mlsanityData to 14 Oct 2026

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks

arXiv 2504.19854 ↗First posted 28 Apr 2025cs.RO cs.AI cs.CVcited by 127

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

Existing Visual-Language-Action (VLA) models have shown promising performance in zero-shot scenarios, demonstrating impressive task execution and reasoning capabilities. However, a significant challenge arises from the limitations of visual encoding, which can result in failures during tasks such as object grasping. Moreover, these models typically suffer from high computational overhead due to their large sizes, often exceeding 7B parameters. While these models excel in reasoning and task planning, the substantial computational overhead they incur makes them impractical for real-time robotic environments, where speed and efficiency are paramount. To address the limitations of existing VLA models, we propose NORA, a 3B-parameter model designed to reduce computational overhead while maintaining strong task performance. NORA adopts the Qwen-2.5-VL-3B multimodal model as its backbone, leveraging its superior visual-semantic understanding to enhance visual reasoning and action grounding. Additionally, our model is trained on 970k real-world robot demonstrations and equipped with the FAST+ tokenizer for efficient action sequence generation. Experimental results demonstrate that NORA outperforms existing large-scale VLA models, achieving better task performance with significantly reduced computational overhead, making it a more practical solution for real-time robotic autonomy.

Key facts. Cited by 127 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 23 of its 25 references that are in the map. First posted on arXiv 28 Apr 2025.

Builds on

23 of 25 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar
  2. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  3. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul

Other references · 20

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  11. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  12. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
8 more
  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  2. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  3. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  4. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  5. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  6. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 304
  7. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
  8. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 250

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 33; 2026: 94.

127 papers.

Sort:

By area:

  1. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 303
  2. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 260
  3. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 197
  4. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 151
  5. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 145
  6. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 103
  7. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  8. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 74
  9. 2025RynnVLA-002: A Unified Vision-Language-Action and World Modelcited by 74
  10. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
  11. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 69
  12. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 50
38 more
  1. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 49
  2. 2026Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agentscited by 47
  3. 2025BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulationcited by 43
  4. 2025The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruningcited by 36
  5. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 36
  6. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 35
  7. 2025Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulationcited by 34
  8. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  9. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelscited by 33
  10. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systemscited by 31
  11. 2026ABot-M0.5: Unified Mobility-and-Manipulation World Action Modelcited by 30
  12. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 28
  13. 2025SRPO: Self-Referential Policy Optimization for Vision-Language-Action Modelscited by 27
  14. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 26
  15. 2025NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewardscited by 26
  16. 2025AVA-VLA: Improving Vision-Language-Action models with Active Visual Attentioncited by 25
  17. 2026AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Modelscited by 23
  18. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 18
  19. 2025Contrastive Representation Regularization for Vision-Language-Action Modelscited by 17
  20. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 16
  21. 2025dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoningcited by 14
  22. 2026Stable Language Guidance for Vision-Language-Action Modelscited by 14
  23. 2026On-the-Fly VLA Adaptation via Test-Time Reinforcement Learningcited by 14
  24. 2025Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresightcited by 13
  25. 2026Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuningcited by 13
  26. 2026VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillationcited by 13
  27. 2025Confidence Calibration in Vision-Language-Action Modelscited by 12
  28. 2025Expertise need not monopolize: Action-Specialized Mixture of Experts for Vision-Language-Action Learningcited by 12
  29. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  30. 2026Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflectioncited by 11
  31. 2026GeoSem-WAM: Geometry- and Semantic-Aware World Action Modelscited by 11
  32. 2026Geometric Action Model for Robot Policy Learningcited by 11
  33. 2026Flex-π: A Multi-Stream World-Action Model with Compute Flexibilitycited by 11
  34. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  35. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulationcited by 10
  36. 2026GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specializationcited by 10
  37. 2026MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Modelscited by 10
  38. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baselinecited by 9

50 most cited of 127 All 127 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
  2. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  3. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
  4. 2026CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts
  5. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
  6. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
  7. 2025OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction
  8. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks