Metraipolis › archive › dc_93cb7da39067
ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models — arXiv:2609.07581
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07581
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:31:11.918Z
- SHA-256 of the archived text
3008d01f4b9a8eb88822216944933956bfb68d9d71797e6a45fa6cb16024744d- Stable URL of this page
https://metraipolis.com/documento/dc_93cb7da39067
How to cite
ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models — arXiv:2609.07581 — arXiv (en), https://arxiv.org/abs/2609.07581 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_93cb7da39067 (Metraipolis archive dc_93cb7da39067, sha256 3008d01f4b9a8eb88822216944933956bfb68d9d71797e6a45fa6cb16024744d)
BibTeX
@misc{dc93cb7da39067,
title = {ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models — arXiv:2609.07581},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07581},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_93cb7da39067; sha256 3008d01f4b9a8eb88822216944933956bfb68d9d71797e6a45fa6cb16024744d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07581. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language-Action (VLA) policies are commonly adapted to new manipulation settings through additional gradient updates, which limits rapid deployment when task-specific data or compute is scarce. We present ICI-VLA, a training and retrieval framework that equips a text-action VLM with few-shot test-time adaptation through in-context demonstrations. Unlike mainstream VLA designs based on action-specific multimodal fusion, ICI-VLA retains the native text-generation interface. ICI-VLA updates its parameters only during offline training; at inference, the policy remains fixed and conditions action generation on retrieved micro-demonstrations. The framework decomposes long trajectories into short, semantically labeled examples and trains an RD-Encoder with positives mined by Dynamic Time Warping (DTW), aligning the retrieved context with the phase and geometry of the current subtask. We further introduce Target Action Masking, a context-corruption objective designed to reduce direct action copying and increase reliance on the current observation. ICI-VLA reaches average success rates of 97.7% on LIBERO and 60.4% on RoboTwin 2.0, exceeding the highest reported baseline average on RoboTwin 2.0 by 19.3 percentage points. It also achieves 83.2% across four physical tasks. These results indicate that a fixed VLA policy can benefit from conditioning on spatiotemporally aligned demonstrations at test time. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.07581 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T15:11:47.603Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).