语言大模型 / LLM - arXivDaily 专题

2605.07569 2026-05-11 cs.DC 89%

HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware

HexiSeq: 适配长上下文训练的LLM异构硬件支持

Yan Liang, Youhe Jiang, Ran Yan, Binhang Yuan, Wei Wang, Chuan Wu

专题命中长上下文与记忆：LLM(title_cn,summary_cn)；large language model(abstract)；language model(abstract)

AI总结 HexiSeq通过异构GPU集群的计算、内存和通信能力分配，实现非对称CP-HP分区，提升长上下文LLM训练吞吐量，实验显示在混合H100-A100和模拟集群中性能提升达1.11至1.72倍。

2502.08875 2026-04-09 q-fin.GN 89%

Utilizing Pre-trained and Large Language Models for 10-K Items Segmentation

利用预训练和大语言模型进行10-K文件分段

Hsin-Min Lu, Yu-Tai Chien, Huan-Hsun Yen, Yen-Hsiu Chen

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)

AI总结本文提出两种先进分段方法，BERT4ItemSeg与GPT4ItemSeg，通过预训练模型与Bi-LSTM结合或大语言模型，提升10-K报告分段性能，核心指标达到宏F1值0.9825。

Comments Accepted for publication in the Journal of Information Systems

2604.05114 2026-04-08 cs.CL cs.AI cs.LG 89%

$π^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models

$π^2$：结构起源的推理数据提升大语言模型的长上下文推理能力

Quyet V. Do, Thinh Pham, Nguyen Nguyen, Sha Li, Pratibha Zunjare, Tu Vu

机构 * Virginia Tech（弗吉尼亚理工大学）

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

AI总结本文提出$π^2$方法，通过结构化数据生成高质量推理数据，提升大语言模型的长上下文推理能力，在四个基准测试中取得显著改进。

Comments Our structured analytical reasoning data, which originates from Wikipedia tables, significantly improves long-context reasoning capability of LLMs

2603.01154 2026-03-05 cs.CR 89%

vEcho: A Paradigm Shift from Vulnerability Verification to Proactive Discovery with Large Language Models

vEcho：从漏洞验证到大语言模型主动发现的范式转变

Mingcheng Jiang, Jiancheng Huang, Jiangfei Wang, Zhengzhu Xie, Nan Fang, Guang Cheng, Xiaoyan Hu, Hua Wu

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结 vEcho利用大语言模型主动发现漏洞，显著提升检测率并降低误报率，同时发现新的0日漏洞。

2508.01255 2026-01-28 cs.SE 89%

TestWeaver: Execution-aware, Feedback-driven Regression Testing Generation with Large Language Models

TestWeaver: 基于执行意识和反馈驱动的回归测试生成方法

Cuong Chi Le, Cuong Duc Van, Tung Duy Vu, Thai Minh Pham Vu, Hoang Nhat Phan, Huy Nhat Phan, Tien N. Nguyen

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结 TestWeaver通过整合轻量级程序分析和针对性执行上下文，提升LLM在回归测试生成中的覆盖率和效率。

Comments Accepted in ICSE 2026

2512.03356 2026-01-13 cs.CR 89%

From static to adaptive: immune memory-based jailbreak detection for large language models

从静态到适应性：基于免疫记忆的大型语言模型 jailbreak 检测

Jun Leng, Yu Liu, Litian Zhang, Ruihan Hu, Zhuting Fang, Xi Zhang

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结基于免疫记忆的框架，通过动态记忆更新和主动免疫机制，提升大型语言模型对 jailbreak 攻击的检测准确率至 94%。

2507.19854 2025-12-30 cs.RO cs.HC 89%

Think, Act, Learn: A Framework for Autonomous Robotic Agents using Closed-Loop Large Language Models

思考、行动、学习：一种利用闭环大语言模型的自主机器人代理框架

Anjali R. Menon, Rohit K. Sharma, Priya Singh, Chengyu Wang, Aurora M. Ferreira, Mateja Novak

机构 * Dept. of Electronics & Comm. Eng.（电子与通信工程系）； Government Engineering College（政府工程学院）； Dept. of Electrical & Electronics Eng.（电气与电子工程系）； Poornima College of Engineering（波奥尼玛工程学院）； Dept. of Electronics & Telecom. Eng.（电子与电信工程系）； Shivaji University College of Eng.（希瓦吉大学工程学院）； Department of Computer Science（计算机科学系）； San Francisco State University（旧金山州立大学）； Dept. of Electrical Eng.（电气工程系）； Instituto Federal do Maranhão（马里兰联邦学院）； Dept. of Electrical & Computer Eng.（电气与计算机工程系）； Technical University of Košice（科希丘夫技术大学）

