AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference
AdaVFM:通过LLM引导执行实现边缘智能的自适应视觉基础模型
Yiwei Zhao, Yi Zheng, Huapeng Su, Jieyu Lin, Stefano Ambrogio, Cijo Jose, Michael Ramamonjisoa, Patrick Labatut, Barbara De Salvo, Chiao Liu, Phillip B. Gibbons, Ziyun Li
机构
*
Carnegie Mellon University(卡内基梅隆大学)
;
Meta
专题命中
视觉定位与Grounding
:multimodal large language model(abstract);分类 cs.CV、cs.LG
CommentsFixed scoring-normalization error in Neural Defend/TruthScan results, revising the central finding: MCC and ROC-AUC are strongly correlated (r ~ 0.86) overall, with only a specific subset showing one-directional threshold miscalibration. Abstract, tables, Discussion, Conclusion updated
Alejandro García-Castellanos, David R. Wessels, Nicky J. van den Berg, Remco Duits, Daniël M. Pelt, Erik J. Bekkers
机构
*
Amsterdam Machine Learning Lab (AMLab), University of Amsterdam(阿姆斯特丹机器学习实验室(AMLab),阿姆斯特丹大学)
;
New Theory(新理论)
;
Department of Mathematics and Computer Science, Eindhoven University of Technology(数学与计算机科学系,埃因霍温理工大学)
;
Leiden Institute of Advanced Computer Science, Universiteit Leiden(莱顿高级计算机科学研究所,莱顿大学)
Self-Distillation of Hidden Layers for Self-Supervised Representation Learning
隐藏层自蒸馏用于自监督表示学习
Scott C. Lowe, Anthony Fuller, Sageev Oore, Evan Shelhamer, Graham W. Taylor
机构
*
Vector Institute(向量研究所)
;
Carleton University(卡尔顿大学)
;
Dalhousie University(达尔豪斯大学)
;
University of British Columbia(不列颠哥伦比亚大学)
;
University of Guelph(圭尔夫大学)
Comments15 pages, 3 figures. Reliability protocol and library (cua_reliability), completion verifier, and leakage-free held-out plus bootstrap evaluation harness are open-source
CommentsFull version of a to be published paper in proceedings of the 9th AAAI/ACM conference in AI, Ethics and Society (AIES 2026). Includes supplementary material. 20 pages, 2 figures
CommentsAccepted for publication in the 30th Conference on Medical Image Understanding and Analysis (MIUA 2026), Dublin. To appear in Springer Lecture Notes in Computer Science (LNCS)
机构
*
Namibia University of Science and Technology(纳米比亚科技大学)
;
Indian Institute of Technology Indore(印度理工学院印多尔分校)
;
Namdeb Diamond Corporation(纳米比亚钻石公司)
机构
*
Beihang University(北京航空航天大学)
;
State Key Laboratory of Space Information System and Integrated Application(空间信息系统与集成应用国家重点实验室)
;
Nanjing University(南京大学)
;
Harbin Engineering University(哈尔滨工程大学)
;
Beijing Zhongguancun Academy(北京中关村科学城)
Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers
解开特征结构:Transformer中数学上可证明的两阶段训练动态
Zixuan Gong, Shijia Li, Yong Liu, Jiaye Teng
机构
*
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学耿丽人工智能学院)
;
School of Mechanical-Electronic and Vehicle Engineering, Beijing University of Civil Engineering and Architecture(北京建筑大学机械电子与车辆工程学院)
;
School of Statistics and Management, Shanghai University of Finance and Economics(上海财经大学统计与管理学院)
AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
AnchorMoE: 基于锚点路由的混合专家模型实现可解释时间序列分类
Tao Xie, Zexi Tan, Haoyi Xiao, Mengke Li, Yiqun Zhang, Yang Lu, Cuie Yang, Yiu-ming Cheung
机构
*
School of Automation, Guangdong University of Technology(广东工业大学自动化学院)
;
School of Computer Science and Technology, Guangdong University of Technology(广东工业大学计算机科学与技术学院)
;
College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机科学与软件工程学院)
;
School of Informatics, Xiamen University(厦门大学信息学院)
;
State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University(东北大学过程工业综合自动化国家重点实验室)
;
Department of Computer Science, Hong Kong Baptist University(香港 Baptist 大学计算机科学系)