Data-Efficient Robot Learning

Overview

Data-efficient robot learning studies how robots can learn useful skills without costly collections of demonstrations or extensive trial and error on physical hardware. Common approaches include imitation learning, sample-efficient reinforcement learning, world models that support planning or simulated practice, and methods that select, augment, or reuse demonstrations. Human videos, pretrained vision-language-action models, and transfer across robot embodiments can provide useful starting points, while benchmarks such as LIBERO and RoboCasa test manipulation performance in simulation and on real robots. A central challenge is that gains on offline prediction or simulated tasks do not always translate to reliable real-world behavior, and adaptation must improve new skills without losing old ones or requiring excessive supervision.

Latest papers

CardsList

211 papers27 papers in the last four weeks, down 52% on the four weeks before. 0.2% of all new papers.

  1. Phoenix: Learning Scene Structure Representations for Generalizable World-Action Models

    Nov 18, 2026Yupeng Zheng, Chaoyue Li, Linbo Wang +15World Model LearningWorld Action Models

  2. SHAPE: Discrete Supervision and Parallel Continuous Streams for Learning Dexterous Manipulation from Egocentric Human Data

    Nov 18, 2026Yaping Li, Zhihong Liu, Jiacheng Li +10Robotic ManipulationVLMs for Robotics

  3. Where Do Human-to-Robot Transfer Gains Come From?

    Nov 17, 2026Jiachen Li, Shihao Li, Soovadeep Bakshi +4Transfer LearningRobot Learning

  4. ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters

    Nov 16, 2026Ruixi Yu, Dairu Liu, Xuchuan Chen +9Vision-Language-Action ModelsRobotic Manipulation

  5. QTOP: Scaling Humanoid Motion Tracking with Quantile Critics

    Nov 16, 2026Markus Peschl, Dana Kianfar, Daniel DijkmanHumanoid Motion TrackingRL for Robotics

  6. Cleanly-DINO: Efficiently Learning Visual Task Spaces for Robotics

    Nov 15, 2026Adrian Röfer, Melika Shekarriz, José Arce y de la Borbolla +2RoboticsData-Efficient Robot Learning

  7. A Recipe for Physical Action Model Training

    Nov 12, 2026Shaojiang Wang, Geer YangRoboticsData-Efficient Robot Learning

  8. Video-Action Models for Data-Efficient Industrial Manipulation

    Nov 11, 2026Eugenio Chisari, Stefanos Charalambous, Oliver Sanchez +23Data-Efficient Robot LearningRobot Learning from Video

  9. CrowdMAPS: Crowdsourcing Multiple Actions per State for Real-World Imitation Learning

    Nov 11, 2026Yilong Song, Harshvardhan Chandirasekar, Karthik Desingh +1Robotic Data CollectionRobot Imitation Learning

  10. VLA Adaptation with Real and Simulated Data: A Case Study on Robotic Chess

    Nov 9, 2026Matěj Kripner, Milan StrakaVLA AdaptationData-Efficient Robot Learning

  11. GAP: Generalized Adaptation Prior for Dexterous Piano Playing

    Nov 9, 2026Jinyi Chen, Hongyi Li, Lei Jiang +6Robot Policy AdaptationData-Efficient Robot Learning

  12. The Relative Value of Demonstration Data: Execution Time Limits and Operator Mixtures in Behavior Cloning

    Nov 9, 2026Jiaxuan Guo, Xingyu Ren, Youran Sun +3Learning from DemonstrationData-Efficient Robot Learning

  13. Accelerated Reinforcement Learning for Soft Robotics: Hours Instead of Years

    Nov 9, 2026Roshan S. Kaundinya, Hehui Zheng, Robert K. Katzschmann +1RL for RoboticsData-Efficient Robot Learning

  14. MoE-DAgger: Transition-Aware Router-Entropy Gating for Selective Human Correction in Phase-Structured Manipulation

    Nov 7, 2026Sungjun Heo, Sungjun Yang, Heedon Jeong +2Data-Efficient Robot LearningRobotic Data Collection

  15. UniLatent: Cross-Embodiment Transfer via Latent Observation Alignment

    Nov 6, 2026Yufei Ding, Yi Du, Weiduo Yuan +5Cross-Embodiment TransferLatent Space Alignment

  16. Latent RL Priors for Data-Efficient Dexterous Manipulation

    Nov 5, 2026Yixiao Wang, Peiyi Chen, Mustafa Mukadam +3Robotic ManipulationData-Efficient Robot Learning

  17. ELA: End-to-End Latent Action Policy Learning from Video Demonstrations

    Nov 3, 2026Cheng-Chun Hsu, Peter StoneLatent Action LearningRobot Imitation Learning

  18. GUILD: Guided Iterative Data Collection for Imitation Learning

    Nov 3, 2026Shivin Dass, Kevin Nguyen, Rohan Yelandur +2Robotic Data CollectionImitation Learning

  19. Robotic Data Inoculation

    Oct 28, 2026Qiyang Li, Zhiyuan Zhou, Charles Xu +1Robotic Data CollectionData-Efficient Robot Learning

  20. HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model

    Oct 25, 2026Chao Chen, Zhenrong Wang, Jilong Wang +4Robot Policy AdaptationHumanoid Motion Tracking

  21. Move, don't think: sample-efficient collision avoidance with lossy proximity sensors

    Oct 22, 2026Carson Kohlbrenner, Niraj Pudasaini, William Xie +3Robot Collision AvoidanceData-Efficient Robot Learning

  22. Learning Robot Behavior Priors from Non-Robotic Synthetic Data

    Oct 22, 2026Mateusz Odrowaz-Sypniewski, Michael Amir, Jasmine Bayrooti +2Synthetic Data PretrainingData-Efficient Robot Learning

  23. RangeNav: Task-Aligned LiDAR Range-Image Pretraining for Robot Navigation

    Oct 21, 2026Samuel Foo Enze, Manthan Patel, Fan Yang +4Robot Navigation3D Representation Learning

  24. Real2Sem2Real: 3D Semantic Augmentations for Robot Learning from a Single Human RGB Demonstration

    Oct 20, 2026Matthew Strong, Ankush K. Dhawan, Julien Poffet +3Robot Learning from VideoSynthetic Data Generation for Robotics

  25. Learning Tactile-Aware Hand Representations from Human Hand-Object Interaction Data

    Oct 20, 2026Yeonguk Yu, Jaehong Kim, Byungok HanRobotic Tactile SensingData-Efficient Robot Learning