mlsanityData to 7 Oct 2026

LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model

arXiv 2603.01068 ↗First posted 1 Mar 2026cs.CV cs.LGcited by 8

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

We present LLaDA-o, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, while coupling them through a shared, simple, and efficient attention backbone that reduces redundant computation for fixed conditions. Building on MoD, we further introduce a data-centric length adaptation strategy that enables flexible-length decoding in multimodal settings without architectural changes. Extensive experiments show that LLaDA-o achieves state-of-the-art performance among omni-diffusion models on multimodal understanding and generation benchmarks, and reaches 87.04 on DPG-Bench for text-to-image generation, supporting the effectiveness of unified omni diffusion modeling. Code is available at https://github.com/ML-GSAI/LLaDA-o.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 78 of its 86 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

78 of 86 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding7 Oct
  2. 2025Show-o2: Improved Native Unified Multimodal Models18 Jun
  3. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning22 May
  4. 2025MMaDA: Multimodal Large Diffusion Language Models21 May
  5. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset14 May
  6. 2025From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning22 Apr
  7. 2025Unified Multimodal Discrete Diffusion26 Mar
  8. 2024Dual Diffusion for Unified Image Generation and Understanding31 Dec
  9. 2024Emu3: Next-Token Prediction is All You Need27 Sep
  10. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment8 Mar
  11. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment17 Oct

Other references · 67

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  8. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  9. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  10. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  11. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  12. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
38 more
  1. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  2. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  3. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  4. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  5. 2025Qwen-Image Technical Reportcited by 973
  6. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 929
  7. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
  8. 2025Large Language Diffusion Modelscited by 872
  9. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  10. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  11. 2024Simple and Effective Masked Diffusion Language Modelscited by 800
  12. 2016A Diagram Is Worth A Dozen Imagescited by 793
  13. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 787
  14. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  15. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 712
  16. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 606
  17. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  18. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  19. 2025Dream 7B: Diffusion Large Language Modelscited by 515
  20. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 498
  21. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 468
  22. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 447
  23. 2021InfographicVQAcited by 430
  24. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 371
  25. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 326
  26. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 277
  27. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 273
  28. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 241
  29. 2025LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Trainingcited by 233
  30. 2025Mercury: Ultra-Fast Language Models Based on Diffusioncited by 225
  31. 2024MetaMorph: Multimodal Understanding and Generation via Instruction Tuningcited by 205
  32. 2025d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learningcited by 178
  33. 2025Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inferencecited by 173
  34. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100Bcited by 154
  35. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 151
  36. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 125
  37. 2025SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generationcited by 118
  38. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 108

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generationcited by 17
  2. 2026LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Modelcited by 12
  3. 2026Improved Large Language Diffusion Modelscited by 12
  4. 2026Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Modelscited by 1
  5. 2026Relative Score Policy Optimization for Diffusion Language Modelscited by 0
  6. 2026DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Modelscited by 0
  7. 2026PixelUMM: Encoder-Free Unified Image and Video Understanding and Generationcited by 0
  8. 2026Omni-Diffusion-Distill: Few-Step Distillation of Unified Multimodal Diffusion Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
  2. 2025Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
  3. 2026Dynin-Omni: Omnimodal Unified Large Diffusion Language Model
  4. 2026LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
  5. 2023Efficient Multimodal Diffusion Models Using Joint Data Infilling with Partially Shared U-Net
  6. 2025Decoder-Only LLMs are Better Controllers for Diffusion Models
  7. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
  8. 2026Efficient Token Pruning for LLaDA-V