paper-with-me

Papers

Value Gradient Guidance for Flow Matching Alignment

2025-12-04 · Zhen Liu, Tim Z. Xiao, Carles Domingo-Enrich, Weiyang Liu, Dinghuai Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.05116

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GRASP: Guided Residual Adapters with Sample-wise Partitioning

2025-12-01 · Felix Nützel, Mischa Dombrowski, Bernhard Kainz arxiv

Text-to-image flow matching transformers degrade sharply in long-tail settings: tail-class outputs collapse in fidelity and diversity, limiting their value as synthetic augmentation for rare conditions. We trace this to …

On the Guidance of Flow Matching

2025-02-04 · Ruiqi Feng, Tailin Wu, Chenglei Yu, Wenhao Deng 외

Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where guided generation is pivotal. However, the guidance of flow matching is more gener…

Decision MakingImage Generation

Improving Classifier-Free Guidance of Flow Matching via Manifold Projection

2026-01-29 · Jian-Feng Cai, Haixia Liu, Zhengyi Su, Chao Wang arxiv

Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirical success, CFG relies on a heuristic linear extrapolation that is often sensit…

Computational Efficiency

Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation

2026-01-31 · Yidong Ouyang, Liyan Xie, Hongyuan Zha, Guang Cheng arxiv

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given …

Text-to-Image Generation

Q-VGM: Q-Value-Gradient Matching for Offline-to-Online Reinforcement Learning of Flow-Matching VLA

2026-06-06 · Ziqian Wang, Jiayu Sun, Xingjian Mao, Minqian Wang 외 arxiv

We propose Q-Guided Value-Gradient Matching (Q-VGM), an offline-to-online reinforcement learning (RL) method for fine-tuning flow-matching vision-language-action (VLA) policies with a learned Q-function. Classical off-po…

Reinforcement Learning