mlsanityData to 7 Oct 2026

MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation

arXiv 2603.25406 ↗First posted 26 Mar 2026cs.ROcited by 10

On the map: Vision-language-action models → Efficient VLA inference and adaptation

Abstract (arXiv)

Vision-Language-Action (VLA) models map visual observations and natural-language instructions to robot actions; however, hierarchical and autoregressive paradigms often incur architectural overhead, accumulate long-horizon errors, and require auxiliary modules to capture environment dynamics. To this end, we present MMaDA-VLA, a fully native, pretrained discrete diffusion VLA that unifies multi-modal understanding and generation. Specifically, MMaDA-VLA uses a shared discrete token space to jointly denoise a future goal observation and an action chunk, grounding actions in predicted visual outcomes without an auxiliary world model. In this way, parallel, order-free refinement improves long-horizon consistency. Extensive experiments and comprehensive analyses demonstrate that MMaDA-VLA achieves an average success rate of 98.0% on LIBERO and an average successful sequence length of 4.78 on CALVIN, while performing strongly in real-world settings. The project page is available at https://yliu-cs.github.io/MMaDA-VLA.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models. Builds on 95 of its 109 references that are in the map. First posted on arXiv 26 Mar 2026.

Builds on

95 of 109 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process3 Nov
  2. 2025OmniSAT: Compact Action Token, Faster Auto Regression8 Oct
  3. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies27 Aug
  4. 2025VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers1 Jul
  5. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding16 Jun
  6. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding4 Mar
  7. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Models16 Jan
  8. 2024Diffusion Transformer Policy21 Oct

Other references · 87

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  7. 2023Qwen Technical Reportcited by 3,273
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  9. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  10. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  11. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  12. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
38 more
  1. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  2. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  3. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  4. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  5. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  6. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  7. 2025Large Language Diffusion Modelscited by 872
  8. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  9. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  10. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  11. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  12. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  13. 2024Genie: Generative Interactive Environmentscited by 706
  14. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  15. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  16. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  17. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  18. 2025Dream 7B: Diffusion Large Language Modelscited by 515
  19. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  20. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  21. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  22. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 399
  23. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  24. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  25. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  26. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  27. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  28. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 273
  29. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  30. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 241
  31. 2022Interactive Language: Talking to Robots in Real Timecited by 217
  32. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  33. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 202
  34. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 183
  35. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 168
  36. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 159
  37. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  38. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 145

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026DMax: Aggressive Parallel Decoding for dLLMscited by 14
  2. 2026Human Cognition in Machines: A Unified Perspective of World Modelscited by 5
  3. 2026TACG: Trajectory-Aware Commit Gating for Diffusion Language Model Decodingcited by 2
  4. 2026dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Modelscited by 1
  5. 2026SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performancecited by 1
  6. 2026WorldDiT: A Unified Diffusion Architecture for World and Action Modelingcited by 0
  7. 2026WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLAcited by 0
  8. 2026Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challengescited by 0
  9. 2026Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Modelcited by 0
  10. 2026KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought
  2. 2025E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion
  3. 2025Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone
  4. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
  5. 2025Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
  6. 2026StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models
  7. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
  8. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control