语言大模型 / LLM - arXivDaily 专题

2503.03777 2025-03-07 cs.OS cs.AI 83%

FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference

Hongchao Du, Shangyu Wu, Arina Kharlamova, Nan Guan, Chun Jason Xue

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

Comments 9 pages, 5 figures, to be published in EuroMLSys '25

2503.02718 2025-03-05 cs.CL 83%

Evaluating Knowledge Generation and Self-Refinement Strategies for LLM-based Column Type Annotation

Keti Korini, Christian Bizer

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

2412.02956 2025-03-04 cs.CL 83%

Curriculum-style Data Augmentation for LLM-based Metaphor Detection

Kaidi Jia, Yanxia Wu, Ming Liu, Rongsheng Li

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

2408.00724 2025-03-04 cs.AI 83%

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, Yiming Yang

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

2502.16806 2025-03-04 cs.CL 83%

CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers

Anh Duc Le, Tu Vu, Nam Le Hai, Nguyen Thi Ngoc Diep, Linh Ngo Van, Trung Le, Thien Huu Nguyen

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

2502.20566 2025-03-03 cs.LG 83%

Stochastic Rounding for LLM Training: Theory and Practice

Kaan Ozkara, Tao Yu, Youngsuk Park

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

Comments AISTATS 2025

2502.10636 2025-03-03 cs.AI cs.HC cs.RO 83%

USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot Interactions

Hamed Rahimi, Adil Bahaj, Mouad Abrini, Mahdi Khoramshahi, Mounir Ghogho, Mohamed Chetouani

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

2502.18512 2025-02-27 cs.CV cs.AI 83%

FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression

Jianjian Li, Junquan Fan, Feng Tang, Gang Huang, Shitao Zhu, Songlin Liu, Nian Xie, Wulong Liu, Yong Liao

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

Comments 20 pages, 18 figures, 6 tables

2502.18468 2025-02-27 cs.SE cs.AI cs.CR 83%

SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment

Ariful Haque, Sunzida Siddique, Md. Mahfuzur Rahman, Ahmed Rafi Hasan, Laxmi Rani Das, Marufa Kamal, Tasnim Masura, Kishor Datta Gupta

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

2410.09343 2025-02-27 cs.CL 83%

ELICIT: LLM Augmentation via External In-Context Capability

Futing Wang, Jianhao Yan, Yue Zhang, Tao Lin

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

Comments Published at ICLR 2025

2502.18405 2025-02-26 cs.LG 83%

Enhancing DNA Foundation Models to Address Masking Inefficiencies

Monireh Safari, Pablo Millan Arias, Scott C. Lowe, Lila Kari, Angel X. Chang, Graham W. Taylor

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

Comments 10 pages, 5 figures

2502.17763 2025-02-26 cs.CR cs.AI cs.DC cs.PF 83%

Design and implementation of a distributed security threat detection system integrating federated learning and multimodal LLM

Yuqing Wang, Xiao Yang

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

2502.14976 2025-02-24 cs.LG cs.CR cs.CV 83%

EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models

Nastaran Darabi, Devashri Naik, Sina Tayebati, Dinithi Jayasuriya, Ranganath Krishnan, Amit Ranjan Trivedi

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

2502.14412 2025-02-21 cs.CV cs.CR cs.LG 83%

Evaluating Precise Geolocation Inference Capabilities of Vision Language Models

Neel Jay, Hieu Minh Nguyen, Trung Dung Hoang, Jacob Haimes

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

Comments AAAI 2025 Workshop DATASAFE

2502.14271 2025-02-21 cs.CL 83%

PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant

Congrui Yin, Evan Wei, Zhongxing Zhang, Zaifu Zhan

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

2502.13886 2025-02-20 cs.LG cs.CE 83%

Refining embeddings with fill-tuning: data-efficient generalised performance improvements for materials foundation models

Matthew P. Wilson, Edward O. Pyzer-Knapp, Nicolas Galichet, Luke Dicks

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

Comments 8 pages, 4 figures

2410.20727 2025-02-20 cs.LG stat.ML 83%

Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment

Tong Yang, Jincheng Mei, Hanjun Dai, Zixin Wen, Shicong Cen, Dale Schuurmans, Yuejie Chi, Bo Dai

