语言大模型 / LLM - arXivDaily 专题

2412.16215 2024-12-24 cs.CV cs.AI cs.IR 83%

Zero-Shot Image Moderation in Google Ads with LLM-Assisted Textual Descriptions and Cross-modal Co-embeddings

Enming Luo, Wei Qiao, Katie Warren, Jingxiang Li, Eric Xiao, Krishna Viswanathan, Yuan Wang, Yintao Liu, Jimin Li, Ariel Fuxman

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

2412.15303 2024-12-23 cs.CL 83%

Self-Evolution Knowledge Distillation for LLM-based Machine Translation

Yuncheng Song, Liang Ding, Changtong Zan, Shujian Huang

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

Comments COLING 2025

2409.09739 2024-12-18 cs.CR cs.CL 83%

PersonaMark: Personalized LLM watermarking for model protection and user attribution

Yuehan Zhang, Peizhuo Lv, Yinpeng Liu, Yongqiang Ma, Wei Lu, Xiaofeng Wang, Xiaozhong Liu, Jiawei Liu

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

Comments Under review

2409.14785 2024-12-10 cs.CL cs.CV 83%

Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models

Patrick Amadeus Irawan, Genta Indra Winata, Samuel Cahyawijaya, Ayu Purwarianti

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

Comments Preprint

2412.04180 2024-12-10 cs.LG 83%

SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization

Runsheng Bai, Bo Liu, Qiang Liu

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

2412.04718 2024-12-09 cs.AI 83%

Adaptive Optimization for Enhanced Efficiency in Large-Scale Language Model Training

Jiajing Chen, Bingying Liu, Xiaoxuan Liao, Jia Gao, Hongye Zheng, Yue Li

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

2401.00211 2024-12-06 cs.AI 83%

Open-TI: Open Traffic Intelligence with Augmented Language Model

Longchao Da, Kuanru Liou, Tiejin Chen, Xuesong Zhou, Xiangyong Luo, Yezhou Yang, Hua Wei

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

Comments Published on International Journal of Machine Learning and Cybernetics, Preview version: https://rdcu.be/dHu0b, Github: https://github.com/DaRL-LibSignal/OpenTI

2412.02594 2024-12-04 cs.AR cs.AI 83%

PrefixLLM: LLM-aided Prefix Circuit Design

Weihua Xiao, Venkata Sai Charan Putrevu, Raghu Vamshi Hemadri, Siddharth Garg, Ramesh Karri

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

2411.16020 2024-11-26 cs.CL 83%

TransCompressor: LLM-Powered Multimodal Data Compression for Smart Transportation

Huanqi Yang, Rucheng Wu, Weitao Xu

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

Comments 6 pages

2410.15526 2024-11-26 cs.LG cs.DC 83%

SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training

Jinda Jia, Cong Xie, Hanlin Lu, Daoce Wang, Hao Feng, Chengming Zhang, Baixi Sun, Haibin Lin, Zhi Zhang, Xin Liu, Dingwen Tao

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

Comments Accepted by NeurIPS 2024

2411.13159 2024-11-21 cs.CL cs.SD eess.AS 83%

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM

Jiawei Yu, Yuang Li, Xiaosong Qiao, Huan Zhao, Xiaofeng Zhao, Wei Tang, Min Zhang, Hao Yang, Jinsong Su

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

2411.13004 2024-11-21 cs.LG cs.CR 83%

MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification

Yuxuan Chen, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

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

2411.09590 2024-11-15 cs.SE cs.AI 83%

Adopting RAG for LLM-Aided Future Vehicle Design

Vahid Zolfaghari, Nenad Petrovic, Fengjunjie Pan, Krzysztof Lebioda, Alois Knoll

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

Comments Conference paper accepted in IEEE FLLM 2024

2405.19101 2024-11-06 cs.LG 83%

Poseidon: Efficient Foundation Models for PDEs

Maximilian Herde, Bogdan Raonić, Tobias Rohner, Roger Käppeli, Roberto Molinaro, Emmanuel de Bézenac, Siddhartha Mishra

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

2402.17946 2024-11-04 cs.CL 83%

SparseLLM: Towards Global Pruning for Pre-trained Language Models

Guangji Bai, Yijiang Li, Chen Ling, Kibaek Kim, Liang Zhao

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

Comments NeurIPS 2024

2410.20418 2024-10-29 cs.CR cs.AI 83%

Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models

Zhengmian Hu, Heng Huang

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

2410.18641 2024-10-25 cs.IR cs.AI 83%

Smart ETL and LLM-based contents classification: the European Smart Tourism Tools Observatory experience

Diogo Cosme, António Galvão, Fernando Brito e Abreu

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

2410.17950 2024-10-24 cs.AI 83%

Benchmarking Floworks against OpenAI & Anthropic: A Novel Framework for Enhanced LLM Function Calling

Nirav Bhan, Shival Gupta, Sai Manaswini, Ritik Baba, Narun Yadav, Hillori Desai, Yash Choudhary, Aman Pawar, Sarthak Shrivastava, Sudipta Biswas

