Paper Detail
Yu Qi, Zhang Ye, Xinyi Xu, Yuxuan Lu, Amitoj Sandhu, Boce Hu, Haojie Huang, Jonathan Tremblay, Lawson L. S. Wong
Compositional generalization is essential for robot to follow diverse instructions. However, pretrained policies are known to take shortcuts, deferring to salient cues rather than grounding language. We introduce a diagnostic framework that localizes this failure to individual \textit{instruction factors}, \textit{e.g.,} reusable semantic components such as color, verb, object, size, and spatial attribute. Our framework formalizes instruction factor bias, the tendency of fine-tuned policies to over-rely on dominant factors as shortcuts, and quantifies it through two metrics: Factor Dominance Rate (FDR), capturing pairwise bias between factors, and Factor Dominance Hierarchy (FDH), aggregating these into a global ranking. Evaluation on six foundation policies reveals broadly consistent ordering, \textit{i.e.}, color $\geq$ object $\geq$ spatial $\geq$ verb $\geq$ size, with color dominant, and verb and size most under-grounded. We further show the diagnosis is actionable: a bias-aware data collection strategy that reallocates a fixed budget toward under-grounded factors outperforms baselines in simulation and on a real robot using half the demonstrations, thereby enabling more sample-efficient and generalizable policy learning.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{qi2026scale,
title = {Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation},
author = {Yu Qi and Zhang Ye and Xinyi Xu and Yuxuan Lu and Amitoj Sandhu and Boce Hu and Haojie Huang and Jonathan Tremblay and Lawson L. S. Wong},
year = {2026},
abstract = {Compositional generalization is essential for robot to follow diverse instructions. However, pretrained policies are known to take shortcuts, deferring to salient cues rather than grounding language. We introduce a diagnostic framework that localizes this failure to individual \textbackslash{}textit\{instruction factors\}, \textbackslash{}textit\{e.g.,\} reusable semantic components such as color, verb, object, size, and spatial attribute. Our framework formalizes instruction factor bias, the tendency of fine-tuned policies to o},
url = {https://arxiv.org/abs/2607.21582},
keywords = {cs.RO, cs.CV},
eprint = {2607.21582},
archiveprefix = {arXiv},
}
{}