语言大模型 / LLM

Between Predictability and Randomness: Seeking Artistic Inspiration from AI Generative Models

Olga Vechtomova

机构 * University of Waterloo（滑铁卢大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Presented as a keynote at the 50th Linguistic Association of Canada and the United States (LACUS) conference in July 2024 and will be published in LACUS Forum 50

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache

Xiaoran Liu, Siyang He, Qiqi Wang, Ruixiao Li, Yuerong Song, Zhigeng Liu, Linlin Li, Qun Liu, Zengfeng Huang, Qipeng Guo, Ziwei He, Xipeng Qiu

机构 * School of Computer Science, Fudan University（复旦大学计算机科学学院） ； Shanghai Innovation Institute（上海创新研究院） ； Huawei Noah’s Ark Lab（华为诺亚方舟实验室） ； Shanghai AI Lab（上海AI实验室） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 10 pages, 7 figures, work in progress

From Tool Calling to Symbolic Thinking: LLMs in a Persistent Lisp Metaprogramming Loop

Jordi de la Torre

机构 * Ph.D. in Computer Science and Mathematics of Security Barcelona, ES（巴塞罗那安全计算机科学与数学博士） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

On Many-Shot In-Context Learning for Long-Context Evaluation

Kaijian Zou, Muhammad Khalifa, Lu Wang

机构 * Computer Science and Engineering, University of Michigan（计算机科学与工程系，密歇根大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments ACL 2025 Main Conference

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding

Zikai Xiao, Ziyang Wang, Wen Ma, Yan Zhang, Wei Shen, Yan Wang, Luqi Gong, Zuozhu Liu

机构 * Zhejiang University（浙江大学） ； University of Science and Technology of China（中国科学技术大学） ； Bytedance（字节跳动） ； Zhejiang Lab（浙江省实验室） ； Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding

Xiao Wang, Qingyi Si, Jianlong Wu, Shiyu Zhu, Li Cao, Liqiang Nie

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； Huawei Technologies Co., Ltd.（华为技术有限公司） ； Shandong University（山东大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

Jing Xiong, Jianghan Shen, Chuanyang Zheng, Zhongwei Wan, Chenyang Zhao, Chiwun Yang, Fanghua Ye, Hongxia Yang, Lingpeng Kong, Ngai Wong

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments This paper has been accepted by ICML 2025

Memory OS of AI Agent

Jiazheng Kang, Mingming Ji, Zhe Zhao, Ting Bai

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Tencent AI Lab（腾讯AI实验室） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

Lost in the Passage: Passage-level In-context Learning Does Not Necessarily Need a "Passage"

Hao Sun, Chenming Tang, Gengyang Li, Yunfang Wu

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition

Masato Mita, Ryo Yoshida, Yohei Oseki

机构 * The University of Tokyo（东京大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to ACL2025 (main, long)

Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators

Kosmas Alexandridis, Vasileios Titopoulos, Giorgos Dimitrakopoulos

机构 * Integrated Circuits Lab（集成电路实验室） ； Electrical and Computer Engineering（电子与计算机工程） ； Democritus University of Thrace（德米特里乌斯大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2025)

M+: Extending MemoryLLM with Scalable Long-Term Memory

Yu Wang, Dmitry Krotov, Yuanzhe Hu, Yifan Gao, Wangchunshu Zhou, Julian McAuley, Dan Gutfreund, Rogerio Feris, Zexue He

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity

Yu Zhang, Dong Guo, Fang Wu, Guoliang Zhu, Dian Ding, Yiming Zhang

机构 * Xiamen University（厦门大学） ； Shanghai Jiao Tong University（上海交通大学） ； Xi’an Jiaotong University（西安交通大学） ； Chipltech（ChipTech） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Efficiently Enhancing General Agents With Hierarchical-categorical Memory

Changze Qiao, Mingming Lu

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG

Zilun Zhang, Haozhan Shen, Tiancheng Zhao, Zian Guan, Bin Chen, Yuhao Wang, Xu Jia, Yuxiang Cai, Yongheng Shang, Jianwei Yin

