Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
基于置信度蒸馏的门控关系对齐用于高效视觉语言模型
Yanlong Chen, Amirhossein Habibian, Luca Benini, Yawei Li
机构
*
Department of Information Technology(信息科技系)
;
Electrical Engineering, ETH Zurich, Zurich, Switzerland(电气工程,苏黎世联邦理工学院,苏黎世,瑞士)
;
Qualcomm AI Research, Amsterdam, the Netherlands(高通人工智能研究,阿姆斯特丹,荷兰)
;
Department of Electrical, Electronic and Information Engineering(电气、电子与信息工程系)
;
University of Bologna, Bologna, Italy(博洛尼亚大学,博洛尼亚,意大利)
;
School of Electrical and Electronic Engineering(电气与电子工程学院)
MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction
MPFlow: 多模态后验引导的流匹配用于零样本MRI重建
Seunghoi Kim, Chen Jin, Henry F. J. Tregidgo, Matteo Figini, Daniel C. Alexander
机构
*
1 Hawkes Institute, UCL \, 2 Dept. of Medical Physics
;
Biomedical Engineering, UCL 3 Dept. of Computer Science, UCL 4 Centre for AI, DS\&AI, AstraZeneca, UK
Comments6 pages, 5 figures. Published in MobiSys Workshop '26
Journal refIn Proceedings of the 24th Annual International Conference on Mobile Systems, Applications and Services Workshops (MobiSys Workshop '26), June 21-25, 2026, Cambridge, United Kingdom. ACM, New York, NY, USA, 6 pages
When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
LLM何时值得用于超参数优化?基于表格数据的预算匹配研究发现热启动是默认配置,而非模型
Carson Rodrigues, Oysturn Vas, Isaiah Abner DCosta, Nithish Kumar Prabhakaran
机构
*
Celabe
;
University of Waterloo(滑铁卢大学)
专题命中
领域大模型
:LLM(title,title_cn);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG