mlsanityData to 14 Oct 2026

VLA-0: Building State-of-the-Art VLAs with Zero Modification

arXiv 2510.13054 ↗First posted 15 Oct 2025cs.RO cs.AIcited by 49

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

Abstract (arXiv)

Vision-Language-Action models (VLAs) hold immense promise for enabling generalist robot manipulation. However, the best way to build them remains an open question. Current approaches often add complexity, such as modifying the existing vocabulary of a Vision-Language Model (VLM) with action tokens or introducing special action heads. Curiously, the simplest strategy of representing actions directly as text has remained largely unexplored. This work introduces VLA-0 to investigate this idea. We find that VLA-0 is not only effective; it is surprisingly powerful. With the right design, VLA-0 outperforms more involved models. On LIBERO, a popular benchmark for evaluating VLAs, VLA-0 outperforms all existing methods trained on the same robotic data, including π0.5-KI, OpenVLA-OFT and SmolVLA. Furthermore, without large-scale robotics-specific training, it outperforms methods trained on large-scale robotic data, like π0.5-KI, π0, GR00T-N1 and MolmoAct. These findings also translate to the real world, where VLA-0 outperforms SmolVLA, a VLA model pre-trained on large-scale real data. This paper summarizes our unexpected findings and spells out the specific techniques required to unlock the high performance of this simple yet potent VLA design. Visual results, code, and trained models are provided here: https://vla0.github.io/.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 22 of its 24 references that are in the map. First posted on arXiv 15 Oct 2025.

Builds on

22 of 24 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  2. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better29 May
  3. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  4. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  5. 2025HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation8 Feb
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 14

  1. 2024Qwen2.5 Technical Reportcited by 4,942
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  6. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  7. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  8. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 225
  9. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 197
  10. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 138
  11. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 137
  12. 2024LLARVA: Vision-Action Instruction Tuning Enhances Robot Learningcited by 87
2 more
  1. 2025ManiFlow: A General Robot Manipulation Policy via Consistency Flow Trainingcited by 49
  2. 2025OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Modelcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 45.

49 papers.

Sort:

By area:

  1. 2026ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queriescited by 29
  2. 2026A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulationcited by 22
  3. 2026Show-Harness: Just a VLM Agent Can Play Robotscited by 20
  4. 2025StereoVLA: Enhancing Vision-Language-Action Models with Stereo Visioncited by 18
  5. 2026LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfercited by 18
  6. 2026ActionCodec: What Makes for Good Action Tokenizerscited by 18
  7. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 18
  8. 2025AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Modelscited by 17
  9. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 16
  10. 2026VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Modelscited by 14
  11. 2026World-Value-Action Model: Implicit Planning for Vision-Language-Action Systemscited by 14
  12. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
37 more
  1. 2026Flex-π: A Multi-Stream World-Action Model with Compute Flexibilitycited by 11
  2. 2026HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensingcited by 10
  3. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
  4. 2026Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategiescited by 9
  5. 2026Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVRcited by 8
  6. 2025Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-trainingcited by 7
  7. 2026PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policiescited by 7
  8. 2026One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policycited by 6
  9. 2026Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignmentcited by 6
  10. 2026UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Modelscited by 5
  11. 2026VLCP: Vision Language Control Policy Closed-Loop Code Replanning for Robot Manipulationcited by 5
  12. 2026Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Modelcited by 4
  13. 2026Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Modelscited by 4
  14. 2026ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Modelscited by 3
  15. 2026Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulationcited by 2
  16. 2026Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generationcited by 2
  17. 2026ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinementcited by 2
  18. 2025Look, Zoom, Understand: The Robotic Eyeball for Embodied Perceptioncited by 1
  19. 2026CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchorscited by 1
  20. 2026Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?cited by 1
  21. 2026TBD-VLA: Temporal Block Diffusion Vision Language Action Modelcited by 1
  22. 2026Decoupling the Declarative from the Procedural in Vision-Language-Action Modelscited by 1
  23. 2026Flatness Preserves Instruction Following in Vision-Language-Action Modelscited by 1
  24. 2026When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agentscited by 1
  25. 2026SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Modelscited by 1
  26. 2026ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Modelscited by 1
  27. 2026Trajectory-Level Redirection Attacks on Vision-Language-Action Modelscited by 0
  28. 2026Encoder Winners Do Not Reliably Transfer Across VLA Backbone Scale: A Frozen-Backbone Grafting Diagnosticcited by 0
  29. 2026UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modelingcited by 0
  30. 2026CLAP: Direct VLM-to-VLA Adaptation via Language-Action Groundingcited by 0
  31. 2026Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classificationcited by 0
  32. 2026Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Testscited by 0
  33. 2026WorldDiT: A Unified Diffusion Architecture for World and Action Modelingcited by 0
  34. 2026CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Modelcited by 0
  35. 2026AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policiescited by 0
  36. 2026Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matchingcited by 0
  37. 2026Rho: A Foundation for Efficiently Adaptable VLA Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  2. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots
  3. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  4. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  5. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  6. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
  7. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
  8. 2026VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models