语言大模型 / LLM - arXivDaily 专题

2310.17936 2023-10-30 cs.CL cs.AI cs.LG 67%

Transformers as Graph-to-Graph Models

James Henderson, Alireza Mohammadshahi, Andrei C. Coman, Lesly Miculicich

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to Big Picture workshop at EMNLP 2023

2310.13669 2023-10-23 cs.LG cs.AI cs.CL cs.PL 67%

Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis

Philip John Gorinski, Matthieu Zimmer, Gerasimos Lampouras, Derrick Goh Xin Deik, Ignacio Iacobacci

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 9 pages + 4 pages appendix; 4 Figures, 4 Tables, 1 Algorithm; Accepted to Findings of EMNLP 2023

2310.05381 2023-10-10 cs.CL cs.AI cs.LG 67%

CCAE: A Corpus of Chinese-based Asian Englishes

Yang Liu, Melissa Xiaohui Qin, Long Wang, Chao Huang

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NLPCC'2023 (12 pages, 3 figures, 4 charts)

2309.12829 2023-10-06 cs.CV cs.AI cs.CL cs.LG 67%

Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiography

Rabin Adhikari, Manish Dhakal, Safal Thapaliya, Kanchan Poudel, Prasiddha Bhandari, Bishesh Khanal

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at the 4th International Workshop of Advances in Simplifying Medical UltraSound (ASMUS)

2307.02570 2023-10-05 cs.CL cs.AI cs.LG cs.SI 67%

Named Entity Inclusion in Abstractive Text Summarization

Sergey Berezin, Tatiana Batura

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments https://aclanthology.org/2022.sdp-1.17/

Journal ref In Proceedings of the Third Workshop on Scholarly Document Processing, 2022

2309.13664 2023-09-26 eess.AS cs.AI cs.CL cs.LG cs.SD 67%

VoiceLDM: Text-to-Speech with Environmental Context

Yeonghyeon Lee, Inmo Yeon, Juhan Nam, Joon Son Chung

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Demos and code are available at https://voiceldm.github.io

2205.14704 2023-09-20 cs.CL cs.AI cs.IR cs.LG 67%

Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning

Xiang Chen, Lei Li, Ningyu Zhang, Xiaozhuan Liang, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NeurIPS 2022 (Spotlight)

2309.09003 2023-09-19 cs.CV 67%

RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework

Yuelei Wang, Ting Zhang, Liangjin Zhao, Lin Hu, Zhechao Wang, Ziqing Niu, Peirui Cheng, Kaiqiang Chen, Xuan Zeng, Zhirui Wang, Hongqi Wang, Xian Sun

专题命中预训练与数据：foundation model(abstract)；pretraining(abstract)

2308.09442 2023-08-22 cs.CE 67%

BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine

Yizhen Luo, Jiahuan Zhang, Siqi Fan, Kai Yang, Yushuai Wu, Mu Qiao, Zaiqing Nie

专题命中预训练与数据：language model(abstract)；foundation model(abstract)

Comments 12 pages, 4 figures

2308.09089 2023-08-21 cs.SD cs.CV cs.IR cs.MM eess.AS 67%

Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries

Julia Wilkins, Justin Salamon, Magdalena Fuentes, Juan Pablo Bello, Oriol Nieto

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments WASPAA 2023. Project page: https://juliawilkins.github.io/sound-effects-retrieval-from-video/. 4 pages, 2 figures, 2 tables

2308.00389 2023-08-02 physics.chem-ph 67%

Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials

Siwoo Lee, Stefan Heinen, Danish Khan, O. Anatole von Lilienfeld

专题命中预训练与数据：large language model(abstract)；language model(abstract)

2211.07730 2023-06-29 cs.LG cs.AI cs.CL 67%

QueryForm: A Simple Zero-shot Form Entity Query Framework

Zifeng Wang, Zizhao Zhang, Jacob Devlin, Chen-Yu Lee, Guolong Su, Hao Zhang, Jennifer Dy, Vincent Perot, Tomas Pfister

专题命中预训练与数据：prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to Findings of ACL 2023

2306.05500 2023-06-12 cs.CL cs.AI cs.CV cs.LG 67%

Word-Level Explanations for Analyzing Bias in Text-to-Image Models

Alexander Lin, Lucas Monteiro Paes, Sree Harsha Tanneru, Suraj Srinivas, Himabindu Lakkaraju

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 5 main pages, 3 pages in appendix, and 3 figures

2306.01443 2023-06-05 cs.CL cs.AI cs.LG 67%

Unsupervised Paraphrasing of Multiword Expressions

Takashi Wada, Yuji Matsumoto, Timothy Baldwin, Jey Han Lau

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 13 pages; accepted for Findings of ACL 2023

2212.10823 2023-06-01 cs.CL cs.AI cs.LG 67%

Continual Contrastive Finetuning Improves Low-Resource Relation Extraction

Wenxuan Zhou, Sheng Zhang, Tristan Naumann, Muhao Chen, Hoifung Poon

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2023

2305.17719 2023-05-30 eess.AS cs.SD 67%

Adapting Language-Audio Models as Few-Shot Audio Learners

Jinhua Liang, Xubo Liu, Haohe Liu, Huy Phan, Emmanouil Benetos, Mark D. Plumbley, Wenwu Wang

