Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to fine-grained spatial relationships, often producing images that appear plausible overall yet contain inaccuracies in object positioning. In this work, we present \textbf{SpatialReward}, a verifiable reward model explicitly designed to evaluate spatial layouts in generated images. SpatialReward adopts a multi-stage pipeline: a \emph{Prompt Decomposer} extracts entities, attributes, and spatial metadata from free-form prompts; expert detectors provide accurate visual grounding of object positions and attributes; and a vision-language model applies chain-of-thought reasoning over grounded observations to assess complex spatial relations that are challenging for rule-based methods. To more comprehensively evaluate spatial relationships in generated images, we introduce \textbf{SpatRelBench}, a benchmark covering object attributes, orientation, inter-object relations, and rendered text placement. Experiments on Stable Diffusion and FLUX show that incorporating SpatialReward into RL training consistently improves spatial consistency and overall generation quality, with results aligned more closely to human judgments. These findings indicate that verifiable reward models hold considerable potential for enabling more accurate and controllable optimization in text-to-image generation models.
SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));The Hong Kong University of Science and Technology(香港科学与技术大学);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生学院,清华大学)
Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base
Lanzhou Center for Theoretical Physics, Key Laboratory of Theoretical Physics of Gansu Province, Key Laboratory of Quantum Theory and Applications of MoE, Gansu Provincial Research Center for Basic Disciplines of Quantum Physics(兰州理论物理中心、甘肃省理论物理重点实验室、教育部量子理论与应用重点实验室、甘肃省量子物理基础学科研究省重点中心);Institute of Theoretical Physics, Chinese Academy of Sciences(中国科学院理论物理研究所);DP Technology(DP技术);Institute of Physics, Chinese Academy of Sciences(中国科学院物理研究所);Département d’Informatique, École normale supérieure(巴黎高等师范大学计算机系)
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Nanyang Technological University(南洋理工大学);University of California, Berkeley(加州大学伯克利分校);University of California, San Diego(加州大学圣地亚哥分校);The University of Tokyo(东京大学);The Chinese University of Hong Kong(香港中文大学);University of Michigan(密歇根大学);Johns Hopkins University(约翰霍普金斯大学);University of California, Davis(加州大学戴维斯分校);University of California, Los Angeles(加州大学洛杉矶分校);Carnegie Mellon University(卡内基梅隆大学);Columbia University(哥伦比亚大学);University of Toronto(多伦多大学)
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
ByteDance Seed(字节跳动种子);Fudan University(复旦大学);Institute for AI Industry Research (AIR), Tsinghua University(人工智能产业研究院(AIR),清华大学);Nanjing University(南京大学);Shanghai Jiao Tong University(上海交通大学);SIA-Lab of Tsinghua AIR and ByteDance Seed(清华大学AIR实验室和字节跳动种子)
GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning
The Hong Kong Polytechnic University(香港理工大学);Shenzhen University(深圳大学);West China Hospital of Sichuan University(四川大学华西医院);IHPC, Agency for Science, Technology and Research(科技研究局IHPC)
Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
Key Laboratory of Network Data Science(网络数据科学实验室);Technology, Institute of Computing Technology, Chinese Academy of Sciences(技术,计算技术研究所,中国科学院);State Key Laboratory of AI Safety(人工智能安全国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);University of California, Merced(加州大学梅尔塞德斯分校)
Tsinghua University(清华大学);Meituan Inc(美团公司);Central South University(中南大学);Peking University(北京大学);University of Chinese Academy of Sciences(中国科学院大学);Nanyang Technological University(南洋理工大学)
GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision
College of Computer Science and Technology(计算机科学与技术学院);Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University(教育部符号计算与知识工程重点实验室)
CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency
School of Computer Science and Technology, Xidian University(西安电子科技大学计算机科学与技术学院);Warren Alpert Medical School of Brown University(布朗大学沃伦·阿尔珀特医学学院);School of Biomedical Engineering, Capital Medical University(首都医科大学生物医学工程学院)