语言大模型 / LLM - arXivDaily 专题

2404.07839 2024-08-29 cs.LG cs.AI cs.CL 82%

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Aleksandar Botev, Soham De, Samuel L Smith, Anushan Fernando, George-Cristian Muraru, Ruba Haroun, Leonard Berrada, Razvan Pascanu, Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Sertan Girgin, Olivier Bachem, Alek Andreev, Kathleen Kenealy, Thomas Mesnard, Cassidy Hardin, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, Pouya Tafti, Armand Joulin, Noah Fiedel, Evan Senter, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, David Budden, Arnaud Doucet, Sharad Vikram, Adam Paszke, Trevor Gale, Sebastian Borgeaud, Charlie Chen, Andy Brock, Antonia Paterson, Jenny Brennan, Meg Risdal, Raj Gundluru, Nesh Devanathan, Paul Mooney, Nilay Chauhan, Phil Culliton, Luiz Gustavo Martins, Elisa Bandy, David Huntsperger, Glenn Cameron, Arthur Zucker, Tris Warkentin, Ludovic Peran, Minh Giang, Zoubin Ghahramani, Clément Farabet, Koray Kavukcuoglu, Demis Hassabis, Raia Hadsell, Yee Whye Teh, Nando de Frietas

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

2407.20920 2024-07-31 cs.CV 82%

SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition

Hao Tan, Zichang Tan, Jun Li, Jun Wan, Zhen Lei, Stan Z. Li

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

Comments 13 pages, 8 figures

2407.16526 2024-07-24 cs.CV cs.AI cs.CL cs.LG 82%

Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models

Aristeidis Panos, Rahaf Aljundi, Daniel Olmeda Reino, Richard E Turner

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

2407.14177 2024-07-22 cs.CV 82%

EVLM: An Efficient Vision-Language Model for Visual Understanding

Kaibing Chen, Dong Shen, Hanwen Zhong, Huasong Zhong, Kui Xia, Di Xu, Wei Yuan, Yifei Hu, Bin Wen, Tianke Zhang, Changyi Liu, Dewen Fan, Huihui Xiao, Jiahong Wu, Fan Yang, Size Li, Di Zhang

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

2401.07886 2024-07-16 cs.LG cs.AI cs.CL cs.DC 82%

Learned Best-Effort LLM Serving

Siddharth Jha, Coleman Hooper, Xiaoxuan Liu, Sehoon Kim, Kurt Keutzer

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

Comments Es-FoMo @ ICML 2024

2403.00579 2024-06-21 cs.AR 82%

NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing

Guseul Heo, Sangyeop Lee, Jaehong Cho, Hyunmin Choi, Sanghyeon Lee, Hyungkyu Ham, Gwangsun Kim, Divya Mahajan, Jongse Park

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

Comments 16 pages, 15 figures

Journal ref ASPLOS 2024

2403.02419 2024-06-06 cs.LG cs.AI cs.CL cs.SY eess.SY 82%

Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems

Lingjiao Chen, Jared Quincy Davis, Boris Hanin, Peter Bailis, Ion Stoica, Matei Zaharia, James Zou

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

2405.21013 2024-06-05 cs.CV 82%

StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond

Pengyuan Lyu, Yulin Li, Hao Zhou, Weihong Ma, Xingyu Wan, Qunyi Xie, Liang Wu, Chengquan Zhang, Kun Yao, Errui Ding, Jingdong Wang

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

2402.04396 2024-06-05 cs.LG cs.AI cs.CL 82%

QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks

Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, Christopher De Sa

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

Comments ICML 2024

2310.17022 2024-06-05 cs.LG cs.AI cs.CL 82%

Controlled Decoding from Language Models

Sidharth Mudgal, Jong Lee, Harish Ganapathy, YaGuang Li, Tao Wang, Yanping Huang, Zhifeng Chen, Heng-Tze Cheng, Michael Collins, Trevor Strohman, Jilin Chen, Alex Beutel, Ahmad Beirami

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

Comments ICML 2024

2406.01432 2024-06-04 cs.CV 82%

ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models

Thanh-Dat Truong, Xin Li, Bhiksha Raj, Jackson Cothren, Khoa Luu

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

2405.16854 2024-05-28 cs.MA 82%

Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning

Zhihao Liu, Xianliang Yang, Zichuan Liu, Yifan Xia, Wei Jiang, Yuanyu Zhang, Lijuan Li, Guoliang Fan, Lei Song, Bian Jiang

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

2405.14161 2024-05-24 cs.CL cs.AI cs.LG cs.SD eess.AS 82%

Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models

Yuchen Hu, Chen Chen, Chao-Han Huck Yang, Chengwei Qin, Pin-Yu Chen, Eng Siong Chng, Chao Zhang

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

Comments 23 pages, Preprint

2405.01582 2024-05-14 cs.CL cs.AI cs.LG 82%

Text Quality-Based Pruning for Efficient Training of Language Models

Vasu Sharma, Karthik Padthe, Newsha Ardalani, Kushal Tirumala, Russell Howes, Hu Xu, Po-Yao Huang, Shang-Wen Li, Armen Aghajanyan, Gargi Ghosh, Luke Zettlemoyer

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

2404.08886 2024-04-16 cs.CV cs.AI cs.CL cs.IR cs.LG 82%

EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM

Henry Peng Zou, Gavin Heqing Yu, Ziwei Fan, Dan Bu, Han Liu, Peng Dai, Dongmei Jia, Cornelia Caragea

