Data-Efficient Robot Learning

Follow this topic Ask about this topic

Momentum

25 papers in the last four weeks, up 400% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
May 8, 2026Yanzhe Chen, Kevin Yuchen Ma, Qi Lv +4Robot Policy Adaptation VLM Adaptation
National University of Singapore · Institude for Information Research, A*STAR · Harbin Institute of Technology (Shenzhen).
Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot
May 1, 2026Devdutt Subhasish, Henrik Hose, Sebastian TrimpeRobot Skill Learning Autonomous Racing
Institute for Data Science in Mechanical Engineering, RWTH Aachen University, 52062 Aachen
Can Tabular Foundation Models Guide Exploration in Robot Policy Learning?
Apr 30, 2026Buqing Ou, Frederike DümbgenTabular Foundation Models Robot Policy Learning
Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Inria, Département d’informatique de l’ENS, CNRS, PSL Research University, Paris, France
RL Token: Bootstrapping Online RL with Vision-Language-Action Models
Apr 24, 2026Charles Xu, Jost Tobias Springenberg, Michael Equi +4RL for Robotics Robot Skill Learning
Physical Intelligence
From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
Mar 10, 2026Zhanyi Sun, Shuran SongRL for Robotics Robot Policy Learning
1Stanford University.
Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation
Jan 27, 2026Kaipeng Fang, Weiqing Liang, Yuyang Li +5Robot Skill Learning Bimanual Robotic Manipulation
University of Electronic Science and Technology of China · Southwest Jiaotong University · Tongji University +1

May 8, 2026, cs.ROJ/K move · Enter open · S save

Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation

Yanzhe Chen, Kevin Yuchen Ma, Qi Lv, Yiqi Lin+3

National University of Singapore · Institude for Information Research, A*STAR · Harbin Institute of Technology (Shenzhen).

Robot Policy Adaptation VLM Adaptation Generalization in Robotic Manipulation Robotic Manipulation Data-Efficient Robot Learning VLMs for Robotics+1

Open paper AskPDF arXiv

While Vision-Language-Action (VLA) models offer broad general capabilities, deploying them on specific hardware requires real-world adaptation to bridge the embodiment gap. Since robot demonstrations are costly, this adaptation must often occur under a strict data budget. In this work, we identify a critical diversity trap: the standard heuristic of "maximizing coverage" by collecting diverse, single-shot demonstrations can be self-defeating due to non-vanishing estimation noise. We formalize this phenomenon as a Coverage--Density Trade-off. By decomposing the policy error into estimation (density) and extrapolation (coverage) terms, we characterize an interior optimal allocation of unique conditions for a fixed budget. Guided by this analysis, we propose Anchor-Centric Adaptation (ACA), a two-stage framework that first stabilizes a policy skeleton through repeated demonstrations at core anchors, then selectively expands coverage to high-risk boundaries via teacher-forced error mining and constrained residual updates. Real-robot experiments validate our trade-off framework and demonstrate that ACA significantly improves task reliability and success rates over standard diverse sampling strategies under the same budget.

Momentum

Related topics

Latest papers 66

Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation

Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot

Can Tabular Foundation Models Guide Exploration in Robot Policy Learning?

RL Token: Bootstrapping Online RL with Vision-Language-Action Models

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning

Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation