The Hong Kong University of Science and Technology（香港科技大学）

MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning

MultivationBench：多模态序列动机推理基准

Kawai Chung, Chunkit Chan, Yauwai Yim, Yuxuan Liu, Haochen Shi, Weiqi Wang, Qing Zong, Tianshi Zheng, Yixuan Fu, Kai Chung Wong, Hao Liang, Yifan Gao, Xi Yang, Janet Hui-wen Hsiao, Yangqiu Song

机构 * The Hong Kong University of Science and Technology（香港科技大学） 纠错

AI总结 本文提出MultivationBench基准，基于心理学框架评估多模态序列动机推理，发现现有模型难以在序列语境中保持一致的动机推理，暴露了静态识别与动态推理的差距。

Comments 31 pages, including appendices; 6 figures and 22 tables. Code: https://github.com/HKUST-KnowComp/MultivationBench

CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games

CaM-Wolf：面向社交推理游戏的因果感知多模态智能体

Zheng Zhang, Nanjie Yao, Jiarui He, Deheng Ye, Peilin Zhao, Hao Wang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Nanyang Technological University（南洋理工大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

AI总结 该研究针对现有SDG智能体多模态特性缺失的问题，提出首个整合多模态感知生成的CaM-Wolf，经实验验证其游戏性能与交互质量均有提升。

Comments Accepted by ACMMM 2026

Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels

面向可信赖的具身智能：一个系统框架与分级可信赖性水平

Xinyu Yang, Tianxing Chen, Honghao Su, Minxuan Wang, Chenze Yu, Zhangzheng Tu, Yue Chen, Yuxiao Huo, Lingfeng Zhang, Yan Huang, Yan Qin, Shaolong Zhu, Qiwei Liang, Hekun Tian, Shujia Liu, Guangyu Chen, Junhao Gong, Zixuan Li, Wenwei Lin, Zijian Lin, Wenxuan Zhu, Eric J Chen, Yue Yuan, Qize Yu, Jiaqi Liang, Haowen Yan, Hengfei Zhao, Weijie Wan, Zikun Xiao, Junyuan Tang, Baijun Chen, Kai-Chong Lei, Kaixuan Wang, Kailun Su, Zanxin Chen, Yao Mu, Renjing Xu, Chuqiao Lyu, Qi Xiong, Ping Luo, Wenbo Ding

机构 * THU（清华大学） ； PKU（北京大学） ； HKUST (GZ)（香港科技大学（广州）） 纠错

AI总结 该研究提出具身智能可信赖性的四层系统框架，构建涵盖多维度的可信赖性水平层级，为具身智能的可信赖部署、评估等提供依据。

Comments Website: https://xsparkai.com/sparklab/towards-trustworthy-eai