mlsanityData to 7 Oct 2026

PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding

arXiv 2503.02310 ↗First posted 4 Mar 2025cs.RO cs.CVcited by 88

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

also in 1 more
Abstract (arXiv)

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control. However, action chunking linearly scales up action dimensions in VLA models with increased chunking sizes. This reduces the inference efficiency. To tackle this problem, we propose PD-VLA, the first parallel decoding framework for VLA models integrated with action chunking. Our framework reformulates autoregressive decoding as a nonlinear system solved by parallel fixed-point iterations. This approach preserves model performance with mathematical guarantees while significantly improving decoding speed. In addition, it enables training-free acceleration without architectural changes, as well as seamless synergy with existing acceleration techniques. Extensive simulations validate that our PD-VLA maintains competitive success rates while achieving 2.52 times execution frequency on manipulators (with 7 degrees of freedom) compared with the fundamental VLA model. Furthermore, we experimentally identify the most effective settings for acceleration. Finally, real-world experiments validate its high applicability across different tasks.

Key facts. Cited by 88 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 34 of its 47 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

34 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Models16 Jan
  2. 2024Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control2 Dec

Other references · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  4. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  8. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  9. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  10. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  11. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  12. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
20 more
  1. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  2. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  3. 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Modelscited by 629
  4. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  5. 2023OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Modelscited by 560
  6. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  7. 2024SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inferencecited by 378
  8. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  9. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 331
  10. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 173
  11. 2024Behavior Generation with Latent Actionscited by 159
  12. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillationcited by 159
  13. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 137
  14. 2023Accelerating Transformer Inference for Translation via Parallel Decodingcited by 123
  15. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Executioncited by 116
  16. 2024LLARVA: Vision-Action Instruction Tuning Enhances Robot Learningcited by 87
  17. 2024CLLMs: Consistency Large Language Modelscited by 71
  18. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robotscited by 55
  19. 2025VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulationcited by 48
  20. 2024GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robotcited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 30; 2026: 58.

88 papers.

Sort:

By area:

  1. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  2. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  3. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  4. 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Modelscited by 89
  5. 2025ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceivercited by 80
  6. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  7. 2025CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsificationcited by 70
  8. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  9. 2025VL-JEPA: Joint Embedding Predictive Architecture for Vision-languagecited by 61
  10. 2025SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Accelerationcited by 56
  11. 2025FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Modelscited by 50
  12. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
38 more
  1. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  2. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decodingcited by 38
  3. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Reviewcited by 38
  4. 2025Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Processcited by 37
  5. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  6. 2025Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptancecited by 31
  7. 2025Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Modelscited by 30
  8. 2025MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Modelscited by 27
  9. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 25
  10. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Modelscited by 24
  11. 2026QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantizationcited by 23
  12. 2025AVA-VLA: Improving Vision-Language-Action models with Active Visual Attentioncited by 22
  13. 2026AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Modelscited by 21
  14. 2025SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulationcited by 20
  15. 2026PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulationcited by 20
  16. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  17. 2026DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Modelscited by 20
  18. 2026Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulationcited by 19
  19. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  20. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 17
  21. 2026S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresightcited by 16
  22. 2026VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizoncited by 14
  23. 2025RationalVLA: A Rational Vision-Language-Action Model with Dual Systemcited by 12
  24. 2025MM-ACT: Learn from Multimodal Parallel Generation to Actcited by 12
  25. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulationcited by 10
  26. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
  27. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baselinecited by 9
  28. 2026DeltaVLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variationcited by 9
  29. 2026Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performancecited by 9
  30. 2026VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillationcited by 9
  31. 2025UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformercited by 8
  32. 2026DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulationcited by 8
  33. 2026CORAL: Scalable Multi-Task Robot Learning via LoRA Expertscited by 8
  34. 2026Point Tracking Improves World Action Modelscited by 7
  35. 2025HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworkscited by 6
  36. 2026StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observationcited by 6
  37. 2026ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulationcited by 6
  38. 2026TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Controlcited by 5

50 most cited of 88 All 88 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference
  2. 2025FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
  3. 2026A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model
  4. 2026ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning
  5. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  6. 2025VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots
  7. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  8. 2025VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation