语言大模型 / LLM - arXivDaily 专题

2508.16568 2025-08-25 cs.LG cs.CV 79%

Closer to Reality: Practical Semi-Supervised Federated Learning for Foundation Model Adaptation

Guangyu Sun, Jingtao Li, Weiming Zhuang, Chen Chen, Chen Chen, Lingjuan Lyu

机构 * Sony AI（索尼人工智能）； University of Central Florida（中央佛罗里达大学）

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

2508.10395 2025-08-15 cs.LG 79%

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization

Aditya Tomar, Coleman Hooper, Minjae Lee, Haocheng Xi, Rishabh Tiwari, Wonjun Kang, Luca Manolache, Michael W. Mahoney, Kurt Keutzer, Amir Gholami

机构 * UC Berkeley（加州大学伯克利分校）； FuriosaAI ； ICSI（国际计算机科学研究所）； LBNL（劳伦斯伯克利国家实验室）

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

Comments 24 pages

2507.09506 2025-08-05 cs.CL 79%

Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models

Junjie Wu, Gefei Gu, Yanan Zheng, Dit-Yan Yeung, Arman Cohan

机构 * Hong Kong University of Science and Technology（香港理工大学）； Carnegie Mellon University（卡内基梅隆大学）； Yale University（耶鲁大学）

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

Comments ACL 2025 Main Conference. First 2 authors contributed equally. Project webpage: https://wujunjie1998.github.io/Ref-Long-website/

2507.21494 2025-07-30 cs.LG 79%

Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning

Wenxuan Bao, Ruxi Deng, Ruizhong Qiu, Tianxin Wei, Hanghang Tong, Jingrui He

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments Accepted by ICCV 2025

2507.13145 2025-07-18 cs.CV cs.AI cs.RO 79%

DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model

Maulana Bisyir Azhari, David Hyunchul Shim

机构 * School of Electrical Engineering, Korea Advanced Institute of Science and Technology（电气工程学院，韩国科学技术院）

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

Comments 8 pages, 6 figures. Accepted for publication in IEEE Robotics and Automation Letters (RA-L), July 2025

2507.11633 2025-07-17 cs.AI 79%

General Modular Harness for LLM Agents in Multi-Turn Gaming Environments

Yuxuan Zhang, Haoyang Yu, Lanxiang Hu, Haojian Jin, Hao Zhang

机构 * Halıcıoğlu Data Science Institute (HDSI), University of California San Diego, La Jolla, CA, USA（Halıcıoğlu数据科学研究所（HDSI），加州大学圣地亚哥分校，拉贾拉，加州，美国）

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

Comments 8 pages, ICML MAS workshop

2507.00453 2025-07-02 cs.LG 79%

Recurrent Memory-Augmented Transformers with Chunked Attention for Long-Context Language Modeling

Ankit Kashyap

机构 * Independent Researcher（独立研究者）

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

Comments 19 pages, 9 figures, 1 table; implemented entirely from scratch in PyTorch

2506.09591 2025-06-12 cs.CL 79%

Memorization in Language Models through the Lens of Intrinsic Dimension

Stefan Arnold

机构 * Friedrich-Alexander-Universität Erlangen-Nürnberg（埃朗根-纽伦堡弗里德里希-亚历山大大学）

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

2505.20718 2025-05-29 cs.CV cs.AI 79%

VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models

Kui Wu, Shuhang Xu, Hao Chen, Churan Wang, Zhoujun Li, Yizhou Wang, Fangwei Zhong

机构 * State Key Laboratory of Complex & Critical Software Environment, Beihang University（北京航空航天大学复杂与关键软件环境国家重点实验室）； School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）； City University of Macau（澳门城市大学）； Center on Frontiers of Computing Studies, School of Computer Science, Nat’l Eng. Research Center of Visual Technology, Peking University（北京大学计算机学院前沿计算研究中心、国家工程视觉技术研究中心）

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

2502.04395 2025-05-27 cs.CV cs.LG 79%

Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting

Siru Zhong, Weilin Ruan, Ming Jin, Huan Li, Qingsong Wen, Yuxuan Liang

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

Comments 20 pages

2502.13843 2025-04-21 cs.IR cs.AI 79%

AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations

Jiahao Liu, Shengkang Gu, Dongsheng Li, Guangping Zhang, Mingzhe Han, Hansu Gu, Peng Zhang, Tun Lu, Li Shang, Ning Gu

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

Comments Accepted by SIGIR 2025, 6 pages

2310.08948 2025-04-14 cs.CV cs.AI 79%

Federated Class-Incremental Learning with Prompting

Xin Luo, Fang-Yi Liang, Jiale Liu, Yu-Wei Zhan, Zhen-Duo Chen, Xin-Shun Xu

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

2411.08909 2025-04-03 q-bio.BM cs.LG 79%

Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers

Yingheng Wang, Zichen Wang, Gil Sadeh, Luca Zancato, Alessandro Achille, George Karypis, Huzefa Rangwala

