mlsanityData to 7 Oct 2026

GR-3 Technical Report

arXiv 2507.15493 ↗First posted 21 Jul 2025cs.RO cs.AI cs.CVcited by 110

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

Abstract (arXiv)

We report our recent progress towards building generalist robot policies, the development of GR-3. GR-3 is a large-scale vision-language-action (VLA) model. It showcases exceptional capabilities in generalizing to novel objects, environments, and instructions involving abstract concepts. Furthermore, it can be efficiently fine-tuned with minimal human trajectory data, enabling rapid and cost-effective adaptation to new settings. GR-3 also excels in handling long-horizon and dexterous tasks, including those requiring bi-manual manipulation and mobile movement, showcasing robust and reliable performance. These capabilities are achieved through a multi-faceted training recipe that includes co-training with web-scale vision-language data, efficient fine-tuning from human trajectory data collected via VR devices, and effective imitation learning with robot trajectory data. In addition, we introduce ByteMini, a versatile bi-manual mobile robot designed with exceptional flexibility and reliability, capable of accomplishing a wide range of tasks when integrated with GR-3. Through extensive real-world experiments, we show GR-3 surpasses the state-of-the-art baseline method, π0, on a wide variety of challenging tasks. We hope GR-3 can serve as a step towards building generalist robots capable of assisting humans in daily life.

Key facts. Cited by 110 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 69 of its 78 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

69 of 78 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  2. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  3. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  4. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots18 Dec
  5. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation29 Nov
  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 · 61

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  7. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  8. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  9. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  10. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  11. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  12. 2019Root Mean Square Layer Normalizationcited by 1,425
38 more
  1. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  2. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  3. 2022A Generalist Agentcited by 802
  4. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  5. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  6. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  7. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  8. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  9. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  10. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  11. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  12. 2024LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Modelscited by 571
  13. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  14. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  15. 2023GLaMM: Pixel Grounding Large Multimodal Modelcited by 447
  16. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  17. 2025Seed1.5-VL Technical Reportcited by 367
  18. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  19. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  20. 2024Latent Action Pretraining from Videoscited by 302
  21. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 290
  22. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  23. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 277
  24. 2019RoboNet: Large-Scale Multi-Robot Learningcited by 268
  25. 2020Query-Key Normalization for Transformerscited by 266
  26. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  27. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  28. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 254
  29. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  30. 2022Masked Visual Pre-training for Motor Controlcited by 246
  31. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
  32. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 215
  33. 2023Any-point Trajectory Modeling for Policy Learningcited by 207
  34. 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Videocited by 191
  35. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 167
  36. 2023Language-Driven Representation Learning for Roboticscited by 163
  37. 2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 160
  38. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 151

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 44; 2026: 66.

110 papers.

Sort:

By area:

  1. 2026Causal World Modeling for Robot Controlcited by 289
  2. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 141
  3. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  4. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 129
  5. 2026A Pragmatic VLA Foundation Modelcited by 97
  6. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 94
  7. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 83
  8. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  9. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  10. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 48
  11. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 46
  12. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoningcited by 44
38 more
  1. 2025GigaBrain-0: A World Model-Powered Vision-Language-Action Modelcited by 43
  2. 2026Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Executioncited by 42
  3. 2025GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulationcited by 41
  4. 2025The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruningcited by 34
  5. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 34
  6. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 30
  7. 2026CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videoscited by 27
  8. 2026When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAscited by 27
  9. 2025RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Modelscited by 26
  10. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 25
  11. 2025From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priorscited by 25
  12. 2026From Foundation to Application: Improving VLA Models in Practicecited by 25
  13. 2025RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulationcited by 24
  14. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectoriescited by 24
  15. 2025Robix: A Unified Model for Robot Interaction, Reasoning and Planningcited by 23
  16. 2025Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agentscited by 23
  17. 2026GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learningcited by 23
  18. 2025AVA-VLA: Improving Vision-Language-Action models with Active Visual Attentioncited by 22
  19. 2025Mixture of Horizons in Action Chunkingcited by 20
  20. 2025A Survey on Agentic Multimodal Large Language Modelscited by 19
  21. 2026Learning Native Continuation for Action Chunking Flow Policiescited by 18
  22. 2025Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policycited by 17
  23. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 17
  24. 2025RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Modelscited by 16
  25. 2025A Step Toward World Models: A Survey on Robotic Manipulationcited by 15
  26. 2025XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representationscited by 15
  27. 2026Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Modelscited by 14
  28. 2026WALL-WM: Carving World Action Modeling at the Event Jointscited by 14
  29. 2026HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoningcited by 13
  30. 2025NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policiescited by 12
  31. 2025MimicFunc: Imitating Tool Manipulation from a Single Human Video via Functional Correspondencecited by 11
  32. 2026chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistenciescited by 11
  33. 2025Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligencecited by 10
  34. 2025HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policiescited by 10
  35. 2026Geometric Action Model for Robot Policy Learningcited by 10
  36. 2026Demystifying Action Space Design for Robotic Manipulation Policiescited by 9
  37. 2026Dexora: Open-source VLA for High-DoF Bimanual Dexteritycited by 9
  38. 2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Compositioncited by 8

50 most cited of 110 All 110 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy
  2. 2025From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models
  3. 2026GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory Planning
  4. 2026Generalizing Manipulation Skills with a Local Coding Agent
  5. 2026Colosseum V2: Benchmarking Generalization for Vision-Language-Action Models
  6. 2025Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots
  7. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  8. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification