Metraipolis › archive › dc_bfab93a8299c
Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models — arXiv:2608.04633
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04633
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:50:01.667Z
- SHA-256 of the archived text
c0c84dc972d4d6e40e55c394dd18b9e150fbc2f34fa76e541aa257465b3456a4- Stable URL of this page
https://metraipolis.com/documento/dc_bfab93a8299c
How to cite
Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models — arXiv:2608.04633 — arXiv (en), https://arxiv.org/abs/2608.04633 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bfab93a8299c (Metraipolis archive dc_bfab93a8299c, sha256 c0c84dc972d4d6e40e55c394dd18b9e150fbc2f34fa76e541aa257465b3456a4)
BibTeX
@misc{dcbfab93a8299c,
title = {Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models — arXiv:2608.04633},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04633},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bfab93a8299c; sha256 c0c84dc972d4d6e40e55c394dd18b9e150fbc2f34fa76e541aa257465b3456a4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04633. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent Vision-Language-Action (VLA) methods improve generalization by aligning their representations with 3D scene geometry. However, these methods are fundamentally instruction-agnostic: the representations align the entire scene uniformly, neglecting the 3D geometry of the specific target object designated by the language instruction. This causes failures on fine-grained manipulation and target occlusion tasks, where success depends on accurate 3D understanding of the target object rather than the entire scene. To address this, we present Mind-VLA, an instruction-aware spatial representation alignment method for VLA models. Specifically, Mind-VLA first obtains the target object specified by the language instruction, then prepares its canonical target views and extracts the corresponding VAE and VGGT features. Finally, the latent representation of the VLA model is aligned with these features to enable instruction-aware 3D understanding. Mind-VLA reaches 94.4% on LIBERO and 4.47 on CALVIN with a compact 345M-parameter backbone. On real-robot tasks with target occlusion, Mind-VLA reaches 54% average success, outperforming the matched scene-VGGT control by 26 percentage points. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.04633 — 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 2026-10-31T11:39:29.939Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).