mlsanity.com/paper/2302.02150/) (2023)
- [Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion](https://mlsanity.com/paper/2501.16679/) (2025)
- [Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free](https://mlsanity.com/paper/2502.03687/) (2025)
- [Polyp-DDPM: Diffusion-Based Semantic Polyp Synthesis for Enhanced Segmentation](https://mlsanity.com/paper/2402.04031/) (2024)
- [Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models](https://mlsanity.com/paper/2506.10634/) (2025)
- [MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow Matching](https://mlsanity.com/paper/2507.19098/) (2025)
- [Multiscale Vector-Quantized Variational Autoencoder for Endoscopic Image Synthesis](https://mlsanity.com/paper/2511.19578/) (2025)

## Abstract (arXiv)

Developing foundation generative models for endoscopy is limited by the gap between natural and clinical images and the computational cost of training large Diffusion Transformers. Although representation alignment has improved efficiency in general computer vision, its role within the highly specialized endoscopic image space remains unclear. We introduce REVEAL (Representation-driven Endoscopic Visual Embedding Alignment), the largest generative foundation model for endoscopy to date, trained on GastroNet-5M (GN-5M), a multicenter dataset of 5 million endoscopic frames. Instead of depending on out-of-domain priors, REVEAL employs encoders pretrained directly on the endoscopic distribution to align diffusion latents with domain-specific visual features, preserving fine textures and intricate anatomical structures. Beyond image generation, REVEAL also serves as a powerful feature extractor; in multiple benchmarks, it delivers performance that is competitive with, and in several cases exceeds, endoscopic foundation models such as EndoViT and Endo-FM, specifically tuned for classification tasks, while demonstrating strong representation robustness under realistic imaging corruptions. REVEAL produces high-fidelity images and maintains robust structural coherence in latent-space edits such as inpainting and outpainting. This high-capacity backbone lowers the computational threshold for building specialized clinical tools, offering an open, versatile foundation for conditional synthesis, segmentation, and out-of-distribution detection in future intelligent gastroenterology systems.