Metraipolis › archive › dc_45ef8ef7d0d0

HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation — arXiv:2610.02197

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02197
License (as archived)
CC0-1.0
Archived
2026-10-06T19:15:48.686Z
SHA-256 of the archived text
2a12893998936d2ec829d29cbba905d457dff5344df4328c8643966c39677960
Stable URL of this page
https://metraipolis.com/documento/dc_45ef8ef7d0d0

How to cite

HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation — arXiv:2610.02197 — arXiv (en), https://arxiv.org/abs/2610.02197 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45ef8ef7d0d0 (Metraipolis archive dc_45ef8ef7d0d0, sha256 2a12893998936d2ec829d29cbba905d457dff5344df4328c8643966c39677960)
BibTeX
@misc{dc45ef8ef7d0d0,
  title = {HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation — arXiv:2610.02197},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02197},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45ef8ef7d0d0; sha256 2a12893998936d2ec829d29cbba905d457dff5344df4328c8643966c39677960},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02197. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video generation models have achieved remarkable visual fidelity and have strong potential to become general-purpose world simulators. Despite this progress, they still fail to generate videos which adhere to laws of physics. The problem becomes even more apparent in realistic settings where multiple physical principles must work together within the same video; for example, "a balloon floating upward while steam rises from a pot" requires buoyancy and fluid dynamics to unfold coherently and simultaneously. Yet existing methods largely ignore multi-principle interactions, focusing on a single principle per video. We propose HiPhy (Hierarchical Physical Alignment), a reinforcement learning framework that grounds video generation in physical laws through a dual-level objective: locally enforcing the temporal dynamics of individual physical principles, and globally ensuring the physical and semantic coherence of the entire scene. To support multi-principle generation, we construct a 50K-prompt dataset and introduce a prompt benchmark MultiPhyBench, spanning a diverse range of co-occurring physical events. Our experiments show that HiPhy significantly outperforms prior methods and baselines, improving physical commonsense and semantic alignment significantly across various benchmarks, with the largest gains on scenes involving multiple concurrent physical principles where competing methods degrade most sharply.

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).
Pagina del lavoro: https://arxiv.org/abs/2610.02197 — 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 2026-10-06T17:37:36.896Z 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).