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

2502.11349 2025-02-18 cs.LG cs.PF stat.ML 83%

Biases in Edge Language Models: Detection, Analysis, and Mitigation

Vinamra Sharma, Danilo Pietro Pau, José Cano

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

Comments Accepted as a full paper by the 2025 EDGE AI FOUNDATION Austin

2502.10486 2025-02-18 cs.CR cs.AI cs.CV 83%

VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap

Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen

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

Comments Work in progress

2405.09113 2025-02-13 cs.LG 83%

Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

Kai Hu, Weichen Yu, Yining Li, Kai Chen, Tianjun Yao, Xiang Li, Wenhe Liu, Lijun Yu, Zhiqiang Shen, Matt Fredrikson

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

Journal ref 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

2501.13629 2025-02-11 cs.CL 83%

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Zhenghao Lin, Zihao Tang, Xiao Liu, Yeyun Gong, Yi Cheng, Qi Chen, Hang Li, Ying Xin, Ziyue Yang, Kailai Yang, Yu Yan, Xiao Liang, Shuai Lu, Yiming Huang, Zheheng Luo, Lei Qu, Xuan Feng, Yaoxiang Wang, Yuqing Xia, Feiyang Chen, Yuting Jiang, Yasen Hu, Hao Ni, Binyang Li, Guoshuai Zhao, Jui-Hao Chiang, Zhongxin Guo, Chen Lin, Kun Kuang, Wenjie Li, Yelong Shen, Jian Jiao, Peng Cheng, Mao Yang

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

2502.05947 2025-02-11 cs.CV cs.CL 83%

Acceleration Multiple Heads Decoding for LLM via Dynamic Tree Attention

Zhendong Zhang

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

2412.07679 2025-02-11 cs.CV cs.AI 83%

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

Greg Heinrich, Mike Ranzinger, Hongxu, Yin, Yao Lu, Jan Kautz, Andrew Tao, Bryan Catanzaro, Pavlo Molchanov

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

2502.05233 2025-02-11 cs.CL cs.IR 83%

Efficient Knowledge Feeding to Language Models: A Novel Integrated Encoder-Decoder Architecture

S Santosh Kumar, Rishi Gottimukkala, Supriya Devidutta, Karthikeyan S

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

Comments Submitted to ACM TIST journal: under revision stage, 8 pages, 2 figures

2502.02074 2025-02-05 cs.CL 83%

Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language models

Prasanta Bhattacharya, Hong Zhang, Yiming Cao, Wei Gao, Brandon Siyuan Loh, Joseph J. P. Simons, Liang Ze Wong

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

2501.19317 2025-02-03 cs.CL 83%

LLM-based Affective Text Generation Quality Based on Different Quantization Values

Yarik Menchaca Resendiz, Roman Klinger

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

2501.15570 2025-01-28 cs.CL 83%

ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer

Lin Yueyu, Li Zhiyuan, Peter Yue, Liu Xiao

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

2410.08405 2025-01-10 cs.CV cs.AI 83%

AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning

Muhammad Awais, Ali Husain Salem Abdulla Alharthi, Amandeep Kumar, Hisham Cholakkal, Rao Muhammad Anwer

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

Comments Accepted at WACV, 2025

2501.03855 2025-01-08 cs.CL 83%

BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context

Alexis Matzopoulos, Charl Hendriks, Hishaam Mahomed, Francois Meyer

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

2412.17743 2024-12-25 cs.CL 83%

YuLan-Mini: An Open Data-efficient Language Model

Yiwen Hu, Huatong Song, Jia Deng, Jiapeng Wang, Jie Chen, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Wayne Xin Zhao, Ji-Rong Wen

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

1. 效率与部署 22456 篇

FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference

Evaluating Knowledge Generation and Self-Refinement Strategies for LLM-based Column Type Annotation

Curriculum-style Data Augmentation for LLM-based Metaphor Detection

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers

Stochastic Rounding for LLM Training: Theory and Practice

USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot Interactions

FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression

SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment

ELICIT: LLM Augmentation via External In-Context Capability

Enhancing DNA Foundation Models to Address Masking Inefficiencies

Design and implementation of a distributed security threat detection system integrating federated learning and multimodal LLM

EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models

Evaluating Precise Geolocation Inference Capabilities of Vision Language Models

PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant

Refining embeddings with fill-tuning: data-efficient generalised performance improvements for materials foundation models

Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment

Biases in Edge Language Models: Detection, Analysis, and Mitigation

VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap

Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Acceleration Multiple Heads Decoding for LLM via Dynamic Tree Attention

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

Efficient Knowledge Feeding to Language Models: A Novel Integrated Encoder-Decoder Architecture

Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language models

LLM-based Affective Text Generation Quality Based on Different Quantization Values

ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer

AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning

BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context

YuLan-Mini: An Open Data-efficient Language Model