语言大模型 / LLM

Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR

听更清晰，用更少：多模态检索与选择增强的对话式LLM基于ASR

Bingshen Mu, Hexin Liu, Hongfei Xue, Kun Wei, Lei Xie

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

AI总结 本文提出MARS方法，通过多模态检索与选择提升对话式LLM-ASR的准确性，仅用1.5K小时数据即可超越训练于179K小时数据的顶级系统。

Comments AAAI 2026

Memory Poisoning Attack and Defense on Memory Based LLM-Agents

基于内存的LLM代理中的内存污染攻击与防御

Balachandra Devarangadi Sunil, Isheeta Sinha, Piyush Maheshwari, Shantanu Todmal, Shreyan Mallik, Shuchi Mishra

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

AI总结 本文研究了基于内存的LLM代理中的内存污染攻击与防御，通过实验发现预存合法记忆可显著降低攻击效果，并提出两种新的防御机制。

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs

AegisAgent：一种对抗LLM-HAR中提示注入攻击的自主防御代理

Yihan Wang, Huanqi Yang, Shantanu Pal, Weitao Xu

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

AI总结 AegisAgent通过自主推理和验证机制，有效降低LLM-HAR系统中提示注入攻击的成功率，提升系统安全性。

Chopper: A Multi-Level GPU Characterization Tool & Derived Insights Into LLM Training Inefficiency

Chopper：一个多级GPU特性工具及对LLM训练低效性的衍生见解

Marco Kurzynski, Shaizeen Aga, Di Wu

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

AI总结 Chopper通过多级GPU特性分析揭示LLM训练低效原因，发现频率开销是性能差距的主要因素。

Boosting Pointer Analysis With LLM-Enhanced Allocation Function Detection

通过LLM增强的分配函数检测提升指针分析

Baijun Cheng, Kailong Wang, Ling Shi, Haoyu Wang, Peng Di, Ding Li, Xiangqun Chen, Yao Guo

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

AI总结 本文提出CAFD技术，通过LLM增强的分配函数检测提升指针分析精度，有效识别CAFs并减少别名集大小，提升分析效率和准确性。

VULSOLVER: Vulnerability Detection via LLM-Driven Constraint Solving

通过LLM驱动的约束求解进行漏洞检测：VULSOLVER

Xiang Li, Yueci Su, Jiahao Liu, Zhiwei Lin, Yuebing Hou, Peiming Gao, Yuanchao Zhang

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

AI总结 VULSOLVER通过LLM驱动的约束求解方法，实现高精度漏洞检测，准确率达97.85%

LLM-Guided Scenario-based GUI Testing

Shengcheng Yu, Yuchen Ling, Chunrong Fang, Quan Zhou, Yi Zhao, Chunyang Chen, Shaomin Zhu, Zhenyu Chen

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

Investigating Software Aging in LLM-Generated Software Systems

César Santos, Ermeson Andrade, Roberto Natella

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

Comments Presented at the 17th International Workshop on Software Aging and Rejuvenation (WoSAR), 2025

Review of Tools for Zero-Code LLM Based Application Development

Priyaranjan Pattnayak, Hussain Bohra

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

Comments Accepted in 6th World Conference on Artificial Intelligence: Advances and Applications (WCAIAA 2025)

RustAssure: Differential Symbolic Testing for LLM-Transpiled C-to-Rust Code

Yubo Bai, Tapti Palit

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

Comments 13 pages to appear in Proceedings of ASE 2025

Can an LLM Induce a Graph? Investigating Memory Drift and Context Length

Raquib Bin Yousuf, Aadyant Khatri, Shengzhe Xu, Mandar Sharma, Naren Ramakrishnan

机构 * Department of Computer Science, Virginia Tech, Alexandria, VA（计算机科学系，弗吉尼亚理工大学，亚历山大，VA） 纠错

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

Comments 2025 IEEE International Conference on Knowledge Graph (ICKG)

KubeIntellect: A Modular LLM-Orchestrated Agent Framework for End-to-End Kubernetes Management

Mohsen Seyedkazemi Ardebili, Andrea Bartolini

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

Strata: Hierarchical Context Caching for Long Context Language Model Serving

Zhiqiang Xie, Ziyi Xu, Mark Zhao, Yuwei An, Vikram Sharma Mailthody, Scott Mahlke, Michael Garland, Christos Kozyrakis

