mlsanityData to 7 Oct 2026

Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution

arXiv 2602.12684 ↗First posted 13 Feb 2026cs.RO cs.LGcited by 42

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

Abstract (arXiv)

In this report, we introduce Xiaomi-Robotics-0, an advanced vision-language-action (VLA) model optimized for high performance and fast and smooth real-time execution. The key to our method lies in a carefully designed training recipe and deployment strategy. Xiaomi-Robotics-0 is first pre-trained on large-scale cross-embodiment robot trajectories and vision-language data, endowing it with broad and generalizable action-generation capabilities while avoiding catastrophic forgetting of the visual-semantic knowledge of the underlying pre-trained VLM. During post-training, we propose several techniques for training the VLA model for asynchronous execution to address the inference latency during real-robot rollouts. During deployment, we carefully align the timesteps of consecutive predicted action chunks to ensure continuous and seamless real-time rollouts. We evaluate Xiaomi-Robotics-0 extensively in simulation benchmarks and on two challenging real-robot tasks that require precise and dexterous bimanual manipulation. Results show that our method achieves state-of-the-art performance across all simulation benchmarks. Moreover, Xiaomi-Robotics-0 can roll out fast and smoothly on real robots using a consumer-grade GPU, achieving high success rates and throughput on both real-robot tasks. To facilitate future research, code and model checkpoints are open-sourced at https://xiaomi-robotics-0.github.io

Key facts. Cited by 42 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 67 of its 71 references that are in the map. First posted on arXiv 13 Feb 2026.

Builds on

67 of 71 references.

Closest ancestors · 11

Same direction, newest first

  1. 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization3 Feb
  2. 2025FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies5 Sep
  3. 2025GR-3 Technical Report21 Jul
  4. 2025Unified Vision-Language-Action Model24 Jun
  5. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better29 May
  6. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  7. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  8. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  10. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  11. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 56

  1. 2022Scalable Diffusion Models with Transformerscited by 5,931
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  5. 2025Qwen3-VL Technical Reportcited by 2,534
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  7. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  8. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  9. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  11. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  12. 2019Towards VQA Models That Can Readcited by 1,696
38 more
  1. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  2. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  6. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  7. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  8. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  9. 2016A Diagram Is Worth A Dozen Imagescited by 793
  10. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  11. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  12. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  13. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  14. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  15. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  16. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  17. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  18. 2024MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attentioncited by 375
  19. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  20. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  21. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  22. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  23. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  24. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  25. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 189
  26. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 183
  27. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 176
  28. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 159
  29. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planningcited by 152
  30. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 151
  31. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 138
  32. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 131
  33. 2023LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Modelscited by 120
  34. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  35. 2025Training-Time Action Conditioning for Efficient Real-Time Chunkingcited by 61
  36. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 54
  37. 2025LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Modelscited by 53
  38. 2024Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learningcited by 46

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 42.

42 papers.

Sort:

By area:

  1. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 65
  2. 2026RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policiescited by 35
  3. 2026From Foundation to Application: Improving VLA Models in Practicecited by 25
  4. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectoriescited by 24
  5. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  6. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 17
  7. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 17
  8. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 13
  9. 2026DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulationcited by 8
  10. 2026DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulationcited by 8
  11. 2026Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Modelscited by 5
  12. 2026OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelismcited by 4
30 more
  1. 2026Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulationcited by 4
  2. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 4
  3. 2026N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulationcited by 2
  4. 2026PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessmentcited by 2
  5. 2026ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-trainingcited by 2
  6. 2026E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulationcited by 1
  7. 2026ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policiescited by 1
  8. 2026PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloudcited by 1
  9. 2026DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulationcited by 1
  10. 2026ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in Manipulation Policiescited by 0
  11. 2026Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Reviewcited by 0
  12. 2026PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulationcited by 0
  13. 2026V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Modelscited by 0
  14. 2026N0-Foundation: Towards the Age of Tactile Intelligencecited by 0
  15. 2026H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Spacecited by 0
  16. 2026Grounded Action Model: 3D Grounding as a Foundation for Roboticscited by 0
  17. 2026HABILIS Brain 0: Geometry-Change Supervision for Vision-Language-Action and Residual Flow Recoverycited by 0
  18. 2026IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Modelscited by 0
  19. 2026An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAMcited by 0
  20. 2026InternW0: A Foundational Physical World Model for Efficient Real-World Interactionscited by 0
  21. 2026Devol-ONE: One Autoregressive Mixture of Transformers to Unify Vision-Language-Action and Latent World Modelingcited by 0
  22. 2026Copper-Policy: Focus on the Representation for Robust Robot Manipulationcited by 0
  23. 2026PlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agentscited by 0
  24. 2026LIBERO-MAX: Do Robot Policies Adapt When the World Changes?cited by 0
  25. 2026Remember What You Did: Action-History Memory with Dual-Expert Denoising for Long-Horizon Vision-Language-Action Policiescited by 0
  26. 2026Rethinking Representations for World-Action Modelingcited by 0
  27. 2026EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Actioncited by 0
  28. 2026TacDyn-WAM: Learning Implicit Tactile Dynamics in a Heterogeneous Visuo-Tactile World Action Modelcited by 0
  29. 2026UniWAM: Unified World-Action Modelcited by 0
  30. 2026REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with 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. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulation
  3. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  4. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
  5. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
  6. 2026A Pragmatic VLA Foundation Model
  7. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
  8. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey