mlsanityData to 7 Oct 2026

Scaling by Diversified Experience for Vision-Language-Action Models

arXiv 2606.09009 ↗First posted 8 Jun 2026cs.CVcited by 0

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

Abstract (arXiv)

Vision-Language-Action models face significant challenges in real-world deployment due to the entanglement of high-level reasoning with low-level control, and the instability of policy optimization. In this paper, we introduce SyVLA, a robust VLA model trained with diversified experiences. We propose an Intention Decoupling algorithm to isolate control-relevant features from reasoning contexts and a similar-sample guided RL pipeline to stabilize policy updates and mitigate distribution shift. Extensive experiments on real-world robotic tasks and multi-modal benchmarks demonstrate that SyVLA achieves superior task success rates and stronger out-of-distribution generalization compared to existing methods, while effectively preserving core vision-language capabilities. Codes and Datasets is released on hrefhttps://sy-vla.github.io/project page.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 37 of its 44 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

37 of 44 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  2. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  3. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  5. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 31

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  7. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  8. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  9. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  10. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  11. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  12. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
19 more
  1. 2016A Diagram Is Worth A Dozen Imagescited by 793
  2. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  3. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
  4. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 572
  5. 2025π*0.6: a VLA That Learns From Experiencecited by 280
  6. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 173
  7. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 141
  8. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 139
  9. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 112
  10. 2025Self-Improving Vision-Language-Action Models with Data Generation via Residual RLcited by 72
  11. 2025WMPO: World Model-based Policy Optimization for Vision-Language-Action Modelscited by 68
  12. 2025World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Trainingcited by 57
  13. 2025Igniting VLMs toward the Embodied Spacecited by 53
  14. 2025Diffusion Guidance Is a Controllable Policy Improvement Operatorcited by 51
  15. 2025RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learningcited by 47
  16. 2025GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulationcited by 41
  17. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thoughtcited by 30
  18. 2025NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewardscited by 26
  19. 2025Reinforcing Action Policies by Prophesyingcited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts
  2. 2026ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
  3. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  4. 2026Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies
  5. 2025VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
  6. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Survey
  7. 2025ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
  8. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics