No One Knows the State of the Art in Geospatial Foundation Models
没有人知道地理空间基础模型的现状
Isaac Corley, Nils Lehmann, Caleb Robinson, Gabriel Tseng, Anthony Fuller, Hamed Alemohammad, Evan Shelhamer, Jennifer Marcus, Hannah Kerner
机构
*
Taylor Geospatial(泰勒地理空间公司)
;
Technical University of Munich(慕尼黑技术大学)
;
Microsoft AI for Good Research Lab(微软AI for Good研究实验室)
;
Allen Institute for AI(艾伦人工智能研究所)
;
Vector Institute(向量研究所)
;
Carleton University(卡尔顿大学)
;
Clark University(克拉克大学)
;
University of British Columbia(不列颠哥伦比亚大学)
;
Arizona State University(亚利桑那州立大学)
机构
*
Tsinghua University(清华大学)
;
Nanyang Technological University(南洋理工大学)
;
University of Hong Kong(香港大学)
;
National University of Singapore(新加坡国立大学)
;
University of Waterloo(滑铁卢大学)
;
StepFun
;
MiroMind
;
Baidu(百度)
;
Fudan University(复旦大学)
;
Hong Kong University of Science and Technology(香港科技大学)
;
Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
;
LMMs-Lab(LMMs实验室)
Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
大型语言模型在持续微调过程中灾难性遗忘的机制分析
Gustav Olaf Yunus Laitinen-Fredriksson Lundstrom-Imanov
机构
*
Division of Statistics and Machine Learning (STIMA), Department of Computer and Information Science (IDA), Linköping University(统计与机器学习系(STIMA)、计算机与信息科学系(IDA)、利厄普堡大学)
专题命中
指令微调
:large language model(title,abstract);language model(title,abstract);LLM(summary_cn);分类 cs.CL、cs.LG
机构
*
MoE Key Lab of BIPC, University of Science and Technology of China(中科院大学科学技术大学MoE关键实验室)
;
Shanghai Innovation Institute(上海创新研究院)
;
Shanghai AI Laboratory(上海人工智能实验室)
Comments20 pages, 5 figures, 7 tables. Major revision and repositioning of arXiv:2504.15610v1-v3 (previously titled "A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained Settings"); withdraws the earlier quantization-boundary and cross-GPU optimizer-transfer claims. Code, dataset, adapter, and evaluation harness released