arXiv：cs.AI· Yilong Wang, Cheng Qian, Edward Johns·· 5 小时前
Instant-Fold：面向可变形物体操作的上下文模仿学习框架
Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation
AI 导读
Instant-Fold 是一个面向可变形物体操作（DOM）的上下文模仿学习框架，仅需单次人类演示即可推断并执行多种操作模式，且无需梯度更新。该方法先通过时序对比预训练学习形变感知视觉表示，再用以演示为条件的流匹配 Transformer 策略预测动作。模型完全在仿真中训练，可泛化到多种折叠模式，并零样本迁移到真实环境，无需额外数据采集或微调。
正文
Abstract:Deformable object manipulation (DOM) is challenging due to high-dimensional, partially observable states that evolve through long-horizon, topology-changing interactions with multiple valid manipulation modes. We introduce Instant-Fold, an in-context imitation learning framework for DOM. Given a single human demonstration, our policy infers and executes diverse manipulation modes directly from the demonstration, including variations in spatial execution and ordering, without requiring gradient updates. Our approach first learns deformation-aware visual representations via temporal contrastive pretraining, after which a flow-matching transformer policy conditioned on the demonstration predicts actions to execute the intended manipulation mode. Trained entirely in simulation, Instant-Fold generalizes across diverse folding modes and transfers zero-shot to real-world settings without additional data collection or finetuning. Videos are available at this https URL.
| Comments: | Accepted at CoRL 2026. Project Webpage: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2606.04269 [cs.RO] |
| (or arXiv:2606.04269v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2606.04269 arXiv-issued DOI via DataCite |
Submission history
From: Yilong Wang [view email]
[v1]
Tue, 2 Jun 2026 22:46:20 UTC (25,188 KB)
[v2]
Sun, 11 Oct 2026 23:29:11 UTC (25,189 KB)
来源：arXiv：cs.AI · arxiv.org