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

Comments model weights open-sourced at https://github.com/amazon-science/LC-PLM

2410.19732 2024-12-23 cs.CL cs.CV 79%

Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models

Yucheng Zhou, Zhi Rao, Jun Wan, Jianbing Shen

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

2404.04163 2024-10-29 cs.IR cs.CL 79%

Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval

João Coelho, Bruno Martins, João Magalhães, Jamie Callan, Chenyan Xiong

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

2410.16775 2024-10-23 cs.CL 79%

Context-Aware LLM Translation System Using Conversation Summarization and Dialogue History

Mingi Sung, Seungmin Lee, Jiwon Kim, Sejoon Kim

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

Comments Accepted to WMT 2024

2410.13510 2024-10-18 cs.CL cs.CV 79%

GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models

Aditya Sharma, Aman Dalmia, Mehran Kazemi, Amal Zouaq, Christopher J. Pal

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

2410.10469 2024-10-15 cs.LG stat.ML 79%

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

Xu Liu, Juncheng Liu, Gerald Woo, Taha Aksu, Yuxuan Liang, Roger Zimmermann, Chenghao Liu, Silvio Savarese, Caiming Xiong, Doyen Sahoo

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

2410.07192 2024-10-11 cs.DC cs.LG 79%

PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training

Daiyaan Arfeen, Zhen Zhang, Xinwei Fu, Gregory R. Ganger, Yida Wang

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

2410.06519 2024-10-10 cs.CL 79%

SEGMENT+: Long Text Processing with Short-Context Language Models

Wei Shi, Shuang Li, Kerun Yu, Jinglei Chen, Zujie Liang, Xinhui Wu, Yuxi Qian, Feng Wei, Bo Zheng, Jiaqing Liang, Jiangjie Chen, Yanghua Xiao

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

Comments EMNLP 2024

2410.05162 2024-10-08 cs.CL 79%

Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models

Mehrdad Farahani, Richard Johansson

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

Comments Accepted at EMNLP 2024

2409.13530 2024-09-23 cs.LG 79%

Towards Long-Context Time Series Foundation Models

Nina Żukowska, Mononito Goswami, Michał Wiliński, Willa Potosnak, Artur Dubrawski

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

2409.12264 2024-09-20 cs.LG stat.ML 79%

User-friendly Foundation Model Adapters for Multivariate Time Series Classification

Vasilii Feofanov, Romain Ilbert, Malik Tiomoko, Themis Palpanas, Ievgen Redko

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

Comments The first two authors contributed equally

2407.09498 2024-09-11 cs.CV cs.LG 79%

OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation

Yunbei Zhang, Akshay Mehra, Jihun Hamm

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

Comments WACV2025

2409.01666 2024-09-04 cs.CL 79%

In Defense of RAG in the Era of Long-Context Language Models

Tan Yu, Anbang Xu, Rama Akkiraju

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

2404.04516 2024-08-09 cs.HC cs.CL cs.CY 79%

Language Models as Critical Thinking Tools: A Case Study of Philosophers

Andre Ye, Jared Moore, Rose Novick, Amy X. Zhang

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

2404.06654 2024-08-08 cs.CL 79%

RULER: What's the Real Context Size of Your Long-Context Language Models?

Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman, Shantanu Acharya, Dima Rekesh, Fei Jia, Yang Zhang, Boris Ginsburg

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

Comments COLM 2024; Code is available at https://github.com/hsiehjackson/RULER

2408.03246 2024-08-07 cs.CL 79%

Making Long-Context Language Models Better Multi-Hop Reasoners

Yanyang Li, Shuo Liang, Michael R. Lyu, Liwei Wang

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

Comments ACL 2024 Main Conference Camera Ready; Dataset, model, and code are available at https://github.com/LaVi-Lab/LongContextReasoner

2408.03062 2024-08-07 cs.CL 79%

Analysis of Argument Structure Constructions in a Deep Recurrent Language Model

Pegah Ramezani, Achim Schilling, Patrick Krauss

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

2407.21778 2024-08-01 cs.AI cs.RO 79%

Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Libraries

Felix Ocker, Daniel Tanneberg, Julian Eggert, Michael Gienger

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

Comments 19 pages, 4 figures

1. 长上下文与记忆 4771 篇

Closer to Reality: Practical Semi-Supervised Federated Learning for Foundation Model Adaptation

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization

Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models

Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning

DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model

General Modular Harness for LLM Agents in Multi-Turn Gaming Environments

Recurrent Memory-Augmented Transformers with Chunked Attention for Long-Context Language Modeling

Memorization in Language Models through the Lens of Intrinsic Dimension

VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models

Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting

AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations

Federated Class-Incremental Learning with Prompting

Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers

Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models

Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval

Context-Aware LLM Translation System Using Conversation Summarization and Dialogue History

GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training

SEGMENT+: Long Text Processing with Short-Context Language Models

Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models

Towards Long-Context Time Series Foundation Models

User-friendly Foundation Model Adapters for Multivariate Time Series Classification

OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation

In Defense of RAG in the Era of Long-Context Language Models

Language Models as Critical Thinking Tools: A Case Study of Philosophers

RULER: What's the Real Context Size of Your Long-Context Language Models?

Making Long-Context Language Models Better Multi-Hop Reasoners

Analysis of Argument Structure Constructions in a Deep Recurrent Language Model

Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Libraries