语言大模型 / LLM - arXivDaily 专题

2501.19377 2025-02-04 cs.SD cs.CL cs.LG eess.AS 86%

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions

Dominik Wagner, Alexander Churchill, Siddharth Sigtia, Erik Marchi

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

Comments Accepted at ICASSP 2025

2501.16744 2025-01-29 cs.LG cs.AI 86%

LLM Assisted Anomaly Detection Service for Site Reliability Engineers: Enhancing Cloud Infrastructure Resilience

Nimesh Jha, Shuxin Lin, Srideepika Jayaraman, Kyle Frohling, Christodoulos Constantinides, Dhaval Patel

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

Comments Accepted at the AAAI-2025 Deployable AI Workshop

2409.20550 2025-01-20 cs.SE cs.AI cs.CL 86%

LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation

Ziyao Zhang, Yanlin Wang, Chong Wang, Jiachi Chen, Zibin Zheng

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

Comments Accepted by ISSTA 2025

2501.08631 2025-01-16 cs.LG cs.CL 86%

SWSC: Shared Weight for Similar Channel in LLM

Binrui Zeng, Yongtao Tang, Xiaodong Liu, Xiaopeng Li

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

Comments 5pages, 3 figures, work in progress

2412.19616 2025-01-07 cs.LG cs.AI 86%

Gradient Weight-normalized Low-rank Projection for Efficient LLM Training

Jia-Hong Huang, Yixian Shen, Hongyi Zhu, Stevan Rudinac, Evangelos Kanoulas

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

Comments Accepted by the 39th AAAI Conference on Artificial Intelligence (AAAI-25) [Main Technical Track]

2412.18819 2024-12-31 cs.AI cs.IR cs.LG 86%

LLM-assisted Vector Similarity Search

Md Riyadh, Muqi Li, Felix Haryanto Lie, Jia Long Loh, Haotian Mi, Sayam Bohra

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

2406.15504 2024-12-31 cs.CL cs.LG 86%

Multi-View Empowered Structural Graph Wordification for Language Models

Zipeng Liu, Likang Wu, Ming He, Zhong Guan, Hongke Zhao, Nan Feng

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

2412.18106 2024-12-30 cs.AI cs.DC cs.LG 86%

Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels

Mingcong Song, Xinru Tang, Fengfan Hou, Jing Li, Wei Wei, Yipeng Ma, Runqiu Xiao, Hongjie Si, Dingcheng Jiang, Shouyi Yin, Yang Hu, Guoping Long

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

2412.17321 2024-12-24 cs.CL cs.AI 86%

Assessing Human Editing Effort on LLM-Generated Texts via Compression-Based Edit Distance

Nicolas Devatine, Louis Abraham

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

2410.16179 2024-12-19 cs.CL cs.LG 86%

MagicPIG: LSH Sampling for Efficient LLM Generation

Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, Yang Zhou, Jianyu Zhang, Niklas Nolte, Yuandong Tian, Matthijs Douze, Leon Bottou, Zhihao Jia, Beidi Chen

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

2405.20612 2024-12-13 cs.CL cs.AI 86%

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation

Hanzhang Zhou, Zijian Feng, Zixiao Zhu, Junlang Qian, Kezhi Mao

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

Comments Accepted to NeurIPS 2024

2407.15504 2024-12-12 cs.LG cs.CL cs.IT math.IT 86%

Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models

Alliot Nagle, Adway Girish, Marco Bondaschi, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim

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

Comments 42 pages, 17 figures. Accepted to NeurIPS 2024

2412.07017 2024-12-11 cs.CL cs.AI 86%

Asynchronous LLM Function Calling

In Gim, Seung-seob Lee, Lin Zhong

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

2411.00774 2024-12-10 cs.SD cs.AI cs.CL eess.AS 86%

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Xiong Wang, Yangze Li, Chaoyou Fu, Yunhang Shen, Lei Xie, Ke Li, Xing Sun, Long Ma

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

Comments Project Page: https://freeze-omni.github.io/

2406.05250 2024-12-09 cs.AI cs.AR cs.LG 86%

LLM-Enhanced Bayesian Optimization for Efficient Analog Layout Constraint Generation

Guojin Chen, Keren Zhu, Seunggeun Kim, Hanqing Zhu, Yao Lai, Bei Yu, David Z. Pan

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

2412.04757 2024-12-09 cs.CL cs.LG 86%

Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern

Hongyin Tang, Di Xiu, Lanrui Wang, Xiurui Geng, Jingang Wang, Xunliang Cai

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

2408.17175 2024-11-28 eess.AS cs.AI cs.CL cs.SD 86%

Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

Zhen Ye, Peiwen Sun, Jiahe Lei, Hongzhan Lin, Xu Tan, Zheqi Dai, Qiuqiang Kong, Jianyi Chen, Jiahao Pan, Qifeng Liu, Yike Guo, Wei Xue

