{"ID":5937902,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T06:28:03.218458835Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03732","arxiv_id":"2607.03732","title":"ProxyUp: Training-Free Proxy-Conditioned Video Generation for Controllable Dynamics","abstract":"Precise control over complex dynamics remains challenging for modern video generative models, as text prompts alone often cannot specify physically plausible, fine-grained motion and interactions. We introduce $\\textit{proxy-conditioned video generation}$, where a coarse proxy video from physics-based simulation or real-world recording serves as a dynamics carrier to control foreground object motion. Given a proxy video and a text prompt, the goal is to synthesize a new video that preserves the proxy dynamics while generating novel content and plausible interactions aligned with the prompt. Since paired proxy-target videos are difficult to obtain, we propose $\\textbf{ProxyUp}$, a training-free framework built on pretrained video generative models. ProxyUp first inverts the proxy video into an intermediate latent representation and applies $\\textbf{region-wise latent noising}$, preserving motion-critical proxy latents while injecting noise into regions intended for text-driven regeneration. To mitigate the distribution mismatch and weak foreground-background coupling introduced by this heuristic latent composition, we further propose $\\textbf{Stochastic Flow Relaxation (SFR)}$, which progressively relaxes the composed latent toward the model's learned distribution before ODE sampling. Experiments on both simulation and real-world proxies show that ProxyUp outperforms strong video editing and motion transfer baselines in dynamic fidelity and text alignment.","short_abstract":"Precise control over complex dynamics remains challenging for modern video generative models, as text prompts alone often cannot specify physically plausible, fine-grained motion and interactions. We introduce $\\textit{proxy-conditioned video generation}$, where a coarse proxy video from physics-based simulation or rea...","url_abs":"https://arxiv.org/abs/2607.03732","url_pdf":"https://arxiv.org/pdf/2607.03732v1","authors":"[\"Zanwei Zhou\",\"Jiazhong Cen\",\"Jiemin Fang\",\"Yumeng He\",\"Chen Yang\",\"Sikuang Li\",\"Fanpeng Meng\",\"Zhikuan Bao\",\"Wei Shen\",\"Qi Tian\"]","published":"2026-07-04T06:39:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}