Metraipolis › archive › dc_cd18e689c902
GenDSR: Transferring Representations from Video Generation Models for Dynamic Spatial Reasoning — arXiv:2610.41314
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41314
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T07:23:35.795Z
- SHA-256 of the archived text
24829852fa501ee03863bca961f2a8ace887e1d6e6820f9fdef2711825fc90ec- Stable URL of this page
https://metraipolis.com/documento/dc_cd18e689c902
How to cite
GenDSR: Transferring Representations from Video Generation Models for Dynamic Spatial Reasoning — arXiv:2610.41314 — arXiv (en), https://arxiv.org/abs/2610.41314 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd18e689c902 (Metraipolis archive dc_cd18e689c902, sha256 24829852fa501ee03863bca961f2a8ace887e1d6e6820f9fdef2711825fc90ec)
BibTeX
@misc{dccd18e689c902,
title = {GenDSR: Transferring Representations from Video Generation Models for Dynamic Spatial Reasoning — arXiv:2610.41314},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41314},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd18e689c902; sha256 24829852fa501ee03863bca961f2a8ace887e1d6e6820f9fdef2711825fc90ec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41314. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dynamic spatial reasoning is essential for connecting visual intelligence to thephysical world, yet remains challenging for vision-language models (VLMs), which must preserve scene state while tracking how spatial relations evolve over time. Meanwhile, video generation models (VGMs), trained to synthesize temporally coherent world dynamics, offer a rich source of spatiotemporal representations. We present GenDSR, a framework that transfers intermediate representations from VGM into VLM for dynamic spatial reasoning. Rather than treating a VGM feature as a monolithic prior, GenDSR constructs two complementary branches: a raw branch preserving holistic generative context and a delta branch emphasizing temporal variation. Task-conditioned tokenwise gates then fuse both signals and inject the result into the native visual representation. On DSR-Bench, GenDSR achieves 67.2%, surpassing the previous best result and establishing a new state of the art. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.41314 — 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 2026-11-03T07:19:48.904Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).