# UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation

arXiv: https://arxiv.org/abs/2605.21611 · HTML: https://mlsanity.com/paper/2605.21611/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 34 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2410.13848/) (2024)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [ImgEdit: A Unified Image Editing Dataset and Benchmark](https://mlsanity.com/paper/2505.20275/) (2025)
- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion](https://mlsanity.com/paper/2403.06976/) (2024)
- [Scaling Up Models and Data with textttt5x and textttseqio](https://mlsanity.com/paper/2203.17189/) (2022)
- [DeepSeek-OCR: Contexts Optical Compression](https://mlsanity.com/paper/2510.18234/) (2025)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)

## Abstract (arXiv)

We introduce spatially grounded contextual image generation, a controllable image generation task that reframes the conditioning paradigm. Instead of supplying a reference image and a global text prompt through two separate encoders, one for vision and one for language, UniVL is trained to bind semantics to spatial locations directly from a single unified visual input, where the textual instruction is rendered onto the spatial mask. This removes the need for a standalone text encoder at inference time. The resulting model supports contextual image generation by following user-specified instructions about what should appear where, while substantially reducing computation. To address this task, we propose a framework in which the UniVL encoder, adapted from an optical-character-recognition-pretrained backbone, reads the unified condition optically and produces a UniVL embedding, fVIL, that fuses visual and semantic intent with spatial locations in a single token sequence. A two-stage pipeline first aligns UniVL with the VAE embedding space and then conditions a pretrained diffusion backbone entirely on UniVL embeddings, eliminating the standalone text encoder, such as T5. Although this reframing uses a deliberately minimal text interface, it yields strong empirical gains. On UniVL-ImgGen, a benchmark of 477K mask-annotated images that we construct for training and evaluation, UniVL improves image quality over text-prompted baselines, reducing FID from 14 to 11 and increasing PSNR from 16 to 20. It also eliminates the text encoder entirely, reducing inference TFLOPs by up to 52% and runtime by up to 44%. Additional ablation studies validate the contributions of the proposed components, paving the way for efficient, spatially grounded image generation with a unified conditioning paradigm.