mlsanityData to 14 Oct 2026

LLaDA-VLA: Vision Language Diffusion Action Models

arXiv 2509.06932 ↗First posted 8 Sep 2025cs.RO cs.CVcited by 30

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

also in 1 more
Abstract (arXiv)

The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive models, have begun to demonstrate competitive performance in text generation and multimodal applications, leading to the development of a series of diffusion-based VLMs (d-VLMs). However, leveraging such models for robot policy learning remains largely unexplored. In this work, we present LLaDA-VLA, the first Vision-Language-Diffusion-Action model built upon pretrained d-VLMs for robotic manipulation. To effectively adapt d-VLMs to robotic domain, we introduce two key designs: (1) a localized special-token classification strategy that replaces full-vocabulary classification with special action token classification, reducing adaptation difficulty; (2) a hierarchical action-structured decoding strategy that decodes action sequences hierarchically considering the dependencies within and across actions. Extensive experiments demonstrate that LLaDA-VLA significantly outperforms state-of-the-art VLAs on both simulation and real-world robots.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 59 of its 59 references that are in the map. First posted on arXiv 8 Sep 2025.

Builds on

59 of 59 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots18 Dec
  2. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul
  3. 2024LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning17 Jun
  4. 2023Vision-Language Foundation Models as Effective Robot Imitators2 Nov
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul
  6. 2023PaLM-E: An Embodied Multimodal Language Model6 Mar

Other references · 53

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  9. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  10. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  11. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  12. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
38 more
  1. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  2. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  3. 2025Large Language Diffusion Modelscited by 912
  4. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 862
  5. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  6. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
  7. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  8. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  9. 2023OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Modelscited by 565
  10. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  11. 2025Dream 7B: Diffusion Large Language Modelscited by 544
  12. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  13. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 495
  14. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 450
  15. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 422
  16. 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 407
  17. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 381
  18. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  19. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
  20. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 339
  21. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 285
  22. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  23. 2024Scaling Diffusion Language Models via Adaptation from Autoregressive Modelscited by 274
  24. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 269
  25. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 250
  26. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 225
  27. 2024RT-H: Action Hierarchies Using Languagecited by 210
  28. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 169
  29. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 148
  30. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 137
  31. 2021Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisationcited by 122
  32. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 113
  33. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  34. 2025LaViDa: A Large Diffusion Language Model for Multimodal Understandingcited by 84
  35. 2023TESS: Text-to-Text Self-Conditioned Simplex Diffusioncited by 65
  36. 2023Robot Learning with Sensorimotor Pre-trainingcited by 51
  37. 2023DINOISER: Diffused Conditional Sequence Learning by Manipulating Noisescited by 50
  38. 2025LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMscited by 40

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 22.

30 papers.

Sort:

By area:

  1. 2025Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Processcited by 39
  2. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thoughtcited by 30
  3. 2026Learning Native Continuation for Action Chunking Flow Policiescited by 19
  4. 2025Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbonecited by 18
  5. 2026DMax: Aggressive Parallel Decoding for dLLMscited by 18
  6. 2025AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Modelscited by 17
  7. 2025dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoningcited by 14
  8. 2026dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Modelcited by 13
  9. 2025Dexbotic: Open-Source Vision-Language-Action Toolboxcited by 12
  10. 2026DM0: An Embodied-Native Vision-Language-Action Model towards Physical AIcited by 12
  11. 2026LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Modelcited by 10
  12. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
18 more
  1. 2026Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performancecited by 9
  2. 2025Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Expertscited by 8
  3. 2026Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVRcited by 8
  4. 2025STORM: Search-Guided Generative World Models for Robotic Manipulationcited by 7
  5. 2026SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policiescited by 7
  6. 2026DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matchingcited by 5
  7. 2026MaDiS: Taming Masked Diffusion Language Models for Sign Language Generationcited by 4
  8. 2026DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executorscited by 4
  9. 2026ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Drivingcited by 3
  10. 2026BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuningcited by 3
  11. 2026TBD-VLA: Temporal Block Diffusion Vision Language Action Modelcited by 1
  12. 2026TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridgingcited by 0
  13. 2026WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLAcited by 0
  14. 2026Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Modelscited by 0
  15. 2026Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challengescited by 0
  16. 2026Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Modelcited by 0
  17. 2026KerColle: Unlocking Fine-Grained GPU Concurrency in Vision-Language-Action Modelscited by 0
  18. 2026Latent evolving World Action Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  2. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  3. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  4. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation
  5. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
  6. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
  7. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
  8. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review