mlsanityData to 14 Oct 2026

Universal Actions for Enhanced Embodied Foundation Models

arXiv 2501.10105 ↗First posted 17 Jan 2025cs.RO cs.AI cs.CVcited by 82

Not on the map. Why?

Cited by 58 in Vision-language-action models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Training on diverse, internet-scale data is a key factor in the success of recent large foundation models. Yet, using the same recipe for building embodied agents has faced noticeable difficulties. Despite the availability of many crowd-sourced embodied datasets, their action spaces often exhibit significant heterogeneity due to distinct physical embodiment and control interfaces for different robots, causing substantial challenges in developing embodied foundation models using cross-domain data. In this paper, we introduce UniAct, a new embodied foundation modeling framework operating in a Universal Action Space. Our learned universal actions capture the generic atomic behaviors across diverse robots by exploiting their shared structural features, and enable enhanced cross-domain data utilization and cross-embodiment generalizations by eliminating the notorious heterogeneity. The universal actions can be efficiently translated back to heterogeneous actionable commands by simply adding embodiment-specific details, from which fast adaptation to new robots becomes simple and straightforward. Our 0.5B instantiation of UniAct outperforms 14X larger SOTA embodied foundation models in extensive evaluations on various real-world and simulation robots, showcasing exceptional cross-embodiment control and adaptation capability, highlighting the crucial benefit of adopting universal actions. Project page: https://github.com/2toinf/UniAct

Key facts. Cited by 82 papers in the map (data through 14 Oct 2026). Builds on 62 of its 75 references that are in the map. First posted on arXiv 17 Jan 2025.

Builds on

62 of 75 references.

References · 62

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  8. 2023Qwen Technical Reportcited by 3,344
  9. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  10. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  11. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  12. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
38 more
  1. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  2. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  3. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  4. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  5. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  6. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  7. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  8. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  9. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  10. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 862
  11. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  12. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  13. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  14. 2024Genie: Generative Interactive Environmentscited by 747
  15. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  16. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  17. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  18. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  19. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  20. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  21. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 440
  22. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
  23. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 346
  24. 2024Latent Action Pretraining from Videoscited by 321
  25. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  26. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 296
  27. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thoughtcited by 279
  28. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 269
  29. 2023Any-point Trajectory Modeling for Policy Learningcited by 215
  30. 2023LIV: Language-Image Representations and Rewards for Robotic Controlcited by 188
  31. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
  32. 2023Language-Driven Representation Learning for Roboticscited by 165
  33. 2023Physically Grounded Vision-Language Models for Robotic Manipulationcited by 165
  34. 2023Video Language Planningcited by 162
  35. 2024Behavior Generation with Latent Actionscited by 160
  36. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 148
  37. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 141
  38. 2024Yell At Your Robot: Improving On-the-Fly from Language Correctionscited by 124

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 37; 2026: 45.

82 papers.

Sort:

By area:

  1. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  2. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 303
  3. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 221
  4. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 192
  5. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  6. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  7. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 74
  8. 2025InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulationcited by 72
  9. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 69
  10. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Modelcited by 56
  11. 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibrationcited by 56
  12. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 49
38 more
  1. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Reviewcited by 38
  2. 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Modelscited by 36
  3. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systemscited by 31
  4. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadcited by 26
  5. 2025Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variationscited by 24
  6. 2025RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Modelscited by 23
  7. 2025Mixture of Horizons in Action Chunkingcited by 21
  8. 2025Is Diversity All You Need for Scalable Robotic Manipulation?cited by 20
  9. 2025Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidancecited by 20
  10. 2026Show-Harness: Just a VLM Agent Can Play Robotscited by 20
  11. 2026LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfercited by 18
  12. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  13. 2025GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulationcited by 17
  14. 2026AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robotscited by 16
  15. 2025Pixel Motion as Universal Representation for Robot Controlcited by 15
  16. 2025A Step Toward World Models: A Survey on Robotic Manipulationcited by 15
  17. 2025XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representationscited by 15
  18. 2026Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wildcited by 15
  19. 2026TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformerscited by 14
  20. 2025X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scalecited by 12
  21. 2026Wall-OSS-0.5 Technical Reportcited by 12
  22. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulationcited by 10
  23. 2026MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Modelscited by 10
  24. 2026ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretrainingcited by 10
  25. 2025RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentationcited by 9
  26. 2025Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attackscited by 9
  27. 2026Demystifying Action Space Design for Robotic Manipulation Policiescited by 9
  28. 2026World2Act: Latent Action Post-Training from World Model Dynamicscited by 8
  29. 2026μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Modelscited by 8
  30. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  31. 2025Asynchronous Fast-Slow Vision-Language-Action Policies for Whole-Body Robotic Manipulationcited by 7
  32. 2026Cross-Hand Latent Representation for Vision-Language-Action Modelscited by 7
  33. 2026X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretrainingcited by 7
  34. 2025Multi-Modal Multi-Task (M3T) Federated Foundation Models for Embodied AI: Potentials and Challenges for Edge Integrationcited by 6
  35. 2026Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitrationcited by 6
  36. 2026UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptationcited by 6
  37. 2025PhysiAgent: An Embodied Agent Framework in Physical Worldcited by 5
  38. 2026EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fieldscited by 5

50 most cited of 82 All 82 (JSON)