语言大模型 / LLM - arXivDaily 专题

2405.20681 2025-03-03 cs.CR cs.AI 85%

No Free Lunch Theorem for Privacy-Preserving LLM Inference

Xiaojin Zhang, Yahao Pang, Yan Kang, Wei Chen, Lixin Fan, Hai Jin, Qiang Yang

专题命中效率与部署：LLM(title)；large language model(abstract)；language model(abstract)；prompting(abstract)

2502.16235 2025-02-28 cs.AI 85%

Dynamic Parallel Tree Search for Efficient LLM Reasoning

Yifu Ding, Wentao Jiang, Shunyu Liu, Yongcheng Jing, Jinyang Guo, Yingjie Wang, Jing Zhang, Zengmao Wang, Ziwei Liu, Bo Du, Xianglong Liu, Dacheng Tao

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 17 pages, 11 figures

2502.14182 2025-02-21 cs.CR cs.LG 85%

Multi-Faceted Studies on Data Poisoning can Advance LLM Development

Pengfei He, Yue Xing, Han Xu, Zhen Xiang, Jiliang Tang

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2502.11021 2025-02-18 cs.NI cs.CL 85%

Leveraging Uncertainty Estimation for Efficient LLM Routing

Tuo Zhang, Asal Mehradfar, Dimitrios Dimitriadis, Salman Avestimehr

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2502.10202 2025-02-17 cs.CL 85%

Can Post-Training Quantization Benefit from an Additional QLoRA Integration?

Xiliang Zhu, Elena Khasanova, Cheng Chen

专题命中效率与部署：post-training(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to NAACL 2025 Industry Track

2502.09209 2025-02-14 cs.AI 85%

On LLM-generated Logic Programs and their Inference Execution Methods

Paul Tarau

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments In Proceedings ICLP 2024, arXiv:2502.08453

Journal ref EPTCS 416, 2025, pp. 1-14

2501.11779 2025-02-12 cs.LG cs.DC cs.PF 85%

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference

Pouya Hamadanian, Sadjad Fouladi

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2410.13919 2025-02-12 cs.CR cs.AI 85%

LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild

Reworr, Dmitrii Volkov

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2502.05220 2025-02-11 cs.CR cs.AI 85%

Aero-LLM: A Distributed Framework for Secure UAV Communication and Intelligent Decision-Making

Balakrishnan Dharmalingam, Rajdeep Mukherjee, Brett Piggott, Guohuan Feng, Anyi Liu

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments This manuscript was accepted by the 1st International Workshop on Integrated Sensing, Communication, and Computing in Internet of Things (IoT) Systems at the The 33rd International Conference on Computer Communications and Networks (ICCCN 2024)

2502.00026 2025-02-10 cs.AR cs.AI 85%

Pushing the Limits of BFP on Narrow Precision LLM Inference

Hui Wang, Yuan Cheng, Xiaomeng Han, Zhengpeng Zhao, Dawei Yang, Zhe Jiang

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2501.18624 2025-02-10 cs.CR cs.AI 85%

Membership Inference Attacks Against Vision-Language Models

Yuke Hu, Zheng Li, Zhihao Liu, Yang Zhang, Zhan Qin, Kui Ren, Chun Chen

专题命中效率与部署：language model(title,abstract)；large language model(abstract)；instruction tuning(abstract)；分类 cs.AI

Comments Accepted by USENIX'25; 22 pages, 28 figures;

2502.03589 2025-02-07 cs.DC cs.LG 85%

HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference

Zeyu Zhang, Haiying Shen, Shay Vargaftik, Ran Ben Basat, Michael Mitzenmacher, Minlan Yu

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2502.02743 2025-02-06 cs.LG 85%

LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing

Yang Li

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2410.14442 2025-02-06 cs.CL 85%

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference

You Wu, Haoyi Wu, Kewei Tu

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to NAACL2025 main conference

2502.00922 2025-02-04 cs.LG cs.AR 85%

Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference

Patrick Yubeaton, Tareq Mahmoud, Shehab Naga, Pooria Taheri, Tianhua Xia, Arun George, Yasmein Khalil, Sai Qian Zhang, Siddharth Joshi, Chinmay Hegde, Siddharth Garg

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2501.16673 2025-01-31 cs.CL 85%

LLM-AutoDiff: Auto-Differentiate Any LLM Workflow

Li Yin, Zhangyang Wang

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2403.06942 2025-01-28 eess.SY cs.LG cs.SY stat.ML 85%

Grid Monitoring with Synchro-Waveform and AI Foundation Model Technologies

Lang Tong, Xinyi Wang, Qing Zhao

专题命中效率与部署：foundation model(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2501.14784 2025-01-28 cs.DC cs.AI 85%

