语言大模型 / LLM - arXivDaily 专题

2502.11098 2025-02-18 cs.AI cs.LG cs.MA 81%

Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems

Zhao Wang, Sota Moriyama, Wei-Yao Wang, Briti Gangopadhyay, Shingo Takamatsu

机构 * Sony Group Corporation（索尼集团公司）

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

2502.09419 2025-02-14 cs.CL cs.LG 81%

On multi-token prediction for efficient LLM inference

Somesh Mehra, Javier Alonso Garcia, Lukas Mauch

机构 * European Research Center (EUREC), Sony Europe B.V.（欧洲研究中心（EUREC），索尼欧洲有限公司）； Swiss Federal Institute of Technology Lausanne (EPFL)（洛桑联邦理工学院）

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

2502.06892 2025-02-12 cs.LG cs.AI 81%

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

Bowei He, Lihao Yin, Hui-Ling Zhen, Jianping Zhang, Lanqing Hong, Mingxuan Yuan, Chen Ma

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

Comments Accepted by ICLR 2025

2410.06625 2025-02-11 cs.CV cs.CL cs.LG 81%

ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

Yi Ding, Bolian Li, Ruqi Zhang

机构 * Purdue University（普渡大学）

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

Comments 29pages

2502.03395 2025-02-06 cs.LG cs.AI 81%

Benchmarking Time Series Forecasting Models: From Statistical Techniques to Foundation Models in Real-World Applications

Issar Arab, Rodrigo Benitez

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

2409.16295 2025-02-06 eess.AS cs.CL cs.LG cs.SD 81%

Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget

Andy T. Liu, Yi-Cheng Lin, Haibin Wu, Stefan Winkler, Hung-yi Lee

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

Comments Accepted to IEEE SLT 2024

Journal ref 2024 IEEE Spoken Language Technology Workshop (SLT)

2502.02584 2025-02-05 cs.LG cs.AI 81%

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

Zongyu Lin, Yao Tang, Xingcheng Yao, Da Yin, Ziniu Hu, Yizhou Sun, Kai-Wei Chang

机构 * University of California, Los Angeles（加利福尼亚大学洛杉矶分校）

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

2502.02201 2025-02-05 cs.HC cs.AI cs.CL cs.ET 81%

Can You Move These Over There? An LLM-based VR Mover for Supporting Object Manipulation

Xiangzhi Eric Wang, Zackary P. T. Sin, Ye Jia, Daniel Archer, Wynonna H. Y. Fong, Qing Li, Chen Li

机构 * The Hong Kong Polytechnic University（香港理工大学）； University College London（伦敦大学学院）； Heep Yunn School（协恩中学）

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

Comments 64 pages (30 in main text), 22 figures (19 in main text)

2412.11276 2025-02-03 cs.LG cs.AI eess.SP 81%

Wearable Accelerometer Foundation Models for Health via Knowledge Distillation

Salar Abbaspourazad, Anshuman Mishra, Joseph Futoma, Andrew C. Miller, Ian Shapiro

机构 * Apple Inc（苹果公司）

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

Comments updated format

2408.12799 2025-02-03 cs.CL cs.AI 81%

Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora

JoonHo Lee, JuYoun Son, Juree Seok, Wooseok Jang, Yeong-Dae Kwon

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

Comments Accepted to NAACL 2025 main conference

2307.09254 2025-01-28 cs.LG cs.CL stat.ML 81%

Selective Generation for Controllable Language Models

Minjae Lee, Kyungmin Kim, Taesoo Kim, Sangdon Park

机构 * GSAI POSTECH（浦项科技大学人工智能研究生院）； SCS & SCP GaTech（佐治亚理工学院计算机科学学院与计算科学与工程学院）； CSE POSTECH（浦项科技大学计算机科学与工程学院）

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

Comments Accepted to NeurIPS 2024 (spotlight)

2406.14162 2025-01-24 cs.IR cs.AI cs.CL 81%

DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation

Jingwei Ni, Tobias Schimanski, Meihong Lin, Mrinmaya Sachan, Elliott Ash, Markus Leippold

机构 * ETH Zurich（苏黎世联邦理工学院）； University of Zurich（苏黎世大学）； Swiss Finance Institute (SFI)（瑞士金融研究所）； University of Electronic Science and Technology of China（电子科技大学）

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

Comments NAACL 2025 Long

2501.06597 2025-01-14 cs.LG cs.CL cs.HC 81%

EmoXpt: Analyzing Emotional Variances in Human Comments and LLM-Generated Responses

Shireesh Reddy Pyreddy, Tarannum Shaila Zaman

机构 * SUNY Polytechnic Institute（纽约州立大学理工学院）； University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）

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

Comments 7 pages, 10 figures, 5 tables. This paper has been accepted and presented at the 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC)

2501.02029 2025-01-07 cs.LG cs.AI cs.CR cs.CV 81%

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models

Ziwei Zheng, Junyao Zhao, Le Yang, Lijun He, Fan Li

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

2307.08941 2025-01-07 cs.LG cs.CL 81%

MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models

Mengting Ai, Tianxin Wei, Yifan Chen, Zeming Guo, Jingrui He

机构 * School of Information Sciences, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校信息科学学院）； Hong Kong Baptist University（香港浸会大学）； Jacobs Technion-Cornell Institute, Cornell Tech（康奈尔理工学院雅各布斯以色列理工学院）

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

Comments v1 accepted to ICML 2023. This work has been submitted to the IEEE for possible publication

