mlsanityData to 7 Oct 2026

HoloBrain-0 Technical Report

arXiv 2602.12062 ↗First posted 12 Feb 2026cs.ROcited by 20

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

Abstract (arXiv)

In this work, we introduce HoloBrain-0, a comprehensive Vision-Language-Action (VLA) framework that bridges the gap between foundation model research and reliable real-world robot deployment. The core of our system is a novel VLA architecture that explicitly incorporates robot embodiment priors, including multi-view camera parameters and kinematic descriptions (URDF), to enhance 3D spatial reasoning and support diverse embodiments. We validate this design through a scalable ``pre-train then post-train" paradigm, achieving state-of-the-art results on simulation benchmarks such as RoboTwin 2.0, LIBERO, and GenieSim, as well as strong results on challenging long-horizon real-world manipulation tasks. Notably, our efficient 0.2B-parameter variant rivals significantly larger baselines, enabling low-latency on-device deployment. To further accelerate research and practical adoption, we fully open-source the entire HoloBrain ecosystem, which includes: (1) powerful pre-trained VLA foundations; (2) post-trained checkpoints for multiple simulation suites and real-world tasks; and (3) RoboOrchard, a full-stack VLA infrastructure for data curation, model training and deployment. Together with standardized data collection protocols, this release provides the community with a complete, reproducible path toward high-performance robotic manipulation.

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 55 of its 63 references that are in the map. First posted on arXiv 12 Feb 2026.

Builds on

55 of 63 references.

Closest ancestors · 8

Same direction, newest first

  1. 2026A Pragmatic VLA Foundation Model26 Jan
  2. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model11 Oct
  3. 2025FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies5 Sep
  4. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  5. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  6. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  7. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  8. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun

Other references · 47

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2025Qwen2.5-VL Technical Reportcited by 5,418
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  8. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  9. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  10. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  11. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  12. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
35 more
  1. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  2. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  3. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  4. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  5. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  6. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  7. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  8. 2021Implicit Behavioral Cloningcited by 442
  9. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  10. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  11. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  12. 2022Behavior Transformers: Cloning k modes with one stonecited by 299
  13. 2026Causal World Modeling for Robot Controlcited by 289
  14. 2020Integrated Task and Motion Planningcited by 281
  15. 2025π*0.6: a VLA That Learns From Experiencecited by 280
  16. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  17. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 278
  18. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 254
  19. 2025Motus: A Unified Latent Action World Modelcited by 231
  20. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 224
  21. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  22. 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Videocited by 191
  23. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 183
  24. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 145
  25. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 135
  26. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 135
  27. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representationscited by 115
  28. 2025Training-Time Action Conditioning for Efficient Real-Time Chunkingcited by 61
  29. 2025Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulationcited by 24
  30. 2024BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligencecited by 10
  31. 2025Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learningcited by 9
  32. 2025SEM: Enhancing Spatial Understanding for Robust Robot Manipulationcited by 8
  33. 2025Genie Centurion: Accelerating Scalable Real-World Robot Training with Human Rewind-and-Refine Guidancecited by 7
  34. 2025Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Spacecited by 3
  35. 2025MOVE: A Simple Motion-Based Data Collection Paradigm for Spatial Generalization in Robotic Manipulationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 20.

20 papers.

Sort:

By area:

  1. 2026Do World Action Models Generalize Better than VLAs? A Robustness Studycited by 35
  2. 2026ABot-M0.5: Unified Mobility-and-Manipulation World Action Modelcited by 28
  3. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 25
  4. 2026From Foundation to Application: Improving VLA Models in Practicecited by 25
  5. 2026DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulationcited by 8
  6. 2026Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Modelscited by 5
  7. 2026EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AIcited by 4
  8. 2026WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learningcited by 4
  9. 2026World Action Models in Real Time: An Empirical Study of Smooth Execution via Asynchronous Deploymentcited by 4
  10. 2026CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Modelscited by 3
  11. 2026Bridge-WA: Predicting Where and How the World Changes for Robotic Actioncited by 2
  12. 2026Spatially Aware World Action Model via Geometric Latent Diffusioncited by 2
8 more
  1. 2026VLA Foundry: A Unified Framework for Training Vision-Language-Action Modelscited by 1
  2. 2026HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memorycited by 1
  3. 2026Long-WAM: Scaling the Context of World-Action Modelscited by 1
  4. 2026LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignmentscited by 0
  5. 2026UniMPA: A Unified Memory-Prediction-Action Model via Action-Grounded Transition Modelingcited by 0
  6. 2026An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAMcited by 0
  7. 2026CrossSafe: Towards Cross-Embodiment Latent Safety Filterscited by 0
  8. 2026Remember What You Did: Action-History Memory with Dual-Expert Denoising for Long-Horizon Vision-Language-Action Policiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots
  2. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulation
  3. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  4. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  5. 2026H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Space
  6. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation
  7. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  8. 2026Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform