mlsanityData to 7 Oct 2026

OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation

arXiv 2505.03912 ↗First posted 6 May 2025cs.RO cs.CVcited by 79

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

Dual-system VLA (Vision-Language-Action) architectures have become a hot topic in embodied intelligence research, but there is a lack of sufficient open-source work for further performance analysis and optimization. To address this problem, this paper will summarize and compare the structural designs of existing dual-system architectures, and conduct systematic empirical evaluations on the core design elements of existing dual-system architectures. Ultimately, it will provide a low-cost open-source model for further exploration. Of course, this project will continue to update with more experimental conclusions and open-source models with improved performance for everyone to choose from. Project page: https://openhelix-robot.github.io/.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 17 of its 23 references that are in the map. First posted on arXiv 6 May 2025.

Builds on

17 of 23 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  3. 2024A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM21 Oct
  4. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation10 Oct
  5. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers12 Sep

Other references · 12

  1. 2023Visual Instruction Tuningcited by 7,792
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  3. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  4. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  5. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  6. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  7. 2025Transfer between Modalities with MetaQueriescited by 231
  8. 2024Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulationcited by 38
  9. 2024From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Controlcited by 34
  10. 2023LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuningcited by 28
  11. 2024CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Predictioncited by 26
  12. 2025Dense Policy: Bidirectional Autoregressive Learning of Actionscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 36; 2026: 43.

79 papers.

Sort:

By area:

  1. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 149
  2. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  3. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 129
  4. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  5. 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Modelscited by 89
  6. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  7. 2025ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceivercited by 80
  8. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  9. 2025VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulatorscited by 65
  10. 2025WorldEval: World Model as Real-World Robot Policies Evaluatorcited by 64
  11. 2025ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledgecited by 49
  12. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
38 more
  1. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 48
  2. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  3. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 46
  4. 2026VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Modelcited by 39
  5. 2026VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Modelscited by 38
  6. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  7. 2026When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAscited by 27
  8. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 25
  9. 2026BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generationcited by 25
  10. 2025RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulationcited by 24
  11. 2025Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representationscited by 21
  12. 2026AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Modelscited by 21
  13. 2025Mixture of Horizons in Action Chunkingcited by 20
  14. 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Modelscited by 19
  15. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 17
  16. 2025Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policycited by 17
  17. 2026Towards Generalizable Robotic Manipulation in Dynamic Environmentscited by 17
  18. 2025RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Modelcited by 16
  19. 2025MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agentcited by 15
  20. 2025Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inferencecited by 14
  21. 2025Real-Time Reasoning Agents in Evolving Environmentscited by 13
  22. 2025RationalVLA: A Rational Vision-Language-Action Model with Dual Systemcited by 12
  23. 2025VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillationcited by 11
  24. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
  25. 2026HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulationcited by 10
  26. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baselinecited by 9
  27. 2026KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Modelscited by 9
  28. 2026Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performancecited by 9
  29. 2026AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Modelscited by 9
  30. 2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Compositioncited by 8
  31. 2026A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Modelcited by 8
  32. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  33. 2026AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edgecited by 7
  34. 2026RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulationcited by 7
  35. 2025HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworkscited by 6
  36. 2025Asynchronous Fast-Slow Vision-Language-Action Policies for Whole-Body Robotic Manipulationcited by 6
  37. 2026StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observationcited by 6
  38. 2026PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidancecited by 6

50 most cited of 79 All 79 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026OpenEAI-Platform: An Open-source Embodied Artificial Intelligence Hardware-Software Unified Platform ↗
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Model
  3. 2025Dexbotic: Open-Source Vision-Language-Action Toolbox
  4. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  5. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  6. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulation
  7. 2026A Pragmatic VLA Foundation Model
  8. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots