World models aim to capture environment dynamics in ways that support perception, reasoning, and action, and have recently become a central direction in Vision-Language-Action-World (VLAW) modeling. Meanwhile, unified vision-language models have demonstrated strong multimodal generation capabilities, yet their potential as world models remains underexplored. In this work, we introduce \texttt{WorldBagel}, a unified VLAW framework built on BAGEL, a modern multimodal unified model, and use it to systematically investigate the role of unification in world modeling. Across multi-task robotic manipulation and cross-domain experiments, \texttt{WorldBagel} consistently outperforms task-specific alternatives and learns action representations that are more structured and semantically aligned with visual and linguistic context. Experiments on LIBERO, Language Table, and Franka show that unification is not only an architectural convenience, but also a key factor in learning effective VLAW models, leading to consistent empirical gains and deeper insights into multimodal world modeling. Code and model checkpoints will be released upon acceptance.
What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models
Institute of Digital Twin, Eastern Institute of Technology(数字孪生研究所,东部技术研究所);Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative(宁波空间智能与数字衍生关键实验室);Shanghai Jiao Tong University(上海交通大学);The Hong Kong Polytechnic University(香港理工大学)
Uncovering Entity Identity Confusion in Multimodal Knowledge Editing
New Laboratory of Pattern Recognition (NLPR)(模式识别新实验室);State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)(多模态人工智能系统国家重点实验室);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Beijing University of Posts and Telecommunications(北京邮电大学);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院);Huazhong University of Science and Technology(华中科技大学);Shandong University(山东大学)
Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs
Nanjing University(南京大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));China Academy of Launch Vehicle Technology(中国运载火箭技术研究院);Beihang University(北京航空航天大学)
Uncovering Intrinsic Capabilities: A Paradigm for Data Curation in Vision-Language Models
Harbin Institute of Technology, Shenzhen, China(哈尔滨工业大学(深圳));Hong Kong Baptist University, China(香港 Baptist大学);City University of Hong Kong, China(香港城市大学)
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
University of Virginia(弗吉尼亚大学);Purdue University(普渡大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Georgia Institute of Technology(佐治亚理工学院)
GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing
RIKEN AIP(日本理化学研究所革新智能研究中心);Wuhan University(武汉大学);Linköping University(林雪平大学);University of Tokyo(东京大学);Nanjing University of Information Science and Technology(南京信息工程大学)
TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts
OpenGV Lab(OpenGV实验室);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院)
Advancing Object Detection in Transportation with Multimodal Large Language Models (MLLMs): A Comprehensive Review and Empirical Testing
Arab American University(阿拉伯美国大学);Columbia University(哥伦比亚大学);Budapest University of Technology and Economics(布达佩斯技术与经济大学);Al-Ahliyya Amman University(阿赫利耶阿曼大学);Queensland University of Technology(昆士兰科技大学)
SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China(电子科技大学深圳研究院);Southwestern University of Finance and Economics(西南财经大学);Engineering Research Center of Intelligent Finance, Ministry of Education(教育部智能金融工程研究中心);Tongji University(同济大学)
The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework
Nanyang Technological University(南洋理工大学);Beijing University of Technology(北京理工大学);Hengxin Tech(恒心科技);Alibaba Group(阿里巴巴集团);Squirrel Ai Learning(squirrel AI 学习)
Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers
Cognitive Computational Neuroscience Group, Patter Recognition Lab, University Erlangen-Nürnberg(认知计算神经科学组、模式识别实验室、埃尔兰根-纽伦堡大学);IDS Institut für Data Science, ZHAW School of Engineering, Winterthur, Switzerland(IDS数据科学研究所、ZHAW工程学院、温特图尔,瑞士);Mannheim Center for Neuromodulation and Neuroprosthetics, University Hospital Mannheim, Heidelberg University(曼海姆神经调制与神经假体中心、曼海姆大学医院、海德堡大学);BGU Ludwigshafen, Germany(BGU路易斯港,德国);Physics and Cognition Group, MCNN, University Hospital Mannheim, Heidelberg University(物理与认知组、MCNN、曼海姆大学医院、海德堡大学);NeuroAI and BCI Group, MCNN, University Hospital Mannheim, Heidelberg University(神经AI与BCI组、MCNN、曼海姆大学医院、海德堡大学)
MAIRA-1: A specialised large multimodal model for radiology report generation
Health Futures, Microsoft Research(微软研究院健康未来部门);Microsoft Research India(微软研究院印度分部);Microsoft Azure AI(微软Azure人工智能);Microsoft Health and Life Sciences(微软健康与生命科学部门)