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结本文提出T-A-L框架，通过闭环大语言模型实现机器人自主学习与策略优化，显著提升复杂任务的成功率和泛化能力。

Comments 13 pages, 7 figures

2505.22657 2025-12-18 cs.CV cs.AI cs.CL cs.LG 89%

3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

3DLLM-Mem: 长期空间-时间记忆用于具身3D大语言模型

Wenbo Hu, Yining Hong, Yanjun Wang, Leison Gao, Zibu Wei, Xingcheng Yao, Nanyun Peng, Yonatan Bitton, Idan Szpektor, Kai-Wei Chang

机构 * University of California, Los Angeles（加州大学洛杉矶分校）

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

AI总结 3DLLM-Mem通过引入动态内存管理和融合模型，提升LLMs在复杂3D环境中的长期空间-时间记忆推理与行动能力。

Comments demos at: https://3dllm-mem.github.io

2409.10506 2025-12-11 cs.SE 89%

SmartC2Rust: Iterative, Feedback-Driven C-to-Rust Translation via Large Language Models for Safety and Equivalence

SmartC2Rust: 基于大语言模型的迭代反馈驱动C到Rust翻译用于安全性和等价性

Momoko Shiraishi, Yinzhi Cao, Takahiro Shinagawa

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结 SmartC2Rust通过迭代反馈机制利用大语言模型实现C到Rust的翻译，提升内存安全性和语义等价性。

Journal ref ICSE '26: Proceedings of the 48th International Conference on Software Engineering, April 12-18, 2026, Rio de Janeiro, Brazil

2512.01541 2025-12-02 cs.AR 89%

RoMe: Row Granularity Access Memory System for Large Language Models

RoMe：面向大语言模型的行粒度访问内存系统

Hwayong Nam, Seungmin Baek, Jumin Kim, Michael Jaemin Kim, Jung Ho Ahn

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结 RoMe通过行粒度访问DRAM并移除冗余结构，简化内存调度并提升带宽，适用于大语言模型的高效内存系统。

Comments 15 pages, 14 figures, accepted at HPCA 2026

2511.17194 2025-11-24 cs.CR 89%

Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models

在阴影中引导：大型语言模型中激活空间攻击的因果放大

Zhiyuan Xu, Stanislav Abaimov, Joseph Gardiner, Sana Belguith

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结本文提出通过因果放大效应，利用激活空间攻击实现对大型语言模型行为的可控引导，展示了其在安全性和有效性上的贡献。

Comments 31 pages, 5 figures, 9 tables

2509.24037 2025-11-17 cs.CR 89%

Automated Vulnerability Validation and Verification: A Large Language Model Approach

Alireza Lotfi, Charalampos Katsis, Elisa Bertino

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2509.17138 2025-10-23 q-bio.NC 89%

Analyzing Memory Effects in Large Language Models through the lens of Cognitive Psychology

Zhaoyang Cao, Lael Schooler, Reza Zafarani

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2505.00270 2025-09-19 physics.comp-ph physics.bio-ph 89%

Large Language Models as AI Agents for Digital Atoms and Molecules: Catalyzing a New Era in Computational Biophysics

Yijie Xia, Xiaohan Lin, Zicheng Ma, Jinyuan Hu, Yanheng Li, Zhaoxin Xie, Hao Li, Li Yang, Zhiqiang Zhao, Lijiang Yang, Zhenyu Chen, Yi Qin Gao

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments 26 pages, 3 figures, 2 tables

2509.01463 2025-09-03 cs.CR 89%

LLMHoney: A Real-Time SSH Honeypot with Large Language Model-Driven Dynamic Response Generation

Pranjay Malhotra

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments 7 Pages

2508.13413 2025-08-20 cs.HC cs.SE 89%

Large Language Models as Visualization Agents for Immersive Binary Reverse Engineering

Dennis Brown, Samuel Mulder

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments Accepted to IEEE VISSOFT 2025

2506.16450 2025-06-23 cs.CV 89%

How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?