2412.19265 2024-12-30 cs.IR cs.CL cs.LG 81%

Optimizing Multi-Stage Language Models for Effective Text Retrieval

Quang Hoang Trung, Le Trung Hoang, Nguyen Van Hoang Phuc

机构 * VJ Technology（VJ科技）

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

2412.15277 2024-12-23 cs.CL cs.AI 81%

PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models

Biao Liu, Wenyi Fang, Xiaoyu Wu, Yang Zheng, Zheng Hu, Bo Yuan

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

2408.09048 2024-12-23 q-bio.QM cs.AI cs.LG 81%

mRNA2vec: mRNA Embedding with Language Model in the 5'UTR-CDS for mRNA Design

Honggen Zhang, Xiangrui Gao, June Zhang, Lipeng Lai

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

2412.06289 2024-12-20 cs.LG cs.AI 81%

S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity

Xinyu Yang, Jixuan Leng, Geyang Guo, Jiawei Zhao, Ryumei Nakada, Linjun Zhang, Huaxiu Yao, Beidi Chen

机构 * CMU（卡内基梅隆大学）； Georgia Tech（佐治亚理工学院）； Caltech（加州理工学院）； Rutgers（罗格斯大学）； UNC-Chapel Hill（北卡罗来纳大学教堂山分校）

专题命中效率与部署：LLM(title)；instruction tuning(abstract)；分类 cs.AI、cs.LG

2412.12226 2024-12-18 cs.LG cs.AI 81%

Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting

Tianyi Yin, Jingwei Wang, Yunlong Ma, Han Wang, Chenze Wang, Yukai Zhao, Min Liu, Weiming Shen, Yufeng Chen

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

2412.10302 2024-12-16 cs.CV cs.AI cs.CL 81%

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Zhiyu Wu, Xiaokang Chen, Zizheng Pan, Xingchao Liu, Wen Liu, Damai Dai, Huazuo Gao, Yiyang Ma, Chengyue Wu, Bingxuan Wang, Zhenda Xie, Yu Wu, Kai Hu, Jiawei Wang, Yaofeng Sun, Yukun Li, Yishi Piao, Kang Guan, Aixin Liu, Xin Xie, Yuxiang You, Kai Dong, Xingkai Yu, Haowei Zhang, Liang Zhao, Yisong Wang, Chong Ruan

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

2406.14124 2024-12-13 cs.AI cs.LG 81%

Measuring Sample Importance in Data Pruning for Language Models based on Information Entropy

Minsang Kim, Seungjun Baek

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

2412.05681 2024-12-10 physics.geo-ph cs.AI cs.LG eess.SP 81%

Leveraging Time-Series Foundation Model for Subsurface Well Logs Prediction and Anomaly Detection

Ardiansyah Koeshidayatullah, Abdulrahman Al-Fakih, SanLinn Ismael Kaka

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

2405.15731 2024-12-10 cs.LG cs.AI cs.SY eess.SY 81%

Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks

Jerome Sieber, Carmen Amo Alonso, Alexandre Didier, Melanie N. Zeilinger, Antonio Orvieto

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

Comments NeurIPS 2024

2412.00722 2024-12-03 cs.CL cs.AI 81%

Towards Adaptive Mechanism Activation in Language Agent

Ziyang Huang, Jun Zhao, Kang Liu

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

Comments COLING2025

Journal ref COLING2025

2410.07404 2024-11-26 cs.AI cs.LG 81%

Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models

Alain Andres, Javier Del Ser

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

Comments Accepted at the Intrinsically Motivated Open-ended Learning workshop at NeurIPS 2024

2312.05356 2024-11-21 cs.SE cs.CL cs.LG 81%

Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation

Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang

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

Comments 13 pages, 7 figures, 7 tables, under peer-review

2411.10543 2024-11-19 cs.LG cs.CL 81%

SoftLMs: Efficient Adaptive Low-Rank Approximation of Language Models using Soft-Thresholding Mechanism

Priyansh Bhatnagar, Linfeng Wen, Mingu Kang

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

2411.06371 2024-11-12 cs.CL cs.LG 81%

LLM Vocabulary Compression for Low-Compute Environments

Sreeram Vennam, Anish Joishy, Ponnurangam Kumaraguru

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

Comments Machine Learning and Compression Workshop @ NeurIPS 2024

2411.02795 2024-11-06 cs.CL cs.AI 81%

The Evolution of RWKV: Advancements in Efficient Language Modeling

Akul Datta

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

1. 效率与部署 22497 篇

Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems

On multi-token prediction for efficient LLM inference

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

Benchmarking Time Series Forecasting Models: From Statistical Techniques to Foundation Models in Real-World Applications

Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

Can You Move These Over There? An LLM-based VR Mover for Supporting Object Manipulation

Wearable Accelerometer Foundation Models for Health via Knowledge Distillation

Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora

Selective Generation for Controllable Language Models

DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation

EmoXpt: Analyzing Emotional Variances in Human Comments and LLM-Generated Responses

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models

MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models

Optimizing Multi-Stage Language Models for Effective Text Retrieval

PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models

mRNA2vec: mRNA Embedding with Language Model in the 5'UTR-CDS for mRNA Design

S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity

Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Measuring Sample Importance in Data Pruning for Language Models based on Information Entropy

Leveraging Time-Series Foundation Model for Subsurface Well Logs Prediction and Anomaly Detection

Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks

Towards Adaptive Mechanism Activation in Language Agent

Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models

Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation

SoftLMs: Efficient Adaptive Low-Rank Approximation of Language Models using Soft-Thresholding Mechanism

LLM Vocabulary Compression for Low-Compute Environments

The Evolution of RWKV: Advancements in Efficient Language Modeling