arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

高校专区

Beihang University(北京航空航天大学)

2026-03-17 至 2026-03-17 共收录 3
2603.15054 2026-03-17 cs.AI

Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning

考虑干扰的多智能体强化学习中的K步可达通信

Ziyu Cheng, Jinsheng Ren, Zhouxian Jiang, Chenzhihang Li, Rongye Shi, Bin Liang, Jun Yang

机构 * School of Software, Beihang University(软件学院,北航) School of Artificial Intelligence, Beihang University(人工智能学院,北航)

AI总结 本文提出IA-KRC框架,通过K步可达协议和干扰预测模块提升多智能体协作效率,克服环境干扰,实现更持久高效的协作。

Comments multi-agent reinforcement learning, communication

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.13427 2026-03-17 cs.CV cs.AI

MIBench: Evaluating LMMs on Multimodal Interaction

MIBench: 评估大多模态模型在多模态交互中的能力

Yu Miao, Zequn Yang, Yake Wei, Ziheng Chen, Haotian Ni, Haodong Duan, Kai Chen, Di Hu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China(中国人民大学人工智能学院,北京,中国) Beijing Key Laboratory of Research on Large Models(大型模型研究关键实验室) Beihang University, Beijing, China(北京航空航天大学,北京,中国) Shanghai Artificial Intelligence Laboratory, Shanghai, China(上海人工智能实验室,上海,中国)

AI总结 MIBench通过多模态交互三元组评估大模型在多模态任务中的能力,发现模型在多模态交互上存在局限性,易受文本干扰,且在基础协同能力上表现不足。

Comments 10 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.02090 2026-03-17 cs.CV

All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmark

全天候多模态图像融合:统一框架与10万基准

Xilai Li, Wuyang Liu, Xiaosong Li, Fuqiang Zhou, Huafeng Li, Feiping Nie

机构 * Guangdong-HongKong-Macao Joint Laboratory for Intelligent MicroNano Optoelectronic Technology(粤港澳联合智能微纳光电子技术实验室) School of Physics and Optoelectronic Engineering, Foshan University(佛山大学物理与光电工程学院) Guangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology(广东省工业智能检测技术重点实验室) School of Instrumentation and Optoelectronic Engineering, Beihang University(北京航空航天大学仪器与光电工程学院) School of Information Engineering and Automation, Kunming University of Science and Technology(昆明理工大学信息工程与自动化学院) School of Artificial Intelligence, Optics and Electronics (i0PEN), School of Computer Science, Northwestern Polytechnical University(人工智能、光学与电子学院(i0PEN),西北工业大学计算机学院)

AI总结 本文提出统一的全天候多模态图像融合框架,通过联合特征融合与恢复提升关键场景信息表征,构建10万张图像对的多模态数据集,实验证明在真实和合成场景中图像融合及下游任务表现优异。

详情

展开后加载摘要…

URL PDF HTML 收藏