arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

共收录 4822 信号源:cs.CL, cs.AI, cs.LG

1. 长上下文与记忆 4822 篇

2512.07850 2025-12-10 cs.LG cs.AI 81%

SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents

SABER: 小动作,大误差 -- 保护LLM代理中的突变步骤

Alejandro Cuadron, Pengfei Yu, Yang Liu, Arpit Gupta

机构 * Amazon AGI Foundations(亚马逊人工智能基础研究)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.AI、cs.LG

AI总结 SABER通过分析LLM代理中的突变步骤,提出针对性保护措施,提升长周期任务的稳定性。

Comments submitted to ICLR2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.05447 2025-11-10 cs.LG cs.AI cs.IR 81%

TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG

Savini Kashmira, Jayanaka L. Dantanarayana, Joshua Brodsky, Ashish Mahendra, Yiping Kang, Krisztian Flautner, Lingjia Tang, Jason Mars

机构 * University of Michigan(密歇根大学)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.AI、cs.LG

Comments Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01805 2025-11-05 cs.CL cs.AI 81%

Accumulating Context Changes the Beliefs of Language Models

Jiayi Geng, Howard Chen, Ryan Liu, Manoel Horta Ribeiro, Robb Willer, Graham Neubig, Thomas L. Griffiths

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00315 2025-11-04 cs.CL cs.AI 81%

Language Modeling With Factorization Memory

Lee Xiong, Maksim Tkachenko, Johanes Effendi, Ting Cai

机构 * Rakuten Group, Inc.(Rakuten集团)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.26835 2025-11-03 cs.DB cs.AI cs.LG 81%

Category-Aware Semantic Caching for Heterogeneous LLM Workloads

Chen Wang, Xunzhuo Liu, Yue Zhu, Alaa Youssef, Priya Nagpurkar, Huamin Chen

机构 * IBM Research(IBM研究院) Tencent(腾讯) Red Hat(红帽)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.AI、cs.LG

Comments 13 pages including reference, position paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09045 2025-11-03 cs.SE cs.AI cs.IR cs.LG 81%

LLM Based Long Code Translation using Identifier Replacement

Manojit Chakraborty, Madhusudan Ghosh, Rishabh Gupta

机构 * Bosch Research & Technology Center(博世研究与技术中心) Indian Association for the Cultivation of Science(印度科学培养协会)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12638 2025-10-28 q-bio.GN cs.AI cs.CE cs.LG 81%

ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibility Data

Yifeng Jiao, Yuchen Liu, Yu Zhang, Xin Guo, Yushuai Wu, Chen Jiang, Jiyang Li, Hongwei Zhang, Limei Han, Xin Gao, Yuan Qi, Yuan Cheng

机构 * Artificial Intelligence Innovation and Incubation Institute, Fudan University(复旦大学人工智能创新与孵化院) Shanghai Academy of Artificial Intelligence for Science(上海人工智能科学研究院) Computer, Electrical and Mathematical Sciences and Engineering Division, KAUST(卡塔尔大学计算机、电子与数学科学与工程系) Center of Excellence for Smart Health, KAUST(卡塔尔大学智能健康卓越中心) Center of Excellence on GenAI, KAUST(卡塔尔大学生成人工智能卓越中心) Zhongshan Hospital, Fudan University(复旦大学中山医院)

专题命中 长上下文与记忆 :foundation model(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.21894 2025-10-28 cs.CL cs.AI 81%

Understanding Network Behaviors through Natural Language Question-Answering

Mingzhe Xing, Chang Tian, Jianan Zhang, Lichen Pan, Peipei Liu, Zhaoteng Yan, Yinliang Yue

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

Comments Large Language Models

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09720 2025-10-14 cs.CL cs.AI 81%

Preference-Aware Memory Update for Long-Term LLM Agents

Haoran Sun, Zekun Zhang, Shaoning Zeng

机构 * Haoran Sun, Zekun Zhang, Shaoning Zeng(作者)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.22424 2025-10-13 cs.SE cs.AI cs.CL 81%

Issue Localization via LLM-Driven Iterative Code Graph Searching

Zhonghao Jiang, Xiaoxue Ren, Meng Yan, Wei Jiang, Yong Li, Zhongxin Liu

机构 * The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China(区块链与数据安全国家重点实验室,浙江大学,杭州,中国) School of Big Data and Software Engineering, Chongqing University, Chongqing, China(大数据与软件工程学院,重庆大学,重庆,中国)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.CL、cs.AI

Comments Accepted by ASE 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.21102 2025-10-02 cs.CL cs.AI 81%

Exploring and Controlling Diversity in LLM-Agent Conversation

KuanChao Chu, Yi-Pei Chen, Hideki Nakayama

机构 * The University of Tokyo(东京大学)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.CL、cs.AI

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02480 2025-09-03 cs.DC cs.AI cs.LG 81%

MLP-Offload: Multi-Level, Multi-Path Offloading for LLM Pre-training to Break the GPU Memory Wall

Avinash Maurya, M. Mustafa Rafique, Franck Cappello, Bogdan Nicolae

机构 * Argonne National Laboratory(阿贡国家实验室) Rochester Institute of Technology(罗切斯特理工学院)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.AI、cs.LG

Comments SC'25: The International Conference for High Performance Computing, Networking, Storage and Analysis

Journal ref SC'25: The International Conference for High Performance Computing, Networking, Storage and Analysis, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01514 2025-09-03 cs.CL cs.AI 81%

MeVe: A Modular System for Memory Verification and Effective Context Control in Language Models

Andreas Ottem

机构 * Independent Researcher(独立研究者)