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； Binjiang Research Institute of Zhejiang University（浙江大学滨江研究院） ； School of Software Engineering of Zhejiang University（浙江大学软件工程学院） ； Polytechnic Institute of Zhejiang University（浙江大学 polytechnic 院） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted by IEEE Geoscience and Remote Sensing Magazine

What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs

Sangyeop Kim, Yohan Lee, Yongwoo Song, Kimin Lee

机构 * Coxwave ； Seoul National University（首尔国立大学） ； Kyung Hee University（庆熙大学） ； KAIST（韩国科学技术院） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted by ACL 2025

Theoretical Foundations for Semantic Cognition in Artificial Intelligence

Sebastian Dumbrava

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 248 pages, 77 figures

Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG

Wenbin Wang, Yongcheng Jing, Liang Ding, Yingjie Wang, Li Shen, Yong Luo, Bo Du, Dacheng Tao

机构 * Wuhan University（武汉大学） ； Nanyang Technological University（南洋理工大学） ； The University of Sydney（悉尼大学） ； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Keys to Robust Edits: from Theoretical Insights to Practical Advances

Jianhao Yan, Futing Wang, Yun Luo, Yafu Li, Yue Zhang

机构 * Zhejiang University（浙江大学） ； School of Engineering, Westlake University（西湖大学工程学院） ； Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖先进研究院技术研究所） ； Shanghai AI Lab（上海人工智能实验室） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments ACL 2025 Main Conference

MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems

Yinsicheng Jiang, Yao Fu, Yeqi Huang, Ping Nie, Zhan Lu, Leyang Xue, Congjie He, Man-Kit Sit, Jilong Xue, Li Dong, Ziming Miao, Dayou Du, Tairan Xu, Kai Zou, Edoardo Ponti, Luo Mai

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Duplicate submission of arXiv:2412.07067

CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents

Rebecca Westhäußer, Frederik Berenz, Wolfgang Minker, Sebastian Zepf

机构 * Mercedes-Benz AG（梅赛德斯-奔驰集团） ； Ulm University（乌尔姆大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

Sentience Quest: Towards Embodied, Emotionally Adaptive, Self-Evolving, Ethically Aligned Artificial General Intelligence

David Hanson, Alexandre Varcoe, Fabio Senna, Vytas Krisciunas, Wenwei Huang, Jakub Sura, Katherine Yeung, Mario Rodriguez, Jovanka Wilsdorf, Kathy Smith

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration

Jipeng Cen, Jiaxin Liu, Zhixu Li, Jingjing Wang

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

SAKR: Enhancing Retrieval-Augmented Generation via Streaming Algorithm and K-Means Clustering

Haoyu Kang, Yuzhou Zhu, Yukun Zhong, Ke Wang

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

Adversarial Suffix Filtering: a Defense Pipeline for LLMs

David Khachaturov, Robert Mullins

机构 * Department of Computer Science and Technology（计算机科学与技术系） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.LG

A Grounded Memory System For Smart Personal Assistants

Felix Ocker, Jörg Deigmöller, Pavel Smirnov, Julian Eggert

机构 * Honda Research Institute Europe（本田研究院欧洲分部） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 8 pages, 5 figures, accepted for the ESWC 2025 TEXT2KG workshop

ParaICL: Towards Parallel In-Context Learning

Xingxuan Li, Xuan-Phi Nguyen, Shafiq Joty, Lidong Bing

机构 * Shanda AI Research Institute（上海沙达人工智能研究院） ； Nanyang Technological University（南洋理工大学） ； Salesforce Research（Salesforce 研究） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted by NAACL 2025

Quantifying Memory Utilization with Effective State-Size

Rom N. Parnichkun, Neehal Tumma, Armin W. Thomas, Alessandro Moro, Qi An, Taiji Suzuki, Atsushi Yamashita, Michael Poli, Stefano Massaroli

机构 * The University of Tokyo（东京大学） ； Stanford University（斯坦福大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.LG

WuNeng: Hybrid State with Attention

Liu Xiao, Li Zhiyuan, Lin Yueyu

机构 * Uniartisan 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Needle Threading: Can LLMs Follow Threads through Near-Million-Scale Haystacks?

Jonathan Roberts, Kai Han, Samuel Albanie

机构 * University of Cambridge（剑桥大学） ； The University of Hong Kong（香港大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted at ICLR 2025