[2512.05116] Value Gradient Guidance for Flow Matching Alignment

Computer Science > Machine Learning arXiv:2512.05116 (cs) [Submitted on 4 Dec 2025 (v1), last revised 3 Mar 2026 (this version, v2)] Title:Value Gradient Guidance for Flow Matching Alignment Authors:Zhen Liu, Tim Z. Xiao, Carles Domingo-Enrich, Weiyang Liu, Dinghuai Zhang View a PDF of the paper titled Value Gradient Guidance for Flow Matching Alignment, by Zhen Liu and 4 other authors View PDF HTML (experimental) Abstract:While methods exist for aligning flow matching models--a popular and effective class of generative models--with human preferences, existing approaches fail to achieve both adaptation efficiency and probabilistically sound prior preservation. In this work, we leverage the theory of optimal control and propose VGG-Flow, a gradient-matching-based method for finetuning pretrained flow matching models. The key idea behind this algorithm is that the optimal difference between the finetuned velocity field and the pretrained one should be matched with the gradient field of a value function. This method not only incorporates first-order information from the reward model but also benefits from heuristic initialization of the value function to enable fast adaptation. Empirically, we show on a popular text-to-image flow matching model, Stable Diffusion 3, that our method can finetune flow matching models under limited computational budgets while achieving effective and prior-preserving alignment. Comments: Subjects: Machine Learning (cs.LG); Computer Vision and Patt...