[
    {
        "id": "osp-17744",
        "type": "article-journal",
        "title": "Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training",
        "author": [
            {
                "family": "Huang",
                "given": "Hong"
            },
            {
                "family": "Liu",
                "given": "Yuqiu"
            },
            {
                "family": "You",
                "given": "Chenyu"
            },
            {
                "family": "Martin",
                "given": "Daniel"
            },
            {
                "family": "Zou",
                "given": "Chuhang"
            },
            {
                "family": "Chen",
                "given": "Wuyang"
            }
        ],
        "URL": "https://omanscience.com/en/articles/fluid-gen-zero-grounding-pretrained-video-generators-in-physics-without-training",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "We present Fluid-Gen-Zero, a training-free framework for physics-aware fluid-object interaction video generation that decouples physical reasoning from appearance synthesis. Our key insight is to delegate motion dynamics to a physics simulator while preserving the appearance modeling capacity of pretrained video generators. We bridge these two domains through a two-level agentic workflow: generation-time planning, where a vision-language model (VLM) agent interprets intent and the simulation rollout to organize generation clips, and latent-space guidance, which injects simulation signals into denoising through region-aware latent wrapping. This plug-and-play design is compatible with current video foundation models. We further introduce a benchmark for fluid-object interaction video generation. Across Tora (CogVideoX-based), VACE and WanMove (Wan-based), Fluid-Gen-Zero consistently improves simulation alignment, reducing object trajectory error by 26.7%-81.5% and fluid fEPE (fluid flow endpoint error) by 67.9%-84.0%, while largely preserving perceptual quality. In a human preference study, raters favor Fluid-Gen-Zero in 55.1%-74.4% of same-backbone comparisons across three backbones, and in 90.4%-94.2% of comparisons against simulation-based methods. Code and data will be released upon acceptance."
    }
]