mlsanityData to 7 Oct 2026

A Pragmatic VLA Foundation Model

arXiv 2601.18692 ↗First posted 26 Jan 2026cs.RO cs.CVcited by 97

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

Abstract (arXiv)

Offering great potential in robotic manipulation, a capable Vision-Language-Action (VLA) foundation model is expected to faithfully generalize across tasks and platforms while ensuring cost efficiency (e.g., data and GPU hours required for adaptation). To this end, we develop LingBot-VLA with around 20,000 hours of real-world data from 9 popular dual-arm robot configurations. Through a systematic assessment on 4 robotic platforms, each completing 100 tasks with 130 post-training episodes per task, our model achieves clear superiority over competitors, showcasing its strong performance and broad generalizability. We have also built an efficient codebase, which delivers a throughput of 261 samples per second with an 8-GPU training setup, representing a 1.5~2.8× (depending on the relied VLM base model) speedup over existing VLA-oriented codebases. The above features ensure that our model is well-suited for real-world deployment. To advance the field of robot learning, we provide open access to the code, base model, and benchmark data, with a focus on enabling more challenging tasks and promoting sound evaluation standards.

Key facts. Cited by 97 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 29 of its 31 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

29 of 31 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025OmniVLA: Physically-Grounded Multimodal VLA with Unified Multi-Sensor Perception for Robotic Manipulation3 Nov
  2. 2025Dexbotic: Open-Source Vision-Language-Action Toolbox27 Oct
  3. 2025Galaxea Open-World Dataset and G0 Dual-System VLA Model30 Aug
  4. 2025GR-3 Technical Report21 Jul
  5. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct

Other references · 23

  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  4. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  5. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  6. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  7. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  8. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  9. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  10. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  11. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  12. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 138
11 more
  1. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  2. 2025Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfercited by 86
  3. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 83
  4. 2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Modelscited by 68
  5. 20253DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understandingcited by 63
  6. 2025RoboArena: Distributed Real-World Evaluation of Generalist Robot Policiescited by 63
  7. 2025Igniting VLMs toward the Embodied Spacecited by 53
  8. 2025RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policiescited by 29
  9. 2026Masked Depth Modeling for Spatial Perceptioncited by 24
  10. 2025VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoocited by 20
  11. 2025Vision-Centric Activation and Coordination for Multimodal Large Language Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 97.

97 papers.

Sort:

By area:

  1. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 104
  2. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103
  3. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  4. 2026MEM: Multi-Scale Embodied Memory for Vision Language Action Modelscited by 55
  5. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
  6. 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodimentscited by 42
  7. 2026Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agentscited by 37
  8. 2026RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policiescited by 35
  9. 2026ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?cited by 33
  10. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 30
  11. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systemscited by 27
  12. 2026From Foundation to Application: Improving VLA Models in Practicecited by 25
38 more
  1. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectoriescited by 24
  2. 2026ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignmentcited by 23
  3. 2026HoloBrain-0 Technical Reportcited by 20
  4. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  5. 2026Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imaginationcited by 17
  6. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 17
  7. 2026MaskWAM: Unifying Mask Prompting and Prediction for World-Action Modelscited by 15
  8. 2026WALL-WM: Carving World Action Modeling at the Event Jointscited by 14
  9. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 13
  10. 2026Wall-OSS-0.5 Technical Reportcited by 11
  11. 2026GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearchcited by 10
  12. 2026NavDreamer: Video Models as Zero-Shot 3D Navigatorscited by 9
  13. 2026Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflectioncited by 9
  14. 2026Long-Horizon Manipulation via Trace-Conditioned VLA Planningcited by 9
  15. 2026HumanNet: Scaling Human-centric Video Learning to One Million Hourscited by 9
  16. 2026TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAMcited by 9
  17. 2026DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulationcited by 8
  18. 2026Kairos: A Regret-Aware Native World-Action Model Stack for Physical AIcited by 8
  19. 2026ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretrainingcited by 8
  20. 2026DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulationcited by 8
  21. 2026RotVLA: Rotational Latent Action for Vision-Language-Action Modelcited by 7
  22. 2026Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Actioncited by 7
  23. 2026PRTS: A Primitive Reasoning and Tasking System via Contrastive Representationscited by 6
  24. 2026GEM: Generative Supervision Helps Embodied Intelligencecited by 6
  25. 2026X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretrainingcited by 6
  26. 2026DreamWAM: Beyond RGB Future Prediction for World Action Modelscited by 6
  27. 2026Human Cognition in Machines: A Unified Perspective of World Modelscited by 5
  28. 2026APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policiescited by 5
  29. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  30. 2026Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervisioncited by 5
  31. 2026Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Modelscited by 5
  32. 2026VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesiscited by 4
  33. 2026WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learningcited by 4
  34. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 4
  35. 2026DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adaptercited by 3
  36. 2026Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLAcited by 3
  37. 2026Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?cited by 3
  38. 2026PanoWorld: Real-World Panoramic Generationcited by 3

50 most cited of 97 All 97 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  2. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
  3. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  4. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  5. 2026VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
  6. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulation
  7. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  8. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation