语言大模型 / LLM - arXivDaily 专题

2509.22170 2025-09-29 cs.SE 78%

Leveraging LLM Agents for Automated Video Game Testing

Chengjia Wang, Lanling Tang, Ming Yuan, Jiongchi Yu, Xiaofei Xie, Jiajun Bu

专题命中长上下文与记忆：LLM(title,abstract)

Comments 17 pages

2508.08256 2025-09-18 cs.DB 78%

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference

Dongwei Wang, Zijie Liu, Song Wang, Yuxin Ren, Jianing Deng, Jingtong Hu, Tianlong Chen, Huanrui Yang

专题命中长上下文与记忆：LLM(title,abstract)

Comments EMNLP2025 Camera-ready

2508.18721 2025-09-04 cs.SE 78%

LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging

Yunrui Pei, Hongshu Wang, Wenjie Zhang, Yun Lin, Weiyu Kong, Jin song Dong

专题命中长上下文与记忆：LLM(title,abstract)

2508.12175 2025-08-19 cs.CR 78%

Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous

Ben Nassi, Stav Cohen, Or Yair

专题命中长上下文与记忆：LLM(title,abstract)

Comments https://sites.google.com/view/invitation-is-all-you-need/home

2508.08585 2025-08-13 eess.AS 78%

Joint decoding method for controllable contextual speech recognition based on Speech LLM

Yangui Fang, Jing Peng, Yu Xi, Xu Li, Haoyu Li, Chengwei Zhang, Guohui Zhong, Kai Yu

专题命中长上下文与记忆：LLM(title,abstract)

2508.04450 2025-08-07 eess.IV cs.CV 78%

TotalRegistrator: Towards a Lightweight Foundation Model for CT Image Registration

Xuan Loc Pham, Gwendolyn Vuurberg, Marjan Doppen, Joey Roosen, Tip Stille, Thi Quynh Ha, Thuy Duong Quach, Quoc Vu Dang, Manh Ha Luu, Ewoud J. Smit, Hong Son Mai, Mattias Heinrich, Bram van Ginneken, Mathias Prokop, Alessa Hering

机构 * Department of Imaging, Radboudumc, Nijmegen, the Netherlands（影像部，Radboudumc，尼姆egen，荷兰）； Institute for Medical Informatics, University of Lübeck, Lübeck, Germany（医学信息研究所，吕贝克大学，吕贝克，德国）； Department of Nuclear Medicine, Hospital 108, Hanoi, Vietnam（核医学部，108医院，河内，越南）； Department of Diagnostic Imaging and Interventional Radiology, Thai Nguyen National Hospital, Thai Nguyen, Vietnam（诊断影像和介入放射科，Thai Nguyen国家医院，Thai Nguyen，越南）； Interventional Radiology Center, Tam Anh Hospital, Hanoi, Vietnam（介入放射科中心，Tam Anh医院，河内，越南）； FET, Vietnam National University, University of Engineering and Technology, Hanoi, Vietnam（FET，越南国家大学，工程与技术大学，河内，越南）

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

2507.09217 2025-07-15 cs.CV 78%

Online Long-term Point Tracking in the Foundation Model Era

Görkay Aydemir

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

Comments arXiv admin note: substantial text overlap with arXiv:2501.18487

2501.18564 2025-07-15 cs.RO 78%

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation

Haoquan Fang, Markus Grotz, Wilbert Pumacay, Yi Ru Wang, Dieter Fox, Ranjay Krishna, Jiafei Duan

机构 * University of Washington（华盛顿大学）； Universidad Católica San Pablo（卡塔尔大学）； NVIDIA（NVIDIA公司）； Allen Institute for Artificial Intelligence（人工智能研究院）

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

Comments Including Appendix, Project Page: https://sam2act.github.io

2506.22636 2025-07-01 cs.CV 78%

ReCo: Reminder Composition Mitigates Hallucinations in Vision-Language Models

Sotirios Panagiotis Chytas, Miso Choi, Hyunwoo J. Kim, Vikas Singh

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校）； Korea University（韩国大学）； KAIST（韩国科学技术院）

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

2503.20362 2025-06-30 cs.CV 78%

Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding

Joao Pereira, Vasco Lopes, David Semedo, Joao Neves

机构 * DeepNeuronic ； NOVA LINCS, University of Beira Interior（NOVA LINCS，贝拉内里大学）

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

2506.04167 2025-06-05 cs.HC 78%

Neural and Cognitive Impacts of AI: The Influence of Task Subjectivity on Human-LLM Collaboration

Matthew Russell, Aman Shah, Giles Blaney, Judith Amores, Mary Czerwinski, Robert J. K. Jacob

专题命中长上下文与记忆：LLM(title,abstract)

Comments 15 pages, 12 figures

2505.24496 2025-06-02 eess.AS 78%

Speech Token Prediction via Compressed-to-fine Language Modeling for Speech Generation

Wenrui Liu, Qian Chen, Wen Wang, Yafeng Chen, Jin Xu, Zhifang Guo, Guanrou Yang, Weiqin Li, Xiaoda Yang, Tao Jin, Minghui Fang, Jialong Zuo, Bai Jionghao, Zemin Liu

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

2505.19218 2025-05-27 cs.CV 78%

Advancing Video Self-Supervised Learning via Image Foundation Models

Jingwei Wu, Zhewei Huang, Chang Liu

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

Journal ref Pattern Recognition Letters, 2025, 192: 22-28

2503.00715 2025-05-02 cs.HC 78%

Exploring the Design Space of Real-time LLM Knowledge Support Systems: A Case Study of Jargon Explanations

Yuhan Liu, Aadit Shah, Jordan Ackerman, Manaswi Saha

专题命中长上下文与记忆：LLM(title,abstract)

Comments This work is accepted and will be presented at CHI25

Journal ref Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

2501.06727 2025-04-29 eess.AS cs.SD 78%

Integrating Pause Information with Word Embeddings in Language Models for Alzheimer's Disease Detection from Spontaneous Speech

Yu Pu, Wei-Qiang Zhang

机构 * Department of Electronic Engineering, Tsinghua University（电子工程系，清华大学）

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

Comments accepted by ICASSP2025. Copyright 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component

Journal ref ICASSP (2025)

2503.04359 2025-03-07 cs.SE 78%

LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding

Jia Li, Xuyuan Guo, Lei Li, Kechi Zhang, Ge Li, Jia Li, Zhengwei Tao, Fang Liu, Chongyang Tao, Yuqi Zhu, Zhi Jin

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

Comments 18 pages

2503.04214 2025-03-07 cs.SE 78%

Extracting Fix Ingredients using Language Models

Julian Aron Prenner, Romain Robbes

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

2412.14479 2024-12-20 cs.DC 78%

Frenzy: A Memory-Aware Serverless LLM Training System for Heterogeneous GPU Clusters

Zihan Chang, Sheng Xiao, Shuibing He, Siling Yang, Zhe Pan, Dong Li

专题命中长上下文与记忆：LLM(title,abstract)

2412.09875 2024-12-16 cs.CV 78%

Selective State Space Memory for Large Vision-Language Models

Chee Ng, Yuen Fung

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

2412.09616 2024-12-16 cs.CV 78%

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

Junqi Ge, Ziyi Chen, Jintao Lin, Jinguo Zhu, Xihui Liu, Jifeng Dai, Xizhou Zhu

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

Comments The code and models will be available at https://github.com/OpenGVLab/V2PE

2406.01288 2024-10-31 cs.CL cs.AI cs.CR cs.LG 78%

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu, Jing Jiang, Min Lin

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

Comments NeurIPS 2024

2410.14931 2024-10-22 cs.HC 78%

"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction

Shuning Zhang, Lyumanshan Ye, Xin Yi, Jingyu Tang, Bo Shui, Haobin Xing, Pengfei Liu, Hewu Li

专题命中长上下文与记忆：LLM(title,abstract)

2408.04821 2024-10-04 cs.RO 78%

VLM-MPC: Vision Language Foundation Model (VLM)-Guided Model Predictive Controller (MPC) for Autonomous Driving

Keke Long, Haotian Shi, Jiaxi Liu, Xiaopeng Li

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

2401.01325 2024-07-12 cs.CL cs.AI cs.LG 78%

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Hongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang, Zirui Liu, Chia-Yuan Chang, Huiyuan Chen, Xia Hu

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

Comments ICML2024 Spotlight

2405.11233 2024-05-21 cs.SE 78%

Bridge and Hint: Extending Pre-trained Language Models for Long-Range Code

Yujia Chen, Cuiyun Gao, Zezhou Yang, Hongyu Zhang, Qing Liao

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

Comments Accepted by ISSTA 2024

2401.16603 2024-01-31 cs.CR cs.DC 78%

LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory

Tyler Sorensen, Heidy Khlaaf

专题命中长上下文与记忆：LLM(title,abstract)

2401.01529 2024-01-04 cs.CV 78%

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering

Ziyi Bai, Ruiping Wang, Xilin Chen

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

Comments Accepted in NeurIPS 2023

2310.13418 2023-10-23 eess.AS eess.SP 78%

GenDistiller: Distilling Pre-trained Language Models based on Generative Models

Yingying Gao, Shilei Zhang, Zihao Cui, Yanhan Xu, Chao Deng, Junlan Feng

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

2302.14250 2023-04-21 cs.CV 78%

Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation

Chaohui Yu, Qiang Zhou, Jingliang Li, Jianlong Yuan, Zhibin Wang, Fan Wang

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

Comments CVPR 2023

2208.03987 2022-12-09 cs.CV 78%

Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model

Di Wang, Qiming Zhang, Yufei Xu, Jing Zhang, Bo Du, Dacheng Tao, Liangpei Zhang

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

Comments Accepted by IEEE TGRS. The codes and models are released at https://github.com/ViTAE-Transformer/Remote-Sensing-RVSA

1. 长上下文与记忆 4835 篇

Leveraging LLM Agents for Automated Video Game Testing

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference

LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging

Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous

Joint decoding method for controllable contextual speech recognition based on Speech LLM

TotalRegistrator: Towards a Lightweight Foundation Model for CT Image Registration

Online Long-term Point Tracking in the Foundation Model Era

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation

ReCo: Reminder Composition Mitigates Hallucinations in Vision-Language Models

Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding

Neural and Cognitive Impacts of AI: The Influence of Task Subjectivity on Human-LLM Collaboration

Speech Token Prediction via Compressed-to-fine Language Modeling for Speech Generation

Advancing Video Self-Supervised Learning via Image Foundation Models

Exploring the Design Space of Real-time LLM Knowledge Support Systems: A Case Study of Jargon Explanations

Integrating Pause Information with Word Embeddings in Language Models for Alzheimer's Disease Detection from Spontaneous Speech

LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding

Extracting Fix Ingredients using Language Models

Frenzy: A Memory-Aware Serverless LLM Training System for Heterogeneous GPU Clusters

Selective State Space Memory for Large Vision-Language Models

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction

VLM-MPC: Vision Language Foundation Model (VLM)-Guided Model Predictive Controller (MPC) for Autonomous Driving

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Bridge and Hint: Extending Pre-trained Language Models for Long-Range Code

LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering

GenDistiller: Distilling Pre-trained Language Models based on Generative Models

Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation

Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model