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

2305.12498 2023-05-29 eess.AS cs.AI cs.CL cs.LG cs.SD 67%

Multi-Head State Space Model for Speech Recognition

Yassir Fathullah, Chunyang Wu, Yuan Shangguan, Junteng Jia, Wenhan Xiong, Jay Mahadeokar, Chunxi Liu, Yangyang Shi, Ozlem Kalinli, Mike Seltzer, Mark J. F. Gales

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Interspeech 2023

2305.11487 2023-05-24 cs.CV 67%

PointGPT: Auto-regressively Generative Pre-training from Point Clouds

Guangyan Chen, Meiling Wang, Yi Yang, Kai Yu, Li Yuan, Yufeng Yue

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments 9 pages, 2 figures

2305.12311 2023-05-23 cs.CL cs.AI cs.CV cs.LG eess.AS 67%

i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data

Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Mei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

2212.11261 2023-05-17 cs.CY cs.AI cs.CL cs.CV cs.LG 67%

Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias

Robert Wolfe, Yiwei Yang, Bill Howe, Aylin Caliskan

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 12 pages, 4 figures, 2 tables

Journal ref ACM FAccT 2023

2305.08238 2023-05-16 q-bio.QM 67%

Evaluating the roughness of structure-property relationships using pretrained molecular representations

David E. Graff, Edward O. Pyzer-Knapp, Kirk E. Jordan, Eugene I. Shakhnovich, Connor W. Coley

专题命中预训练与数据：foundation model(abstract)；pretraining(abstract)

Comments 18 pages, 13 figures

2305.07477 2023-05-15 cs.IR 67%

Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval

Iain Mackie, Shubham Chatterjee, Jeffrey Dalton

专题命中预训练与数据：large language model(abstract)；language model(abstract)

2305.06557 2023-05-12 cs.CL cs.AI cs.LG 67%

Long-Tailed Question Answering in an Open World

Yi Dai, Hao Lang, Yinhe Zheng, Fei Huang, Yongbin Li

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL2023 Main Track Long Paper

2305.03187 2023-05-08 cs.CV 67%

Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition

Zikang Leng, Hyeokhyen Kwon, Thomas Plötz

专题命中预训练与数据：large language model(abstract)；language model(abstract)

2305.00331 2023-05-02 cs.IR 67%

Synthetic Cross-language Information Retrieval Training Data

James Mayfield, Eugene Yang, Dawn Lawrie, Samuel Barham, Orion Weller, Marc Mason, Suraj Nair, Scott Miller

专题命中预训练与数据：large language model(abstract)；language model(abstract)

Comments 11 pages, 4 figures

2304.14339 2023-04-28 cs.CL cs.AI cs.LG cs.NE 67%

MarsEclipse at SemEval-2023 Task 3: Multi-Lingual and Multi-Label Framing Detection with Contrastive Learning

Qisheng Liao, Meiting Lai, Preslav Nakov

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments framing, contrastive learning, SemEval-2023 task 3

Journal ref SemEval-2023

2304.07258 2023-04-27 cs.CL cs.AI cs.LG 67%

Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games

Benjamin Towle, Ke Zhou

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP Findings 2022

2304.08491 2023-04-18 cs.CV 67%

Delving into Shape-aware Zero-shot Semantic Segmentation

Xinyu Liu, Beiwen Tian, Zhen Wang, Rui Wang, Kehua Sheng, Bo Zhang, Hao Zhao, Guyue Zhou

专题命中预训练与数据：language model(abstract)；pretraining(abstract)

Comments Accepted to CVPR 2023, code: https://github.com/Liuxinyv/SAZS

2304.07183 2023-04-17 cs.AI cs.CL cs.LG 67%

Just Tell Me: Prompt Engineering in Business Process Management

Kiran Busch, Alexander Rochlitzer, Diana Sola, Henrik Leopold

专题命中预训练与数据：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments accepted for BPMDS 2023

2303.16899 2023-03-30 cs.CV 67%

AutoAD: Movie Description in Context

Tengda Han, Max Bain, Arsha Nagrani, Gül Varol, Weidi Xie, Andrew Zisserman

专题命中预训练与数据：foundation model(abstract)；pretraining(abstract)

Comments CVPR2023 Highlight. Project page: https://www.robots.ox.ac.uk/~vgg/research/autoad/

1. 预训练与数据 12486 篇

Transformers as Graph-to-Graph Models

Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis

CCAE: A Corpus of Chinese-based Asian Englishes

Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiography

Named Entity Inclusion in Abstractive Text Summarization

VoiceLDM: Text-to-Speech with Environmental Context

Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning

RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework

BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine

Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries

Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials

QueryForm: A Simple Zero-shot Form Entity Query Framework

Word-Level Explanations for Analyzing Bias in Text-to-Image Models

Unsupervised Paraphrasing of Multiword Expressions

Continual Contrastive Finetuning Improves Low-Resource Relation Extraction

Adapting Language-Audio Models as Few-Shot Audio Learners

Multi-Head State Space Model for Speech Recognition

PointGPT: Auto-regressively Generative Pre-training from Point Clouds

i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data

Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias

Evaluating the roughness of structure-property relationships using pretrained molecular representations

Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval

Long-Tailed Question Answering in an Open World

Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition

Synthetic Cross-language Information Retrieval Training Data

MarsEclipse at SemEval-2023 Task 3: Multi-Lingual and Multi-Label Framing Detection with Contrastive Learning

Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games

Delving into Shape-aware Zero-shot Semantic Segmentation

Just Tell Me: Prompt Engineering in Business Process Management

AutoAD: Movie Description in Context