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

Comments 13 pages, 14 figures, under peer review

Understanding Users' Privacy Perceptions Towards LLM's RAG-based Memory

Shuning Zhang, Rongjun Ma, Ying Ma, Shixuan Li, Yiqun Xu, Xin Yi, Hewu Li

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

DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model

Gerasimos Gerogiannis, Stijn Eyerman, Evangelos Georganas, Wim Heirman, Josep Torrellas

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

Improving LLM-Based Fault Localization with External Memory and Project Context

Inseok Yeo, Duksan Ryu, Jongmoon Baik

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

Comments 12 Pages, 7 figures

RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing

Jinyao Guo, Chengpeng Wang, Xiangzhe Xu, Zian Su, Xiangyu Zhang

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

Comments 18 pages, 11 tables, 6 figures, 3 listings

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures

Dang Nguyen, Wenhan Yang, Rathul Anand, Yu Yang, Baharan Mirzasoleiman

机构 * Computer Science Department, UCLA（计算机科学系，加州大学洛杉矶分校） 纠错

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

Comments 21 pages, 6 figures, 9 tables, link: https://github.com/BigML-CS-UCLA/CoLM

Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels

Sil Hamilton, Rebecca M. M. Hicke, Matthew Wilkens, David Mimno

机构 * Department of Information Science（信息科学系） ； Department of Computer Science（计算机科学系） ； Cornell University（康奈尔大学） 纠错

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

Augmented Body Communicator: Enhancing daily body expression for people with upper limb limitations through LLM and a robotic arm

Songchen Zhou, Mark Armstrong, Giulia Barbareschi, Toshihiro Ajioka, Zheng Hu, Ryoichi Ando, Kentaro Yoshifuji, Masatane Muto, Kouta Minamizawa

机构 * Keio University Graduate School of Media Design（庆应大学媒体设计研究生院） 纠错

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

LAMeD: LLM-generated Annotations for Memory Leak Detection

Ekaterina Shemetova, Ilya Shenbin, Ivan Smirnov, Anton Alekseev, Alexey Rukhovich, Sergey Nikolenko, Vadim Lomshakov, Irina Piontkovskaya

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

Customizing Emotional Support: How Do Individuals Construct and Interact With LLM-Powered Chatbots

Xi Zheng, Zhuoyang Li, Xinning Gui, Yuhan Luo

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

Comments 20 pages, 3 figures, 3 tables. Accepted to CHI 2025, ACM Conference on Human Factors in Computing Systems

Journal ref Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI '25), Article 376, 20 pages. ACM, New York, NY, USA.

Gene42: Long-Range Genomic Foundation Model With Dense Attention

Kirill Vishniakov, Boulbaba Ben Amor, Engin Tekin, Nancy A. ElNaker, Karthik Viswanathan, Aleksandr Medvedev, Aahan Singh, Maryam Nadeem, Mohammad Amaan Sayeed, Praveenkumar Kanithi, Tiago Magalhaes, Natalia Vassilieva, Dwarikanath Mahapatra, Marco Pimentel, and Shadab Khan

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

RustMap: Towards Project-Scale C-to-Rust Migration via Program Analysis and LLM

Xuemeng Cai, Jiakun Liu, Xiping Huang, Yijun Yu, Haitao Wu, Chunmiao Li, Bo Wang, Imam Nur Bani Yusuf, Lingxiao Jiang

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

Agent-S: LLM Agentic workflow to automate Standard Operating Procedures

Mandar Kulkarni

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

LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents

Ke Zhang, Chenxi Zhang, Chong Wang, Chi Zhang, YaChen Wu, Zhenchang Xing, Yang Liu, Qingshan Li, Xin Peng

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

Towards More Economical Context-Augmented LLM Generation by Reusing Stored KV Cache

Hanchen Li, Yuhan Liu, Yihua Cheng, Kuntai Du, Junchen Jiang

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

DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models

Yanming Liu, Xinyue Peng, Yuwei Zhang, Xiaolan Ke, Songhang Deng, Jiannan Cao, Chen Ma, Mengchen Fu, Tianyu Du, Sheng Cheng, Xun Wang, Jianwei Yin, Xuhong Zhang

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

Comments Fix metadata error

CoS: Chain-of-Shot Prompting for Long Video Understanding

Jian Hu, Zixu Cheng, Chenyang Si, Wei Li, Shaogang Gong

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

Comments A training-free test-time optimisation approach for long video understanding

ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models

Thibaut Thonet, Jos Rozen, Laurent Besacier

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

Comments Published in COLING 2025