The Latin Substrate: How Language Models Represent and Mediate Script Choice
拉丁基底:语言模型如何表示和中介文字选择
Daniil Gurgurov, Alan Saji, Katharina Trinley, Josef van Genabith, Simon Ostermann
机构
*
German Research Center for AI(德国人工智能研究中心)
;
Saarland University(萨尔兰大学)
;
Indian Institute of Technology, Madras(印度理工学院-马德拉斯)
;
Nilekani Centre at AI4Bharat(AI4Bharat的Nilekani中心)
专题命中
知识编辑与模型理解
:language model(title,abstract);LLM(abstract_cn);large language model(abstract);分类 cs.CL
GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
GlucoFM: 一种用于连续血糖监测的双流基础模型
Zechen Li, Keerthana Natarajan, Weizhi Zhang, Menglian Zhou, Simon A. Lee, Yuwei Zhang, Maxwell A. Xu, Zeinab Esmaeilpour, Flora D. Salim, Mark Malhotra, Lindsey Sunden, Shwetak Patel, Yuzhe Yang, Ahmed A. Metwally
机构
*
Google Research(谷歌研究)
;
University of New South Wales(新南威尔士大学)
SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling
SLAP: 用于变分视频-语言建模的语义最小作用原理
Xiang Fang, Wanlong Fang
机构
*
School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件学院)
;
Nanyang Technological University, Singapore(新加坡南洋理工大学)
What Am I Missing? Question-Answering as Hidden State Probing
我遗漏了什么?将问答作为隐藏状态探测
Chu Fei Luo, Samuel Dahan, Xiaodan Zhu
机构
*
Department of Electrical and Computer Engineering & Ingenuity Labs, Queen’s University(电子与计算机工程系及Ingenuity实验室,女王大学)
;
Conflict Analytics Lab, Queen’s University(冲突分析实验室,女王大学)
;
Cornell Law School(康奈尔法学院)
;
Vector Institute for AI(人工智能向量研究所)
专题命中
知识编辑与模型理解
:large language model(abstract);language model(abstract);分类 cs.CL
Comments31 pages, 11 figures. Preprint; presented at ICLR 2026 2nd Workshop on Foundation Models for Science: Real-World Impact and Science-First Design
The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling
混沌替代建模中的动态-概率一致性差距
Andre Herz, Matthijs Pals, Daniel Durstewitz, Georgia Koppe
机构
*
Interdisciplinary Center for Scientific Computing, Heidelberg University, Germany(海德堡大学交叉科学计算中心)
;
Faculty of Mathematics and Computer Science, Heidelberg University, Germany(海德堡大学数学与计算机科学学院)
;
Dept. of Theoretical Neuroscience, Central Institute of Mental Health (CIMH), Mannheim, Germany(曼海姆中央心理健康研究所理论神经科学部门)
;
Faculty of Physics and Astronomy, Heidelberg University, Germany(海德堡大学物理与天文学学院)
;
Hector Institute for AI in Psychiatry and Dept. of Psychiatry and Psychotherapy, CIMH, Mannheim, Germany(曼海姆中央心理健康研究所精神病AI研究所及精神病学与心理学系)
;
Hertie Institute for AI in Brain Health, University of Tübingen, Germany(图宾根大学脑健康AI研究所)
UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
UniRTL:统一代码和图以实现稳健的RTL表示学习
Yi Liu, Hongji Zhang, Lei Chen, Mingxuan Yuan, Qiang Xu
机构
*
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR(计算机科学与工程系,香港中文大学,香港特别行政区)
;
Noah's Ark Lab, Huawei, Hong Kong SAR(华为诺亚实验室,香港特别行政区)
Variational Adapter for Cross-modal Similarity Representation
变分适配器用于跨模态相似性表示
WenZhang Wei, Zhipeng Gui, Dehua Peng, Tiandi Ye, Huayi Wu
机构
*
School of Remote Sensing and Information Engineering(遥感与信息工程学院)
;
Wuhan University(武汉大学)
;
School of Data Science and Engineering(数据科学与工程学院)
;
East China Normal University(华东师范大学)
;
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing(测绘遥感信息工程国家重点实验室)
What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
什么使LVLMs更少产生幻觉?揭示影响幻觉鲁棒性的架构因素
Yusheng He, Jizhe Zhou, Xia Du, Zheng Lin, Jun Luo, Jiancheng Lv
机构
*
School of Computer Science, Engineering Research Center of Machine Learning and Industry Intelligence, Sichuan University(计算机科学学院,机器学习与产业智能工程研究中心,四川大学)
;
School of Computer and Information Engineering, Xiamen University of Technology(计算机与信息工程学院,厦门理工大学)
;
Department of Electrical and Computer Engineering, University of Hong Kong(电气与计算机工程系,香港大学)
;
College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)
View Space: Learning Representation across Arbitrary Graphs
视图空间:跨任意图的学习表示
Dooho Lee, Myeong Kong, Minho Jeong, Jaemin Yoo
机构
*
School of Electrical Engineering, KAIST, Daejeon, Republic of Korea(韩国釜山科学技术院电子工程学院)
;
Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea(首尔国立大学计算机科学与工程系)
Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
取消补丁令牌静音:重新审视多标签音频分类中的探测方法
Lukas Rauch, René Heinrich, Houtan Ghaffari, Lukas Miklautz, Ilyass Moummad, Bernhard Sick, Christoph Scholz
机构
*
University of Kassel(卡塞尔大学)
;
Fraunhofer IEE(弗劳恩霍夫研究所)
;
Ghent University(根特大学)
;
ML and Systems Biology, MPI of Biochemistry(生物化学Max Planck研究所)
;
INRIA Montpellier(蒙彼利埃INRIA)
Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
跨模态注意力校准用于LVLM幻觉缓解
Jiaming Li, Jiacheng Zhang, Zequn Jie, Lin Ma, Guanbin Li
机构
*
Sun Yat-sen University(中山大学)
;
The University of Hong Kong(香港大学)
;
Meituan(美团)
;
Inspur Database Technology(Inspur数据库技术)
;
Guilin University of Electronic Technology(桂林电子科技大学)
;
Shenzhen Loop Area Institute(深圳河套学院)
;
Guangdong Key Laboratory of Big Data Analysis and Processing(广东大数据分析与处理重点实验室)