Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards

Computer Science > Artificial Intelligence [Submitted on 20 May 2026] Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards Xuehui Yu, Fucheng Cai, Meiyi Wang, Xiaopeng Fan, Harold Soh Inference-time guided sampling steers state-of-the-art diffusion and flow models without fine-tuning by interpreting the generation process as a controllable trajectory. This provides a simple and flexible way to inject external constraints (e.g., cost functions or pre-trained verifiers) for controlled generation. However, existing methods often fail when composing multiple constraints simultaneously, which leads to deviations from the true data manifold. In this work, we identify root causes of this off-manifold drift and find that the approximation error scales severely with gradient misalignment. Building on these findings, we propose Conflict-Aware Additive Guidance (g^\text{car}), a lightweight and learnable method, which actively rectifies off-manifold drift by dynamically detecting and resolving gradient conflicts. We validate g^\text{car} across diverse domains, ranging from synthetic datasets and image editing to generative decision-making for planning and control. Our results demonstrate that g^\text{car} effectively rectifies off-manifold drift, surpassing baselines in generation fidelity while using light compute. Code is available at this https URL. Comments: Forty-Third International Conference on Machine Learning (ICML 2026) Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Robotics (cs.RO) Cite as: arXiv:2605.20758 [cs.AI]   (or arXiv:2605.20758v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.20758 Focus to learn more Submission history From: Xuehui Yu [view email] [v1] Wed, 20 May 2026 05:56:55 UTC (11,025 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.CV cs.LG cs.RO References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)