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

Comments Accepted by NAACL 2024 Industry Track

2404.05567 2024-04-09 cs.LG cs.AI cs.CL 82%

Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models

Bowen Pan, Yikang Shen, Haokun Liu, Mayank Mishra, Gaoyuan Zhang, Aude Oliva, Colin Raffel, Rameswar Panda

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

2404.01716 2024-04-03 eess.AS cs.AI cs.CL cs.LG 82%

Effective internal language model training and fusion for factorized transducer model

Jinxi Guo, Niko Moritz, Yingyi Ma, Frank Seide, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer

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

Comments Accepted to ICASSP 2024

2308.11696 2024-04-02 cs.CL cs.AI cs.CV cs.LG 82%

Efficient Benchmarking of Language Models

Yotam Perlitz, Elron Bandel, Ariel Gera, Ofir Arviv, Liat Ein-Dor, Eyal Shnarch, Noam Slonim, Michal Shmueli-Scheuer, Leshem Choshen

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

Comments Accepted to NAACL main track

2404.00207 2024-04-02 cs.CL cs.AI cs.LG 82%

Causal Inference for Human-Language Model Collaboration

Bohan Zhang, Yixin Wang, Paramveer S. Dhillon

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

Comments 9 pages (Accepted for publication at NAACL 2024 (Main Conference))

2403.19710 2024-04-01 cs.CL cs.AI cs.IR cs.LG 82%

STRUM-LLM: Attributed and Structured Contrastive Summarization

Beliz Gunel, James B. Wendt, Jing Xie, Yichao Zhou, Nguyen Vo, Zachary Fisher, Sandeep Tata

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

2403.16993 2024-03-26 cs.CV 82%

Comp4D: LLM-Guided Compositional 4D Scene Generation

Dejia Xu, Hanwen Liang, Neel P. Bhatt, Hezhen Hu, Hanxue Liang, Konstantinos N. Plataniotis, Zhangyang Wang

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

Comments Project page: https://vita-group.github.io/Comp4D/

2205.11100 2024-03-26 cs.CV 82%

Supporting Vision-Language Model Inference with Confounder-pruning Knowledge Prompt

Jiangmeng Li, Wenyi Mo, Wenwen Qiang, Bing Su, Changwen Zheng, Hui Xiong, Ji-Rong Wen

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

2403.14551 2024-03-22 cs.CL cs.AI cs.LG 82%

Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling

Chengxu Zhuang, Evelina Fedorenko, Jacob Andreas

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

2403.07191 2024-03-13 cs.LG cs.AI cs.CL 82%

$\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model

Yufeng Zhang, Liyu Chen, Boyi Liu, Yingxiang Yang, Qiwen Cui, Yunzhe Tao, Hongxia Yang

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

Comments 8 pages

2403.03187 2024-03-06 cs.CL cs.AI cs.LG 82%

Reliable, Adaptable, and Attributable Language Models with Retrieval

Akari Asai, Zexuan Zhong, Danqi Chen, Pang Wei Koh, Luke Zettlemoyer, Hannaneh Hajishirzi, Wen-tau Yih

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

2402.15181 2024-02-26 q-bio.QM q-bio.BM 82%

Substrate Prediction for RiPP Biosynthetic Enzymes via Masked Language Modeling and Transfer Learning

Joseph D. Clark, Xuenan Mi, Douglas A. Mitchell, Diwakar Shukla

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

2402.11131 2024-02-20 cs.CL cs.AI cs.LG 82%

Speculative Streaming: Fast LLM Inference without Auxiliary Models

Nikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Mohammad Rastegari, Mahyar Najibi

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

2402.10099 2024-02-16 cs.CV 82%

Any-Shift Prompting for Generalization over Distributions

Zehao Xiao, Jiayi Shen, Mohammad Mahdi Derakhshani, Shengcai Liao, Cees G. M. Snoek

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

2402.09977 2024-02-16 cs.CL cs.AI cs.LG 82%

Fast Vocabulary Transfer for Language Model Compression

Leonidas Gee, Andrea Zugarini, Leonardo Rigutini, Paolo Torroni

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

Comments The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)

Journal ref Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022): Industry Track

2402.01742 2024-02-06 cs.CL cs.AI cs.LG 82%

Towards Optimizing the Costs of LLM Usage

Shivanshu Shekhar, Tanishq Dubey, Koyel Mukherjee, Apoorv Saxena, Atharv Tyagi, Nishanth Kotla

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

Comments 8 pages + Appendix, Total 12 pages

1. 效率与部署 22497 篇

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition

Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models

EVLM: An Efficient Vision-Language Model for Visual Understanding

Learned Best-Effort LLM Serving

NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing

Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems

StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond

QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks

Controlled Decoding from Language Models

ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models

Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning

Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models

Text Quality-Based Pruning for Efficient Training of Language Models

EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM

Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models

Effective internal language model training and fusion for factorized transducer model

Efficient Benchmarking of Language Models

Causal Inference for Human-Language Model Collaboration

STRUM-LLM: Attributed and Structured Contrastive Summarization

Comp4D: LLM-Guided Compositional 4D Scene Generation

Supporting Vision-Language Model Inference with Confounder-pruning Knowledge Prompt

Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling

$\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model

Reliable, Adaptable, and Attributable Language Models with Retrieval

Substrate Prediction for RiPP Biosynthetic Enzymes via Masked Language Modeling and Transfer Learning

Speculative Streaming: Fast LLM Inference without Auxiliary Models

Any-Shift Prompting for Generalization over Distributions

Fast Vocabulary Transfer for Language Model Compression

Towards Optimizing the Costs of LLM Usage