Metraipolis › archive › dc_cc31570984e1
FutureWorlds: Learning Robotic World Models from Alternative Futures — arXiv:2610.01019
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01019
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T19:12:11.869Z
- SHA-256 of the archived text
1c41f020ad88deeb79d19cd543df3341710d3f8eb2519e2fec06e25a98cde7f7- Stable URL of this page
https://metraipolis.com/documento/dc_cc31570984e1
How to cite
FutureWorlds: Learning Robotic World Models from Alternative Futures — arXiv:2610.01019 — arXiv (en), https://arxiv.org/abs/2610.01019 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc31570984e1 (Metraipolis archive dc_cc31570984e1, sha256 1c41f020ad88deeb79d19cd543df3341710d3f8eb2519e2fec06e25a98cde7f7)
BibTeX
@misc{dccc31570984e1,
title = {FutureWorlds: Learning Robotic World Models from Alternative Futures — arXiv:2610.01019},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01019},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc31570984e1; sha256 1c41f020ad88deeb79d19cd543df3341710d3f8eb2519e2fec06e25a98cde7f7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01019. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robotic world models predict action-conditioned future scenes, providing a foundation for understanding action outcomes. However, turning alternative predictions into useful learning signals remains challenging: similar candidates limit informative quality comparisons, while diverging trajectories require persistent maintenance of their individual histories. We introduce FutureWorlds, a framework that unifies candidate construction, history maintenance, and learning from relative quality. Built on a multimodal discrete autoregressive model, FutureWorlds uses diverse beam search during reinforcement learning to construct candidate futures that balance confidence and diversity. Candidate-specific bounded memory preserves scene states and ensures that generation and policy scoring use matching histories. We further propose MemSPO (Memory-Conditioned Search-Guided Policy Optimization), which converts video trajectory rewards into group-relative advantages to optimize the world model. On RT-1, BridgeV2, and RoboCasa, FutureWorlds reduces LPIPS for 32-frame predictions by 14.78%, 20.84%, and 9.12%, respectively, relative to the strongest baseline on each dataset. Under fixed evaluation configurations, only 200 MemSPO updates further improve generation quality and support continued prediction beyond the training horizon. Memory ablations, decoding sensitivity analysis, and optical-flow evaluation show that these gains extend beyond visual quality to more accurate motion prediction and more consistent object states. Project page and code: this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.01019 — 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 2026-10-06T17:37:36.723Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).