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

Comments 16 pages, 7 figures, held online presentation at NLPA 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22933 2025-08-01 cs.CL cs.AI 81%

Augmented Vision-Language Models: A Systematic Review

Anthony C Davis, Burhan Sadiq, Tianmin Shu, Chien-Ming Huang

机构 * Johns Hopkins University(约翰霍普金斯大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23121 2025-07-15 eess.IV cs.AI cs.CV cs.LG 81%

CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation

Xinlei Yu, Changmiao Wang, Hui Jin, Ahmed Elazab, Gangyong Jia, Xiang Wan, Changqing Zou, Ruiquan Ge

机构 * Hangzhou Dianzi University(杭州电子科技大学) Shenzhen Research Institute of Big Data(深圳大数据研究院) Shenzhen University(深圳大学) Zhejiang University(浙江大学)

专题命中 长上下文与记忆 :prompting(title,abstract);分类 cs.AI、cs.LG

Comments Accepted By ACMMM25

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.08153 2025-07-14 cs.LG cs.AI 81%

ALCo-FM: Adaptive Long-Context Foundation Model for Accident Prediction

Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Rajiv Ramnath

机构 * Department of Computer Science(计算机科学系) Engineering, Ohio State University, Ohio, US(工程系,俄亥俄州立大学,俄亥俄州,美国)

专题命中 长上下文与记忆 :foundation model(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17670 2025-07-09 cs.LG cs.AI 81%

Towards General Continuous Memory for Vision-Language Models

Wenyi Wu, Zixuan Song, Kun Zhou, Yifei Shao, Zhiting Hu, Biwei Huang

机构 * University of California, San Diego(加州大学圣地亚哥分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.01651 2025-06-13 cs.CL cs.AI 81%

Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling

Xiang Hu, Zhihao Teng, Jun Zhao, Wei Wu, Kewei Tu

机构 * ShanghaiTech University(上海科技大学) Fudan University(复旦大学)

专题命中 长上下文与记忆 :language model(title);post-training(abstract);分类 cs.CL、cs.AI

Comments accepted to ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.18077 2025-06-10 cs.CL cs.LG 81%

MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache

Akshat Sharma, Hangliang Ding, Jianping Li, Neel Dani, Minjia Zhang

机构 * UIUC(伊利诺伊大学厄巴纳-香槟分校) University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) SSAIL Lab(超算系统人工智能实验室)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.08651 2025-05-14 cs.CL cs.LG 81%

Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing

Chen Wu, Yin Song

机构 * Amazon Web Services(亚马逊网络服务)

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

Comments 8 pages, 6 figures, ACL 2025 (Industry Track)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.02709 2025-05-06 cs.AI cs.LG 81%

Technical Report: Evaluating Goal Drift in Language Model Agents

Rauno Arike, Elizabeth Donoway, Henning Bartsch, Marius Hobbhahn

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.21716 2025-05-01 cs.RO cs.AI cs.CL 81%

LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics

Marc Glocker, Peter Hönig, Matthias Hirschmanner, Markus Vincze

机构 * Automation and Control Institute, Faculty of Electrical Engineering, TU Wien(自动化与控制研究所,电气工程学院,维也纳技术大学) AIT Austrian Institute of Technology GmbH, Center for Vision, Automation and Control(奥地利技术研究所(AIT)有限公司,视觉、自动化与控制中心)

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.CL、cs.AI

Comments Accepted at Austrian Robotics Workshop 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.07763 2025-03-18 cs.CL cs.AI cs.DB 81%

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Tao Yu

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

Comments ICLR 2025 Oral

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11995 2025-03-11 cs.CL cs.AI 81%

Presumed Cultural Identity: How Names Shape LLM Responses

Siddhesh Pawar, Arnav Arora, Lucie-Aimée Kaffee, Isabelle Augenstein

专题命中 长上下文与记忆 :LLM(title,abstract);分类 cs.CL、cs.AI

Comments 23 Pages, 13 Figures, 4 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.20405 2025-03-03 cs.CL cs.AI 81%

Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration

James Begin, Namit Agrawal, Eshan Singh, Yicheng Fu, Sean O'Brien, Vasu Sharma, Kevin Zhu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.15352 2025-02-11 cs.LG cs.CL 81%

CompAct: Compressed Activations for Memory-Efficient LLM Training

Yara Shamshoum, Nitzan Hodos, Yuval Sieradzki, Assaf Schuster

专题命中 长上下文与记忆 :LLM(title);pretraining(abstract);分类 cs.CL、cs.LG

Comments Accepted to NAACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.12735 2024-12-18 cs.CV cs.AI cs.CL 81%

GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models

Mukai Li, Lei Li, Shansan Gong, Qi Liu

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

Comments Working in progress

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.15265 2024-11-08 cs.LG cs.CL 81%

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

Zirui Liu, Guanchu Wang, Shaochen Zhong, Zhaozhuo Xu, Daochen Zha, Ruixiang Tang, Zhimeng Jiang, Kaixiong Zhou, Vipin Chaudhary, Shuai Xu, Xia Hu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.16264 2024-10-23 cs.CL cs.AI 81%

One Thousand and One Pairs: A "novel" challenge for long-context language models

Marzena Karpinska, Katherine Thai, Kyle Lo, Tanya Goyal, Mohit Iyyer

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

Comments EMNLP 2024, camera ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.15012 2024-10-10 cs.CL cs.LG 81%

Extracting Prompts by Inverting LLM Outputs

Collin Zhang, John X. Morris, Vitaly Shmatikov

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

详情

展开后加载摘要…

URL PDF HTML 收藏