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

Comments 15 pages for main paper, 21 pages in total including references and appendix, 10 figures

2410.17529 2024-10-24 cs.CL 83%

Navigate Complex Physical Worlds via Geometrically Constrained LLM

Yongqiang Huang, Wentao Ye, Liyao Li, Junbo Zhao

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

2410.14042 2024-10-21 cs.CL 83%

Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles

Xiao Pu, Tianxing He, Xiaojun Wan

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

Comments EMNLP 2024 Findings

2408.05541 2024-10-21 cs.CL 83%

P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training

Yingxuan Yang, Huayi Wang, Muning Wen, Xiaoyun Mo, Qiuying Peng, Jun Wang, Weinan Zhang

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

2410.13782 2024-10-18 cs.LG q-bio.QM 83%

DPLM-2: A Multimodal Diffusion Protein Language Model

Xinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue, Shujian Huang, Quanquan Gu

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

2410.12104 2024-10-17 cs.CY cs.LG cs.SE 83%

To Err is AI : A Case Study Informing LLM Flaw Reporting Practices

Sean McGregor, Allyson Ettinger, Nick Judd, Paul Albee, Liwei Jiang, Kavel Rao, Will Smith, Shayne Longpre, Avijit Ghosh, Christopher Fiorelli, Michelle Hoang, Sven Cattell, Nouha Dziri

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

Comments 8 pages, 5 figures

2410.11371 2024-10-16 cs.CL cs.DB 83%

Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL

Qihuang Zhong, Kunfeng Chen, Liang Ding, Juhua Liu, Bo Du, Dacheng Tao

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

Comments Accepted to EMNLP2024 Findings

2406.10701 2024-10-15 cs.CL 83%

MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding

Baixuan Xu, Weiqi Wang, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Long Chen, Yangqiu Song

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

Comments EMNLP 2024 main conference

2409.17634 2024-09-27 cs.CV cs.AI 83%

P4Q: Learning to Prompt for Quantization in Visual-language Models

Huixin Sun, Runqi Wang, Yanjing Li, Xianbin Cao, Xiaolong Jiang, Yao Hu, Baochang Zhang

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

2409.14513 2024-09-25 cs.LG cs.CR stat.ML 83%

Order of Magnitude Speedups for LLM Membership Inference

Rongting Zhang, Martin Bertran, Aaron Roth

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

2409.14517 2024-09-24 cs.IR cs.LG 83%

Sliding Window Training -- Utilizing Historical Recommender Systems Data for Foundation Models

Swanand Joshi, Yesu Feng, Ko-Jen Hsiao, Zhe Zhang, Sudarshan Lamkhede

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

Comments To be published In 18th ACM Conference on Recommender Systems (RecSys '24), October 14--18, 2024, Bari, Italy

2407.11435 2024-09-24 q-bio.GN cs.LG stat.ML 83%

Genomic Language Models: Opportunities and Challenges

Gonzalo Benegas, Chengzhong Ye, Carlos Albors, Jianan Canal Li, Yun S. Song

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

Comments Review article; 26 pages, 3 figures, 1 table

2409.11416 2024-09-19 cs.AR cs.AI cs.PF cs.SY eess.SY 83%

The Unseen AI Disruptions for Power Grids: LLM-Induced Transients

Yuzhuo Li, Mariam Mughees, Yize Chen, Yunwei Ryan Li

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

Comments 21 pages, 18 figures

1. 效率与部署 22456 篇

Zero-Shot Image Moderation in Google Ads with LLM-Assisted Textual Descriptions and Cross-modal Co-embeddings

Self-Evolution Knowledge Distillation for LLM-based Machine Translation

PersonaMark: Personalized LLM watermarking for model protection and user attribution

Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models

SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization

Adaptive Optimization for Enhanced Efficiency in Large-Scale Language Model Training

Open-TI: Open Traffic Intelligence with Augmented Language Model

PrefixLLM: LLM-aided Prefix Circuit Design

TransCompressor: LLM-Powered Multimodal Data Compression for Smart Transportation

SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM

MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification

Adopting RAG for LLM-Aided Future Vehicle Design

Poseidon: Efficient Foundation Models for PDEs

SparseLLM: Towards Global Pruning for Pre-trained Language Models

Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models

Smart ETL and LLM-based contents classification: the European Smart Tourism Tools Observatory experience

Benchmarking Floworks against OpenAI & Anthropic: A Novel Framework for Enhanced LLM Function Calling

Navigate Complex Physical Worlds via Geometrically Constrained LLM

Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles

P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training

DPLM-2: A Multimodal Diffusion Protein Language Model

To Err is AI : A Case Study Informing LLM Flaw Reporting Practices

Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL

MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding

P4Q: Learning to Prompt for Quantization in Visual-language Models

Order of Magnitude Speedups for LLM Membership Inference

Sliding Window Training -- Utilizing Historical Recommender Systems Data for Foundation Models

Genomic Language Models: Opportunities and Challenges

The Unseen AI Disruptions for Power Grids: LLM-Induced Transients