Metraipolis › archive › dc_294dcbe06af9

Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination — arXiv:2610.02626

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02626
License (as archived)
CC0-1.0
Archived
2026-10-06T09:06:58.554Z
SHA-256 of the archived text
9ad2a2db5b259300b0817cf649961bc3084e94047a98a9329f0a35ec8356696f
Stable URL of this page
https://metraipolis.com/documento/dc_294dcbe06af9

How to cite

Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination — arXiv:2610.02626 — arXiv (en), https://arxiv.org/abs/2610.02626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_294dcbe06af9 (Metraipolis archive dc_294dcbe06af9, sha256 9ad2a2db5b259300b0817cf649961bc3084e94047a98a9329f0a35ec8356696f)
BibTeX
@misc{dc294dcbe06af9,
  title = {Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination — arXiv:2610.02626},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02626},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_294dcbe06af9; sha256 9ad2a2db5b259300b0817cf649961bc3084e94047a98a9329f0a35ec8356696f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) models increasingly incorporate intermediate reasoning to improve robotic manipulation, yet existing approaches primarily reason about observed states without explicitly anticipating future scene evolution. Extending such reasoning to explicit future rollouts at every inference step, however, introduces substantial computational overhead. We propose IG-VLA, a VLA reasoning framework that enables models to imagine the future and internalize the gist. Our Latent Spatiotemporal Reasoning learns to imagine task-relevant future scene evolution directly in visual representation space, guiding action prediction without costly pixel-level video generation. To further reduce inference overhead, we introduce Scene Gist Memory, which internalizes reasoning-derived scene-behavior associations into a compact Scene Gist Token, preserving the benefits of future reasoning while bypassing explicit future imagination at inference. Extensive experiments on LIBERO, LIBERO-Plus, and VLABench demonstrate the effectiveness and efficiency of IG-VLA. On the LIBERO-Plus Language suite, both the reasoning and gist policies outperform the strongest baseline by nearly 6% in success rate. The gist policy also achieves up to 6.38x speedup over baselines, reducing inference latency from 1081ms to 169.5ms per action chunk on a single NVIDIA A6000 GPU. These results demonstrate that future spatiotemporal reasoning can be effectively internalized for efficient VLA deployment.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.02626 — 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 2026-10-06T08:21:44.158Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).