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

National University of Singapore(新加坡国立大学)

2026-02-19 至 2026-02-19 共收录 5
2602.16660 2026-02-19 cs.CL cs.AI cs.LG

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment

一次对齐,多语言受益:为LLM安全对齐强制多语言一致性

Yuyan Bu, Xiaohao Liu, ZhaoXing Ren, Yaodong Yang, Juntao Dai

机构 * Beijing Academy of Artificial Intelligence(北京人工智能研究院) National University of Singapore(新加坡国立大学) Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)

AI总结 本文提出一种资源高效的多语言一致性对齐方法,通过多语言一致性损失实现多语言同时对齐,提升跨语言安全性和泛化能力。

Comments Accepted by ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09103 2026-02-19 cs.RO

IMPACT: Behavioral Intention-aware Multimodal Trajectory Prediction with Adaptive Context Trimming

IMPACT: 基于适应性上下文修剪的多模态轨迹预测:行为意图感知

Jiawei Sun, Xibin Yue, Jiahui Li, Tianle Shen, Chengran Yuan, Shuo Sun, Sheng Guo, Quanyun Zhou, Marcelo H Ang

机构 * National University of Singapore(新加坡国立大学) Xiaomi EV(小米电动车)

AI总结 IMPACT提出了一种基于适应性上下文修剪的多模态轨迹预测框架,通过联合预测行为意图和轨迹,提升预测精度、可解释性和效率,并在Waymo数据集上取得优异成绩。

Comments accepted by IEEE Robotics and Automation Letters

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.10265 2026-02-19 cs.AI cs.RO

SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis

SurgRAW:基于链式推理的多智能体工作流用于机器人手术视频分析

Chang Han Low, Ziyue Wang, Tianyi Zhang, Zhu Zhuo, Zhitao Zeng, Evangelos B. Mazomenos, Yueming Jin

机构 * National University of Singapore(国立新加坡大学) Bioinformatics Institute (BII), Agency for Science, Technology and Research (A*STAR)(生物信息研究所(BII),科技研究局(A*STAR)) Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and the Department of Medical Physics and Biomedical Engineering, University College London(Wellcome/EPSRC介入与外科科学中心(WEISS)及伦敦大学学院医学物理与生物医学工程系)

AI总结 SurgRAW通过基于链式推理的多智能体工作流,在机器人手术视频分析中实现零样本多任务推理,提升准确性和临床相关性。

Journal ref IEEE Robotics and Automation Letters, 2026, pp. 1-8

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.11348 2026-02-19 cs.AI

AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition

AgentNoiseBench: 在噪声条件下评估工具使用LLM代理的鲁棒性基准测试

Ruipeng Wang, Yuxin Chen, Yukai Wang, Chang Wu, Junfeng Fang, Xiaodong Cai, Qi Gu, Hui Su, An Zhang, Xiang Wang, Xunliang Cai, Tat-Seng Chua

机构 * University of Science(科学大学) National University of Singapore, Singapore(新加坡国立大学)

AI总结 AgentNoiseBench通过在噪声环境中评估LLM代理的鲁棒性,揭示了现有模型对现实扰动的敏感性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.06207 2026-02-19 cs.RO

Toward Context-Aware Exoskeleton Assistance: Integrating Computer Vision Payload Estimation with a User-Centric Optimization Space

面向情境感知的外骨骼辅助:整合计算机视觉载荷估计与以用户为中心的优化空间

Andrea Dal Prete, Seyram Ofori, Chan Yon Sin, Ashwin Narayan, Ding Shuo, Francesco Braghin, Marta Gandolla, Haoyong Yu

机构 * Department of Mechanical Engineering, Politecnico di Milano(米兰理工学院机械工程系) Department of Biomedical Engineering, National University of Singapore(新加坡国立大学生物医学工程系) School of Science and Technology, Singapore University of Social Sciences(新加坡社会科学院科学与技术学院) College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics(南京航空航天大学机电学院)

AI总结 本文提出一种基于计算机视觉和用户优化的外骨骼辅助系统,通过预提环境感知和用户需求优化,提升工业场景中的人机交互和物理辅助效果。

详情

展开后加载摘要…

URL PDF HTML 收藏