Giuseppe Lando, Rosario Forte, Giovanni Maria Farinella, Antonino Furnari

机构 * Department of Mathematics and Computer Science（数学与计算机科学系）

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2411.08466 2025-06-10 cs.CV 89%

Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models

Quan Zhang, Jinwei Fang, Rui Yuan, Xi Tang, Yuxin Qi, Ke Zhang, Chun Yuan

机构 * Tsinghua University（清华大学）； University of Science and Technology of China（中国科学技术大学）； Shanghai Jiao Tong University（上海交通大学）

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；foundation model(abstract)

Comments Accepted to CVPR

2312.02252 2025-04-28 cs.CV 89%

StoryGPT-V: Large Language Models as Consistent Story Visualizers

Xiaoqian Shen, Mohamed Elhoseiny

机构 * KAUST（卡塞姆大学）

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments Accepted to CVPR 2025; Project page: https://xiaoqian-shen.github.io/StoryGPT-V

2504.14845 2025-04-22 cs.IR 89%

Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph

Qiushi Xiong, Zhipeng Xu, Zhenghao Liu, Mengjia Wang, Zulong Chen, Yue Sun, Yu Gu, Xiaohua Li, Ge Yu

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2504.06214 2025-04-09 cs.CL cs.AI cs.LG 89%

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models

Chejian Xu, Wei Ping, Peng Xu, Zihan Liu, Boxin Wang, Mohammad Shoeybi, Bo Li, Bryan Catanzaro

专题命中长上下文与记忆：large language model(title)；language model(title)；instruction tuning(abstract)；pretraining(abstract)

2501.06828 2025-03-14 cs.CV 89%

GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing

Ruizhe Ou, Yuan Hu, Fan Zhang, Jiaxin Chen, Yu Liu

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2406.11230 2025-02-12 cs.LG cs.AI cs.CL cs.CV 89%

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models

Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang

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

Comments Accepted at NAACL 2025 Main

2408.13986 2025-02-11 cs.LG cs.AI cs.CL cs.IR 89%

AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction

Jie Feng, Yuwei Du, Jie Zhao, Yong Li

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

Comments Accepted by NAACL 2025 as main conference paper, https://github.com/tsinghua-fib-lab/AgentMove

2401.04997 2025-01-17 cs.IR 89%

Tapping the Potential of Large Language Models as Recommender Systems: A Comprehensive Framework and Empirical Analysis

Lanling Xu, Junjie Zhang, Bingqian Li, Jinpeng Wang, Sheng Chen, Wayne Xin Zhao, Ji-Rong Wen

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)

Comments 52 pages, under review

2501.06709 2025-01-14 cs.DC 89%

Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management

Liu Qianli, Hong Zicong, Chen Fahao, Li Peng, Guo Song

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2412.01663 2024-12-03 cs.RO 89%

DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline

Wenhao Sun, Sai Hou, Zixuan Wang, Bo Yu, Shaoshan Liu, Xu Yang, Shuai Liang, Yiming Gan, Yinhe Han

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments 27 pages, 5 figures, submitted to JFR

2411.18143 2024-11-28 cs.CR cs.SE 89%

Harnessing Large Language Models for Seed Generation in Greybox Fuzzing

Wenxuan Shi, Yunhang Zhang, Xinyu Xing, Jun Xu

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2410.11417 2024-10-16 cs.CV cs.MM 89%

VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models

Xiaohan Lan, Yitian Yuan, Zequn Jie, Lin Ma

专题命中长上下文与记忆：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments 9 pages, 4 figures

2407.04787 2024-07-09 cs.CL cs.AI cs.LG 89%

Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning

Eric Pasewark, Kyle Montgomery, Kefei Duan, Dawn Song, Chenguang Wang

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

Comments Accepted to ACL 2024

1. 长上下文与记忆 4738 篇

HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware

Utilizing Pre-trained and Large Language Models for 10-K Items Segmentation

$π^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models

vEcho: A Paradigm Shift from Vulnerability Verification to Proactive Discovery with Large Language Models

TestWeaver: Execution-aware, Feedback-driven Regression Testing Generation with Large Language Models

From static to adaptive: immune memory-based jailbreak detection for large language models

Think, Act, Learn: A Framework for Autonomous Robotic Agents using Closed-Loop Large Language Models

3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

SmartC2Rust: Iterative, Feedback-Driven C-to-Rust Translation via Large Language Models for Safety and Equivalence

RoMe: Row Granularity Access Memory System for Large Language Models

Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models

Automated Vulnerability Validation and Verification: A Large Language Model Approach

Analyzing Memory Effects in Large Language Models through the lens of Cognitive Psychology

Large Language Models as AI Agents for Digital Atoms and Molecules: Catalyzing a New Era in Computational Biophysics

LLMHoney: A Real-Time SSH Honeypot with Large Language Model-Driven Dynamic Response Generation

Large Language Models as Visualization Agents for Immersive Binary Reverse Engineering

How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?

Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models

StoryGPT-V: Large Language Models as Consistent Story Visualizers

Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models

GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models

AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction

Tapping the Potential of Large Language Models as Recommender Systems: A Comprehensive Framework and Empirical Analysis

Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management

DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline

Harnessing Large Language Models for Seed Generation in Greybox Fuzzing

VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models

Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning