Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computationally efficient. Vision-Language Models (VLMs) have emerged as the primary reward provider, leveraging their rich multimodal priors to guide alignment. However, their computation and memory cost can be substantial, and optimizing a latent diffusion generator through a pixel-space reward introduces a domain mismatch that complicates alignment. In this paper, we propose DiNa-LRM, a diffusion-native latent reward model that formulates preference learning directly on noisy diffusion states. Our method introduces a noise-calibrated Thurstone likelihood with diffusion-noise-dependent uncertainty. DiNa-LRM leverages a pretrained latent diffusion backbone with a timestep-conditioned reward head, and supports inference-time noise ensembling, providing a diffusion-native mechanism for test-time scaling and robust rewarding. Across image alignment benchmarks, DiNa-LRM substantially outperforms existing diffusion-based reward baselines and achieves performance competitive with state-of-the-art VLMs at a fraction of the computational cost. In preference optimization, we demonstrate that DiNa-LRM improves preference optimization dynamics, enabling faster and more resource-efficient model alignment.
MVR: Multi-view Video Reward Shaping for Reinforcement Learning
School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院);State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室)
Revisiting Change VQA in Remote Sensing with Structured and Native Multimodal Qwen Models
Computer Engineering Department, College of Computer and Information Sciences, King Saud University(计算机工程系,计算机与信息科学学院,沙特国王大学);Applied Computer Science Department, College of Applied Computer Science, King Saud University(应用计算机科学系,应用计算机科学学院,沙特国王大学)
Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
School of Software, Beihang University(北京航空航天大学软件学院);Shanghai Innovation Institute(上海创新研究院);Shanghai AI Laboratory(上海人工智能实验室);Tsinghua University(清华大学)
SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understanding
College of Computer Science and Technology, Jilin University, China(吉林大学计算机科学与技术学院);Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education(教育部符号计算与知识工程重点实验室)
Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment
Northwestern Polytechnical University(西北工业大学);Southern University of Science and Technology(南方科技大学);The University of Sheffield(谢菲尔德大学);Hengqin Laboratory(横琴实验室);Tsinghua University(清华大学)
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)
MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models
School of Intelligent Science and Technology, Nanjing University, China(南京大学智能科学与技术学院);National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, China(南京大学新型软件技术国家实验室,人工智能学院);School of Artificial Intelligence, Nanjing University, China(南京大学人工智能学院);MACS Lab, University of Washington(华盛顿大学MACS实验室)
Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language Models
School of Information Science and Technology, University of Science and Technology of China(信息科学与技术学院,中国科学技术大学);Institute of Artificial Intelligence (TeleAI), China Telecom(人工智能研究所(TeleAI),中国电信);College of Future Information Technology, Fudan University(未来信息技术学院,复旦大学);College of Computer Science, Wuhan University(计算机科学学院,武汉大学)
SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
Peking University(北京大学);MIT(麻省理工学院);TUM(技术大学(TUM));Meituan(美团);Peking University School of CIT, MCML, MDSIEECS and CSAIL(北京大学计算机学院、MCML、MDSIEECS以及CSAIL)