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

2411.16158 2024-11-26 cs.LG cs.AI cs.AR 86%

MixPE: Quantization and Hardware Co-design for Efficient LLM Inference

Yu Zhang, Mingzi Wang, Lancheng Zou, Wulong Liu, Hui-Ling Zhen, Mingxuan Yuan, Bei Yu

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

2411.16003 2024-11-26 cs.LG cs.AI 86%

eFedLLM: Efficient LLM Inference Based on Federated Learning

Shengwen Ding, Chenhui Hu

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

2411.15997 2024-11-26 cs.LG cs.AI cs.DC cs.MA 86%

Ensuring Fair LLM Serving Amid Diverse Applications

Redwan Ibne Seraj Khan, Kunal Jain, Haiying Shen, Ankur Mallick, Anjaly Parayil, Anoop Kulkarni, Steve Kofsky, Pankhuri Choudhary, Renèe St. Amant, Rujia Wang, Yue Cheng, Ali R. Butt, Victor Rühle, Chetan Bansal, Saravan Rajmohan

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

2404.08509 2024-11-26 cs.DC cs.CL cs.LG 86%

Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction

Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Saurabh Jha, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer

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

Comments Accepted at AIOps'24

2411.12764 2024-11-21 cs.CL cs.AI cs.IR 86%

SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text

Weiqing He, Bojian Hou, Tianqi Shang, Davoud Ataee Tarzanagh, Qi Long, Li Shen

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

2411.07942 2024-11-13 cs.AI cs.LG 86%

Towards Low-bit Communication for Tensor Parallel LLM Inference

Harry Dong, Tyler Johnson, Minsik Cho, Emad Soroush

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

2411.06437 2024-11-12 eess.AS cs.AI cs.CL 86%

CTC-Assisted LLM-Based Contextual ASR

Guanrou Yang, Ziyang Ma, Zhifu Gao, Shiliang Zhang, Xie Chen

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

Comments SLT 2024

2405.18137 2024-11-05 cs.LG cs.AI cs.CR 86%

Exploiting LLM Quantization

Kazuki Egashira, Mark Vero, Robin Staab, Jingxuan He, Martin Vechev

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

2404.10618 2024-11-05 cs.AI cs.CV cs.LG 86%

Private Attribute Inference from Images with Vision-Language Models

Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev

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

2410.23079 2024-10-31 cs.CL cs.AI 86%

BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference

Junqi Zhao, Zhijin Fang, Shu Li, Shaohui Yang, Shichao He

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

2406.10847 2024-10-29 cs.AI cs.CE cs.CL cs.MA 86%

TorchOpera: A Compound AI System for LLM Safety

Shanshan Han, Zijian Hu, Alay Dilipbhai Shah, Han Jin, Yuhang Yao, Dimitris Stripelis, Zhaozhuo Xu, Chaoyang He

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

2410.19206 2024-10-28 cs.LG cs.CL 86%

Inference time LLM alignment in single and multidomain preference spectrum

Sadat Shahriar, Zheng Qi, Nikolaos Pappas, Srikanth Doss, Monica Sunkara, Kishaloy Halder, Manuel Mager, Yassine Benajiba

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

2410.18861 2024-10-25 cs.CR cs.AI cs.CL 86%

Provably Robust Watermarks for Open-Source Language Models

Miranda Christ, Sam Gunn, Tal Malkin, Mariana Raykova

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

1. 效率与部署 22280 篇

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions

LLM Assisted Anomaly Detection Service for Site Reliability Engineers: Enhancing Cloud Infrastructure Resilience

LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation

SWSC: Shared Weight for Similar Channel in LLM

Gradient Weight-normalized Low-rank Projection for Efficient LLM Training

LLM-assisted Vector Similarity Search

Multi-View Empowered Structural Graph Wordification for Language Models

Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels

Assessing Human Editing Effort on LLM-Generated Texts via Compression-Based Edit Distance

MagicPIG: LSH Sampling for Efficient LLM Generation

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation

Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models

Asynchronous LLM Function Calling

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

LLM-Enhanced Bayesian Optimization for Efficient Analog Layout Constraint Generation

Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern

Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

MixPE: Quantization and Hardware Co-design for Efficient LLM Inference

eFedLLM: Efficient LLM Inference Based on Federated Learning

Ensuring Fair LLM Serving Amid Diverse Applications

Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction

SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text

Towards Low-bit Communication for Tensor Parallel LLM Inference

CTC-Assisted LLM-Based Contextual ASR

Exploiting LLM Quantization

Private Attribute Inference from Images with Vision-Language Models

BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference

TorchOpera: A Compound AI System for LLM Safety

Inference time LLM alignment in single and multidomain preference spectrum

Provably Robust Watermarks for Open-Source Language Models