# MetaFold: Language-Guided Multi-Category Garment Folding Framework via Trajectory Generation and Foundation Model

arXiv: https://arxiv.org/abs/2503.08372 · HTML: https://mlsanity.com/paper/2503.08372/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2025.

## Built on by (most cited first, 5 of 5)

- [VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models](https://mlsanity.com/paper/2506.17561/) (2025)
- [FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis](https://mlsanity.com/paper/2505.09109/) (2025)
- [GarmentPile++: Affordance-Driven Cluttered Garments Retrieval with Vision-Language Reasoning](https://mlsanity.com/paper/2603.04158/) (2026)
- [Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation](https://mlsanity.com/paper/2604.05544/) (2026)
- [Exploring 6D Object Pose Estimation with Deformation](https://mlsanity.com/paper/2604.06720/) (2026)

## Abstract (arXiv)

Garment folding is a common yet challenging task in robotic manipulation. The deformability of garments leads to a vast state space and complex dynamics, which complicates precise and fine-grained manipulation. Previous approaches often rely on predefined key points or demonstrations, limiting their generalization across diverse garment categories. This paper presents a framework, MetaFold, that disentangles task planning from action prediction, learning each independently to enhance model generalization. It employs language-guided point cloud trajectory generation for task planning and a low-level foundation model for action prediction. This structure facilitates multi-category learning, enabling the model to adapt flexibly to various user instructions and folding tasks. Experimental results demonstrate the superiority of our proposed framework. Supplementary materials are available on our website: https://meta-fold.github.io/.