mlsanityData to 14 Oct 2026

Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data

arXiv 2606.08107 ↗First posted 6 Jun 2026cs.RO cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Robotics faces a fundamental challenge of data scarcity. Unlike language or vision research, there is no internet-scale dataset for robotic manipulation. A promising path forward is to leverage egocentric human data, which can be collected more easily, with greater breadth, and at a larger scale. Towards this end, we investigate key design choices for learning across human and humanoid embodiments equipped with dexterous five-finger hands, using the π0.5 model as a foundation. Our results show that human data enables robots to learn new task semantics and compose existing skills into novel behaviors without corresponding robot data. The paper website is here: https://egopipaper.github.io/

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 12 of its 17 references that are in the map. First posted on arXiv 6 Jun 2026.

Builds on

12 of 17 references.

References · 12

  1. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  2. 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Videocited by 211
  3. 2023Project Aria: A New Tool for Egocentric Multi-Modal AI Researchcited by 208
  4. 2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 175
  5. 2023AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation Systemcited by 152
  6. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 128
  7. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 102
  8. 2026EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Datacited by 94
  9. 2025Masquerade: Learning from In-the-wild Human Videos using Data-Editingcited by 43
  10. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Modelscited by 42
  11. 2024Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Paintingcited by 36
  12. 2024ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedbackcited by 31

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretrainingcited by 0
  2. 2026Skel-WAM: A Hand-Skeleton-Conditioned World Action Model for Human-to-Robot Manipulation Transfercited by 0
  3. 2026EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026IronMind: Scaling Humanoid Dexterous Manipulation via Camera-Space Ego-Centric Pretraining ↗
  2. 2026Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data
  3. 2025In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data
  4. 2026Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?
  5. 2025PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence
  6. 2026Towards a General Humanoid Loco-Manipulation Model via Egocentric Whole-Body Human Data Pretraining ↗
  7. 2025EgoMI: Learning Active Vision and Whole-Body Manipulation from Egocentric Human Demonstrations
  8. 2025EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data