mlsanityData to 7 Oct 2026

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

arXiv 2604.20796 ↗First posted 22 Apr 2026cs.CVcited by 12

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

Abstract (arXiv)

We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its architecture combines a fully semantic discrete tokenizer, a MoE-based dLLM backbone, and a diffusion decoder. By discretizing continuous visual inputs via SigLIP-VQ, the model enables block-level masked diffusion for both text and vision inputs within the backbone, while the decoder reconstructs visual tokens into high-fidelity images. Inference efficiency is enhanced beyond parallel decoding through prefix-aware optimizations in the backbone and few-step distillation in the decoder. Supported by carefully curated large-scale data and a tailored multi-stage training pipeline, LLaDA2.0-Uni matches specialized VLMs in multimodal understanding while delivering strong performance in image generation and editing. Its native support for interleaved generation and reasoning establishes a promising and scalable paradigm for next-generation unified foundation models. Codes and models are available at https://github.com/inclusionAI/LLaDA2.0-Uni.

Key facts. Cited by 12 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 89 of its 101 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

89 of 101 references.

Closest ancestors · 11

Same direction, newest first

  1. 2026LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model1 Mar
  2. 2025EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing12 Dec
  3. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding7 Oct
  4. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space17 Jun
  5. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning22 May
  6. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understanding22 May
  7. 2025MMaDA: Multimodal Large Diffusion Language Models21 May
  8. 2024OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision11 Nov
  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 · 78

  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  5. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  6. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  7. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  8. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  9. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,582
  10. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  11. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  12. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
38 more
  1. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  2. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  3. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  4. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  5. 2016Modeling Context in Referring Expressionscited by 1,054
  6. 2025Qwen-Image Technical Reportcited by 973
  7. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 893
  8. 2025Large Language Diffusion Modelscited by 872
  9. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  10. 2024Simple and Effective Masked Diffusion Language Modelscited by 800
  11. 2016A Diagram Is Worth A Dozen Imagescited by 793
  12. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 712
  13. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  14. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 572
  15. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Datasetcited by 516
  16. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 494
  17. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
  18. 2023V*: Guided Visual Search as a Core Mechanism in Multimodal LLMscited by 459
  19. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 447
  20. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 417
  21. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 385
  22. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?cited by 281
  23. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  24. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 247
  25. 2025LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Trainingcited by 233
  26. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 225
  27. 2025WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generationcited by 196
  28. 2023Teaching CLIP to Count to Tencited by 194
  29. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100Bcited by 154
  30. 2025Seedream 3.0 Technical Reportcited by 146
  31. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 139
  32. 2025HunyuanImage 3.0 Technical Reportcited by 138
  33. 2025PaddleOCR 3.0 Technical Reportcited by 136
  34. 2024Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Contentcited by 132
  35. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 119
  36. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 108
  37. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 105
  38. 2025Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generationcited by 95

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 12.

12 papers.

  1. 2026Toward Native Multimodal Modeling: A Roadmapcited by 6
  2. 2026Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to Systemcited by 2
  3. 2026Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Modelscited by 1
  4. 2026Relative Score Policy Optimization for Diffusion Language Modelscited by 0
  5. 2026FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generationcited by 0
  6. 2026Efficient Reinforcement for Visual-Textual Thinking with Discrete Diffusion Modelcited by 0
  7. 2026Representation Learning in Diffusion and Flow-based Model: An Application Aspectcited by 0
  8. 2026DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Modelscited by 0
  9. 2026Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Modelcited by 0
  10. 2026LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agentscited by 0
  11. 2026Self-correction Optimization for Interleaved Multimodal Generationcited by 0
  12. 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. 2026UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer
  2. 2025Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
  3. 2024Dual Diffusion for Unified Image Generation and Understanding
  4. 2026Efficient Token Pruning for LLaDA-V
  5. 2025MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
  6. 2025ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability
  7. 2024LMFusion: Adapting Pretrained Language Models for Multimodal Generation
  8. 2026Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models