DeServe: Towards Affordable Offline LLM Inference via Decentralization

Linyu Wu, Xiaoyuan Liu, Tianneng Shi, Zhe Ye, Dawn Song

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2501.14743 2025-01-28 cs.DC cs.LG cs.PF 85%

KVDirect: Distributed Disaggregated LLM Inference

Shiyang Chen, Rain Jiang, Dezhi Yu, Jinlai Xu, Mengyuan Chao, Fanlong Meng, Chenyu Jiang, Wei Xu, Hang Liu

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2501.14312 2025-01-27 cs.DC cs.LG 85%

Locality-aware Fair Scheduling in LLM Serving

Shiyi Cao, Yichuan Wang, Ziming Mao, Pin-Lun Hsu, Liangsheng Yin, Tian Xia, Dacheng Li, Shu Liu, Yineng Zhang, Yang Zhou, Ying Sheng, Joseph Gonzalez, Ion Stoica

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2501.09107 2025-01-17 cs.LG 85%

Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach

Alireza Ghaffari, Sharareh Younesian, Boxing Chen, Vahid Partovi Nia, Masoud Asgharian

专题命中效率与部署：post-training(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2411.19876 2025-01-13 cs.CR cs.AI 85%

LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states

Luis Ibanez-Lissen, Lorena Gonzalez-Manzano, Jose Maria de Fuentes, Nicolas Anciaux, Joaquin Garcia-Alfaro

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2405.10587 2025-01-09 cs.CL cs.IR 85%

RDRec: Rationale Distillation for LLM-based Recommendation

Xinfeng Wang, Jin Cui, Yoshimi Suzuki, Fumiyo Fukumoto

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 10 pages. Accepted to ACL 2024 Main as a short paper

2501.03991 2025-01-08 cs.CL 85%

Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles

Yuxi Xia, Pedro Henrique Luz de Araujo, Klim Zaporojets, Benjamin Roth

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 24 pages, 11 figures, 8 tables

2501.03288 2025-01-08 cs.SE cs.AI 85%

CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models

Zhenyu Xu, Victor S. Sheng

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2501.02600 2025-01-07 cs.DC cs.AI 85%

TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms

Jovan Stojkovic, Chaojie Zhang, Íñigo Goiri, Esha Choukse, Haoran Qiu, Rodrigo Fonseca, Josep Torrellas, Ricardo Bianchini

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2501.02191 2025-01-07 cs.LG cs.SI 85%

On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing

Jianwei Wang, Kai Wang, Ying Zhang, Wenjie Zhang, Xiwei Xu, Xuemin Lin

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2410.09824 2025-01-07 cs.CL 85%

LLM-Based Multi-Agent Systems are Scalable Graph Generative Models

Jiarui Ji, Runlin Lei, Jialing Bi, Zhewei Wei, Xu Chen, Yankai Lin, Xuchen Pan, Yaliang Li, Bolin Ding

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2408.03516 2025-01-07 cs.CV cs.LG cs.RO 85%

Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian

Amirhosein Chahe, Lifeng Zhou

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2412.20682 2024-12-31 cs.CV cs.LG 85%

Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks

Yuhe Ding, Bo Jiang, Aihua Zheng, Qin Xu, Jian Liang

专题命中效率与部署：language model(title,abstract)；large language model(abstract)；pretraining(abstract)；分类 cs.LG

1. 效率与部署 22368 篇

No Free Lunch Theorem for Privacy-Preserving LLM Inference

Dynamic Parallel Tree Search for Efficient LLM Reasoning

Multi-Faceted Studies on Data Poisoning can Advance LLM Development

Leveraging Uncertainty Estimation for Efficient LLM Routing

Can Post-Training Quantization Benefit from an Additional QLoRA Integration?

On LLM-generated Logic Programs and their Inference Execution Methods

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference

LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild

Aero-LLM: A Distributed Framework for Secure UAV Communication and Intelligent Decision-Making

Pushing the Limits of BFP on Narrow Precision LLM Inference

Membership Inference Attacks Against Vision-Language Models

HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference

LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference

Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference

LLM-AutoDiff: Auto-Differentiate Any LLM Workflow

Grid Monitoring with Synchro-Waveform and AI Foundation Model Technologies

DeServe: Towards Affordable Offline LLM Inference via Decentralization

KVDirect: Distributed Disaggregated LLM Inference

Locality-aware Fair Scheduling in LLM Serving

Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach

LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states

RDRec: Rationale Distillation for LLM-based Recommendation

Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles

CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models

TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms

On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing

LLM-Based Multi-Agent Systems are Scalable Graph Generative Models

Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian

Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks