A Survey of Token Compression for Efficient Multimodal Large Language Models
多模态大语言模型高效性中的标记压缩综述
Kele Shao, Keda Tao, Kejia Zhang, Sicheng Feng, Mu Cai, Yuzhang Shang, Haoxuan You, Can Qin, Yang Sui, Huan Wang
机构
*
Zhejiang University(浙江大学)
;
Westlake University(西湖大学)
;
Xiamen University(厦门大学)
;
National University of Singapore(新加坡国立大学)
;
University of Wisconsin-Madison(威斯康星大学麦迪逊分校)
;
University of Central Florida(佛罗里达大学)
;
Salesforce AI Research(Salesforce AI研究)
;
Rice University(德克萨斯大学)
专题命中
效率与部署
:large language model(title,abstract);language model(title,abstract)
Hard Constraints Meet Soft Generation: Guaranteed Feasibility for LLM-based Combinatorial Optimization
硬约束与软生成交汇:为基于LLM的组合优化保证可行性
Yang Liu, Chuan Zhou, Yancheng Chen, Shuai Zhang, Xixun Lin, Xiaoqing Wang
机构
*
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院)
;
School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院)
;
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所)
;
Alibaba Group(阿里巴巴集团)
专题命中
效率与部署
:LLM(title,abstract);large language model(abstract);language model(abstract);preference optimization(abstract)
Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
通过单个神经元的模型自反进行轻量级对齐以提升大语言模型的安全性
Sicheng Shen, Mingyang Lv, Han Shen, Jialin Wu, Binghao Wang, Zhou Yang, Guobin Shen, Dongcheng Zhao, Feifei Zhao, Yi Zeng
机构
*
Beijing Institute of AI Safety and Governance(北京人工智能安全与治理研究院)
;
Beijing Key Laboratory of Safe AI and Superalignment(北京安全人工智能与超对齐重点实验室)
;
Ant Group Co., Ltd.(蚂蚁集团有限公司)
;
BrainCog Lab., CASIA(CASIA脑认知实验室)
;
Zhongguancun Academy(中关村学院)
专题命中
效率与部署
:LLM(title);large language model(abstract);language model(abstract);post-training(abstract)
Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference
探测与跳过:用于高效长上下文LLM推理的自预测token跳过
Zimeng Wu, Donghao Wang, Chaozhe Jin, Jiaxin Chen, Yunhong Wang
机构
*
School of Computer Science and Engineering, Beihang University, Beijing, China(计算机科学与工程学院,北航,北京,中国)
;
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China(虚拟现实技术与系统国家重点实验室,北航,北京,中国)
专题命中
效率与部署
:LLM(title,abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG
ELLMPEG: An Edge-based Agentic LLM Video Processing Tool
ELLMPEG:一种基于边缘的代理LLM视频处理工具
Zoha Azimi, Reza Farahani, Radu Prodan, Christian Timmerer
机构
*
Christian Doppler Laboratory ATHENA, Department of Information Technology (ITEC) University of Klagenfurt(亚琛实验室ATHENA,信息科技系,克雷格弗尔特大学)
;
Department of Information Technology (ITEC) University of Klagenfurt(信息科技系,克雷格弗尔特大学)
;
Department of Computer Science University of Innsbruck(计算机科学系,因斯布鲁克大学)
专题命中
效率与部署
:LLM(title,abstract);large language model(abstract);language model(abstract);分类 cs.LG