mlsanityData to 7 Oct 2026

Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack

arXiv 2606.14409 ↗First posted 12 Jun 2026cs.RO cs.AIcited by 20

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

Abstract (arXiv)

In this report, we present Hy-Embodied-0.5-VLA, abbreviated as HyVLA-0.5, an end-to-end system that spans the full robot learning stack: data collection, model design, continued pre-training and supervised fine-tuning, RL post-training, and real-world deployment. Each component serves a distinct role in this stack.

Key facts. Cited by 20 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 43 of its 55 references that are in the map. First posted on arXiv 12 Jun 2026.

Builds on

43 of 55 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing6 Apr
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 39

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2022Flow Matching for Generative Modelingcited by 5,426
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  8. 2025Qwen3-VL Technical Reportcited by 2,534
  9. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  10. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  11. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  12. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
27 more
  1. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  2. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  3. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
  4. 2025π*0.6: a VLA That Learns From Experiencecited by 280
  5. 2025Improving Video Generation with Human Feedbackcited by 267
  6. 2025Motus: A Unified Latent Action World Modelcited by 231
  7. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226
  8. 2016Temporal Convolutional Networks: A Unified Approach to Action Segmentationcited by 199
  9. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learningcited by 153
  10. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 151
  11. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  12. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 116
  13. 2024GRAPE: Generalizing Robot Policy via Preference Alignmentcited by 106
  14. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 94
  15. 2025Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfercited by 86
  16. 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Modelscited by 69
  17. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  18. 2025DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulationcited by 58
  19. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 54
  20. 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodimentscited by 42
  21. 2026RoboBrain 2.5: Depth in Sight, Time in Mindcited by 38
  22. 2026JoyAI-RA 0.1: A Foundation Model for Robotic Autonomycited by 21
  23. 2025EgoMI: Learning Active Vision and Whole-Body Manipulation from Egocentric Human Demonstrationscited by 12
  24. 2026HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrationscited by 12
  25. 2026FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimizationcited by 8
  26. 2026PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policiescited by 7
  27. 2025Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPOcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 20.

20 papers.

Sort:

By area:

  1. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectoriescited by 24
  2. 2026Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Modelscited by 5
  3. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 4
  4. 2026PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessmentcited by 2
  5. 2026RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imaginationcited by 1
  6. 2026PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloudcited by 1
  7. 2026DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulationcited by 1
  8. 2026TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulationcited by 1
  9. 2026MachEmbodied-U0: Unified Understanding and Generation Model for Embodied Intelligencecited by 1
  10. 2026InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Datacited by 1
  11. 2026Pelican-VLA 0.5: Attending Before Acting Benefits Generalizationcited by 0
  12. 2026WLA3: World Latent Action Modeling for Semantics, Dynamics, and Kinematicscited by 0
8 more
  1. 2026Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Modelcited by 0
  2. 2026HABILIS Brain 0: Geometry-Change Supervision for Vision-Language-Action and Residual Flow Recoverycited by 0
  3. 2026An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAMcited by 0
  4. 2026CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven Interfacescited by 0
  5. 2026Rethinking Representations for World-Action Modelingcited by 0
  6. 2026Magic-W0: A Structured World-Action Foundation Model for Physical Intelligencecited by 0
  7. 2026EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Actioncited by 0
  8. 2026Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
  2. 2026FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence
  3. 2026Hy-Embodied-VLM-1.0: Efficient Physical-World Agents
  4. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  5. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  6. 2024A Survey on Vision-Language-Action Models for Embodied AI
  7. 2026EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents
  8. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model