Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. Models often struggle to satisfy multiple concepts within a single prompt, frequently omitting some concepts and resulting in partial success. Such failures highlight the difficulty of jointly optimizing multiple concepts during reward optimization, where competing concepts can interfere with one another. To address this limitation, we propose Correlation-Weighted Multi-Reward Optimization (CMO), a framework that leverages the correlation structure among concept rewards to adaptively weight each attribute concept in optimization. By accounting for interactions among concepts, CMO balances competing reward signals and emphasizes concepts that are partially satisfied yet inconsistently generated across samples, improving compositional generation. Specifically, we decompose multi-concept prompts into pre-defined concept groups (e.g., objects, attributes, and relations) and obtain reward signals from dedicated reward models for each concept. We then adaptively reweight these rewards, assigning higher weights to conflicting or hard-to-satisfy concepts using correlation-based difficulty estimation. By focusing optimization on the most challenging concepts within each group, CMO encourages the model to consistently satisfy all requested attributes simultaneously. We apply our approach to train state-of-the-art diffusion models, SD3.5 and FLUX.1-dev, and demonstrate consistent improvements on challenging multi-concept benchmarks, including ConceptMix, GenEval 2, and T2I-CompBench. The code is available at https://github.com/TheDarkKnight-21th/CMO.
CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction
National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）；University of Cambridge（剑桥大学）；University of Toronto（多伦多大学）
BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China（知识驱动人机智能工程研究中心，教育部，中国）；International Center of Future Science, Jilin University（未来科学国际中心，吉林大学）
Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards
Smart Systems Institute, National University of Singapore, Singapore（新加坡国立大学智能系统研究所）；Faculty of Computing, Harbin Institute of Technology, Harbin, China（哈尔滨工业大学计算机学院）；School of Computing, National University of Singapore, Singapore（新加坡国立大学计算机学院）
University of Stuttgart Department of Computer Science, Germany（斯图加特大学计算机科学系，德国）；KIT Department of Computer Science, Germany（卡尔斯鲁厄理工学院计算机科学系，德国）；Fraunhofer IOSB of Fraunhofer-Gesellschaft, Germany（弗劳恩霍夫研究所IOSB分部，德国）；University of Southampton Department of Computer Science, United Kingdom（南安普顿大学计算机科学系，英国）
RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment
Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Qwen LLM Application Team, Alibaba（阿里巴巴Qwen大模型应用团队）；Stanford University（斯坦福大学）
CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院）；School of Computer Science（计算机科学学院）；Technology, Hangzhou Dianzi University（技术，杭州电子科技大学）
Learning to Reason About Implicit Multimodal Harm: From Diagnosis to Generalization
Max Planck Institute for Informatics（马克斯·普朗克院信息研究所）；Saarland Informatics Campus（萨尔兰州信息校园）；Saarland University（萨尔兰州大学）；The University of Edinburgh（爱丁堡大学）；Samsung AI Center, Cambridge（三星AI中心，剑桥）
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
Huazhong University of Science and Technology（华中科技大学）；Kuaishou Technology（快手科技）；Nanyang Technological University（南洋理工大学）；Wuhan University（武汉大学）；Tsinghua University（清华大学）
