FineCraft: Enhancing VLA Models for Fine-Grained Manipulation
FineCraft: Enhancing VLA Models for Fine-Grained Manipulation
This research presents FineCraft, a framework designed to enhance Vision-Language-Action (VLA) models for fine-grained manipulation tasks. By utilizing a task-routed mixture of policies that selects between independently adapted DINOv2-DiT or pretrained pi_0.5 policies, the system achieves an overall score of 0.878 in the MetaFine Challenge, ranking fourth and exceeding reference performance on all five tasks. The approach integrates local visual features for object part identification, expert demonstrations for action teaching, and replanning guided by new observations. Official results and local diagnostics characterize performance under visual perturbations, instruction changes, and multi-stage manipulation scenarios.
The paper introduces FineCraft, a framework adapting pretrained models for fine-grained manipulation in the MetaFine Challenge, achieving an overall score of 0.878 and ranking fourth across five tasks while providing code and diagnostics for visual perturbations and instruction changes.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: Available Artifact link Open source S4
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ges, and multi-stage manipulation. Code is available at https://github.com/eqcy/FineCraft
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org