Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning
对齐视觉与语言:无需注释的多模态知识图谱构建以增强大语言模型推理
Junming Liu, Siyuan Meng, Yanting Gao, Song Mao, Pinlong Cai, Guohang Yan, Yirong Chen, Zilin Bian, Ding Wang, Botian Shi
机构
*
Tongji University(同济大学)
;
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
;
East China Normal University(华东师范大学)
;
Stanford University(斯坦福大学)
;
New York University(纽约大学)
专题命中
推理与问题求解
:large language model(abstract);language model(abstract);分类 cs.AI
AI总结
本文提出 VaLiK 方法,通过跨模态信息补充构建无需注释的多模态知识图谱,提升大语言模型推理能力。
Comments14 pages, 7 figures, 6 tables; Accepted by ICCV 2025
Sparse Mixture-of-Experts for Multi-Channel Imaging: Are All Channel Interactions Required?
稀疏专家混合模型用于多通道成像:所有通道交互都必要吗?
Sukwon Yun, Heming Yao, Burkhard Hoeckendorf, David Richmond, Aviv Regev, Russell Littman
机构
*
University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)
;
Research and Early Development (gRED), Genentech(基因泰克研发与早期开发部)
;
Biology Research — AI Development (BRAID), Genentech(基因泰克生物学研究——人工智能开发部)
专题命中
推理与问题求解
:foundation model(abstract);分类 cs.AI
AI总结
本文提出MoE-ViT,通过稀疏专家混合模型优化多通道图像处理,提升效率而不牺牲性能。
CommentsThis has been accepted at the NeurIPS AI4Science Workshop 2025
Fairness Evaluation of Large Language Models in Academic Library Reference Services
学术图书馆参考服务中大型语言模型的公平性评估
Haining Wang, Jason Clark, Yueru Yan, Star Bradley, Ruiyang Chen, Yiqiong Zhang, Hengyi Fu, Zuoyu Tian
机构
*
Indiana University(印第安纳大学)
;
Montana State University(蒙塔纳州立大学)
;
Wuhan University(武汉大学)
;
Guangdong University of Foreign Studies(广东外语外贸大学)
;
San José State University(圣何塞州立大学)
;
Macalester College(麦基尔学院)
专题命中
评测与基准
:large language model(title,abstract);language model(title,abstract);prompting(abstract);分类 cs.CL、cs.AI
机构
*
Center for Postgraduate Clinical Training and Career Development, Nagoya University Hospital(名古屋大学医院研究生临床培训与职业发展中心)
;
Center for Medical Education, Graduate School of Medicine, Nagoya University(名古屋大学医学研究生院医学教育中心)
;
Scientific Research Works Peer Support Group (SRWS-PSG)(科学研究作品同伴支持组)
;
Department of Internal Medicine, Kyoto Min-iren Asukai Hospital(京都Min-iren Asukai医院内科学部)
;
Department of Healthcare Epidemiology, Kyoto University Graduate School of Medicine / School of Public Health(京都大学医学研究院/公共卫生学院卫生流行病学部)
;
Department of International and Community Oral Health, Tohoku University Graduate School of Dentistry(东京东医齿学研究院国际与社区口腔健康部)
;
Department of Psychiatry, Okayama Psychiatric Medical Center(冈山精神医学中心精神病学部)
;
CureApp, Inc.(CureApp公司)
;
Department of Psychiatry, Seichiryo Hospital(Seichiryo医院精神病学部)
;
Oku medical clinic(Oku医疗诊所)
;
Department of Health Promotion and Human Behavior, Kyoto University Graduate School of Medicine / School of Public Health(京都大学医学研究院/公共卫生学院健康促进与人类行为部)
;
Kyoto University Hospital(京都大学医院)
;
Division of Radiology and Biomedical Engineering, Graduate School of Medicine, The University of Tokyo(东京大学医学研究生院放射学与生物医学工程部)
;
Department of Rehabilitation, Kurashiki Medical Centre(Kurashiki医疗中心康复部)
;
Department of Epidemiology, Graduate School of Medicine, Dentistry, and Pharmaceutical Sciences, Okayama University(冈山大学医学、牙科和药学研究生院流行病学部)
专题命中
评测与基准
:large language model(title,abstract);language model(title,abstract);LLM(abstract);分类 cs.AI
Comments9 pages, 1 figure, 4 tables. Presented at the 3rd International Workshop on Value Engineering in AI (VALE 2025), 28th European Conference on AI. To appear in Springer LNCS
ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions
ToolHaystack: 在现实长期交互中压力测试工具增强的语言模型
Beong-woo Kwak, Minju Kim, Dongha Lim, Hyungjoo Chae, Dongjin Kang, Sunghwan Kim, Dongil Yang, Jinyoung Yeo
机构
*
Department of Artificial Intelligence, Yonsei University(人工智能系,延世大学)
;
Department of Computer Science & Engineering, Yonsei University(计算机科学与工程系,延世大学)
专题命中
评测与基准
:language model(title,abstract);large language model(abstract);分类 cs.CL
SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
SePer:通过语义困惑度降低的视角衡量检索效用
Lu Dai, Yijie Xu, Jinhui Ye, Hao Liu, Hui Xiong
机构
*
The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州))
;
The Hong Kong University of Science and Technology(香港科学与技术大学)
;
Carnegie Mellon University(卡内基梅隆大学)
专题命中
评测与基准
:LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI、cs.LG