Metraipolis › archive › dc_3d5a19d992fa
AcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction — arXiv:2608.28491
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28491
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:47:41.042Z
- SHA-256 of the archived text
6144f87ce44d5559693ee951209ed5fcf6edb5881a752611ff1d8cbe0337e7ab- Stable URL of this page
https://metraipolis.com/documento/dc_3d5a19d992fa
How to cite
AcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction — arXiv:2608.28491 — arXiv (en), https://arxiv.org/abs/2608.28491 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d5a19d992fa (Metraipolis archive dc_3d5a19d992fa, sha256 6144f87ce44d5559693ee951209ed5fcf6edb5881a752611ff1d8cbe0337e7ab)
BibTeX
@misc{dc3d5a19d992fa,
title = {AcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction — arXiv:2608.28491},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28491},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d5a19d992fa; sha256 6144f87ce44d5559693ee951209ed5fcf6edb5881a752611ff1d8cbe0337e7ab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28491. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Predicting robot videos requires both precise motion reasoning and preservation of high-frequency appearance, yet monolithic pixel models entangle these objectives and often conceal their progress behind a strong last-frame baseline. We present AcrossVAM1.0, a lightweight, text-assisted video action model that factorizes future prediction into object-centric motion and dense appearance. A frozen SAM3-DLP codec decomposes four context frames into semantic particles for the robot, arm, and gripper, together with a background latent. A 0.28M-parameter spatio-temporal Transformer aligns particle identities, rolls their states forward, and is modulated by a frozen OpenCLIP instruction embedding through FiLM. A causal dual-stream decoder combines particle-rendered motion with appearance encoded exclusively from the last observed frame; a residual refiner and learned delivery mask produce five future frames without access to future appearance. On our VRS benchmark constructed from diverse real-robot trajectories, particle dynamics reduce trajectory error by 21.0\% over persistence. Across three delivery-mask seeds, AcrossVAM1.0 improves future-frame PSNR/SSIM from 19.97/0.796 to 20.573/0.8004, while raw particle generation improves motion-region PSNR from 11.89 to 13.23. The delivered model does not yet beat persistence in LPIPS, and correct-versus- shuffled language changes trajectory error by only 2.8--3.1%. We report these limitations alongside oracle, negative-control, multi-seed, and per-robot analyses. The results show that explicit particle dynamics are a promising low-dimensional interface for robot video prediction, while robust language grounding and appearance delivery remain the principal open challenges. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.28491 — 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 2026-10-17T10:33:42.432Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).