mlsanityData to 7 Oct 2026

EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data

arXiv 2602.16710 ↗First posted 18 Feb 2026cs.ROcited by 77

Not on the map. Why?

Cited by 23 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Human behavior is among the most scalable sources of data for learning physical intelligence, yet how to effectively leverage it for dexterous manipulation remains unclear. While prior work demonstrates human to robot transfer in constrained settings, it is unclear whether large scale human data can support fine grained, high degree of freedom dexterous manipulation. We present EgoScale, a human to dexterous manipulation transfer framework built on large scale egocentric human data. We train a Vision Language Action (VLA) model on over 20,854 hours of action labeled egocentric human video, more than 20 times larger than prior efforts, and uncover a log linear scaling law between human data scale and validation loss. This validation loss strongly correlates with downstream real robot performance, establishing large scale human data as a predictable supervision source. Beyond scale, we introduce a simple two stage transfer recipe: large scale human pretraining followed by lightweight aligned human robot mid training. This enables strong long horizon dexterous manipulation and one shot task adaptation with minimal robot supervision. Our final policy improves average success rate by 54% over a no pretraining baseline using a 22 DoF dexterous robotic hand, and transfers effectively to robots with lower DoF hands, indicating that large scale human motion provides a reusable, embodiment agnostic motor prior.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Feb 2026.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 77.

77 papers.

Sort:

By area:

  1. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103
  2. 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Modelscited by 47
  3. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  4. 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodimentscited by 42
  5. 2026EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Datacited by 17
  6. 2026HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videoscited by 14
  7. 2026RoboTTT: Context Scaling for Robot Policiescited by 13
  8. 2026Egocentric World Model for Photorealistic Hand-Object Interaction Synthesiscited by 10
  9. 2026T-Rex: Tactile-Reactive Dexterous Manipulationcited by 10
  10. 2026World Action Models: A Surveycited by 10
  11. 2026HumanNet: Scaling Human-centric Video Learning to One Million Hourscited by 9
  12. 2026Do as I Do: Dexterous Manipulation Data from Everyday Human Videoscited by 9
38 more
  1. 2026ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretrainingcited by 8
  2. 2026Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalizationcited by 8
  3. 2026Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstrationcited by 6
  4. 2026WAM-TTT: Steering World-Action Models by Watching Human Play at Test Timecited by 6
  5. 2026Motus2: A Self-Evolving General World Model for Dexterous Manipulationcited by 6
  6. 2026Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learningcited by 5
  7. 2026The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstructioncited by 4
  8. 2026Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulationcited by 4
  9. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 4
  10. 2026HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editingcited by 4
  11. 2026MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planningcited by 3
  12. 2026FACT: Failure-Aware Causal Training for World-Action Modelscited by 3
  13. 2026MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardwarecited by 2
  14. 2026EgoExo-WM: Unlocking Exo Video for Ego World Modelscited by 2
  15. 2026StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Videocited by 2
  16. 2026Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Datacited by 2
  17. 2026HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretrainingcited by 2
  18. 2026Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Datacited by 2
  19. 2026LIME: Learning Intent-aware Camera Motion from Egocentric Videocited by 2
  20. 2026EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agentcited by 2
  21. 2026SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulationcited by 2
  22. 2026H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Modelscited by 2
  23. 2026EgoTac: In-the-wild Tactile Prediction from Egocentric Visioncited by 2
  24. 2026LD4WAM: Learning Latent Dynamics from Human Videos for World Action Modelscited by 2
  25. 2026ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-trainingcited by 2
  26. 2026SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worldscited by 1
  27. 2026ForgeVLA: Federated Vision-Language-Action Learning without Language Annotationscited by 1
  28. 2026Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?cited by 1
  29. 2026Not All Actions Are Equal: Rethinking Conditioning for Dexterous World Modelcited by 1
  30. 2026Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robotscited by 1
  31. 2026OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policiescited by 1
  32. 2026A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulationcited by 1
  33. 2026CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understandingcited by 1
  34. 2026World-Action Models for Robot Learning and Control: A Surveycited by 1
  35. 2026XPACE: Joint World and Action Modeling from Heterogeneous Experiencecited by 1
  36. 2026PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamicscited by 1
  37. 2026AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulationcited by 1
  38. 2026EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devicescited by 0

50 most cited of 77 All 77 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026IronMind: Scaling Humanoid Dexterous Manipulation via Camera-Space Ego-Centric Pretraining ↗
  2. 2025In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data
  3. 2026Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data
  4. 2026EgoSteer: An Open-Source Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos
  5. 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
  6. 2024EgoMimic: Scaling Imitation Learning via Egocentric Video
  7. 2025METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model
  8. 2025OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation