Only relative ranks matter in weight-clustered large language models
仅相对排名在权重聚类的大型语言模型中起作用
Borja Aizpurua, Sukhbinder Singh, Román Orús
机构
*
Department of Basic Sciences, Tecnun - University of Navarra, San Sebasti\'an, Spain
;
Donostia International Physics Center, San Sebasti\'an, Spain
专题命中
指令微调
:large language model(title,abstract);language model(title,abstract);分类 cs.CL、cs.LG
NutVLM: A Self-Adaptive Defense Framework against Full-Dimension Attacks for Vision Language Models in Autonomous Driving
NutVLM: 一种针对自动驾驶中视觉语言模型全维度攻击的自适应防御框架
Xiaoxu Peng, Dong Zhou, Jianwen Zhang, Guanghui Sun, Anh Tu Ngo, Anupam Chattopadhyay
机构
*
Department of Control Science and Engineering, Harbin Institute of Technology(控制科学与工程系,哈尔滨工业大学)
;
College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)
CommentsAccepted to LREC 2026. This publication is part of the project Responsible AI for Voice Diagnostics (RAIVD) with file number NGF.1607.22.013 of the research programme NGF AiNed Fellowship Grants, which is financed by the Dutch Research Council (NWO)
Leo Elmecker-Plakolm, Pierre Fasterling, Philip Sosnin, Calvin Tsay, Matthew Wicker
机构
*
Department of Computing(计算系)
;
Imperial College London(帝国理工学院伦敦分校)
;
School of Computer and Comm. Sciences (IC)(计算机与通信科学系)
;
École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)
Exploring parameter-efficient fine-tuning (PEFT) of billion-parameter vision models with QLoRA and DoRA: insights into generalization for limited-data image classification under a 98:1 test-to-train regime