语言大模型 / LLM - arXivDaily 专题

2302.14338 2023-03-28 cs.CV 67%

Turning a CLIP Model into a Scene Text Detector

Wenwen Yu, Yuliang Liu, Wei Hua, Deqiang Jiang, Bo Ren, Xiang Bai

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

Comments CVPR2023

2211.14905 2023-03-28 cs.CV cs.AI cs.CL cs.LG cs.MM 67%

Multi-Modal Few-Shot Temporal Action Detection

Sauradip Nag, Mengmeng Xu, Xiatian Zhu, Juan-Manuel Perez-Rua, Bernard Ghanem, Yi-Zhe Song, Tao Xiang

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

Comments Technical Report

2303.13549 2023-03-27 cs.CV cs.AI cs.CL cs.LG eess.IV 67%

Optical Character Recognition and Transcription of Berber Signs from Images in a Low-Resource Language Amazigh

Levi Corallo, Aparna S. Varde

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

Journal ref AAAI-2023 the 37th AAAI Conference on Artificial Intelligence (AI4EDU workshop)

2211.09371 2023-03-21 cs.CV cs.MM 67%

CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge

Linli Yao, Weijing Chen, Qin Jin

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

Comments Accepted to WWW2023

2210.11006 2023-03-14 cs.CV 67%

SimpleClick: Interactive Image Segmentation with Simple Vision Transformers

Qin Liu, Zhenlin Xu, Gedas Bertasius, Marc Niethammer

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

Comments Tech report. Update 03/11/2023: Add results on a tiny model and append supplementary materials

2303.05431 2023-03-10 cs.CL cs.AI cs.LG 67%

disco: a toolkit for Distributional Control of Generative Models

Germán Kruszewski, Jos Rozen, Marc Dymetman

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

2302.11269 2023-02-23 cs.LG cs.AI cs.CL stat.ML 67%

Learning from Multiple Sources for Data-to-Text and Text-to-Data

Song Duong, Alberto Lumbreras, Mike Gartrell, Patrick Gallinari

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

Comments AISTATS 2023

2302.03540 2023-02-08 cs.SD eess.AS 67%

Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision

Eugene Kharitonov, Damien Vincent, Zalán Borsos, Raphaël Marinier, Sertan Girgin, Olivier Pietquin, Matt Sharifi, Marco Tagliasacchi, Neil Zeghidour

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

2301.12644 2023-01-31 cs.CV 67%

Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval

Yizhen Chen, Jie Wang, Lijian Lin, Zhongang Qi, Jin Ma, Ying Shan

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

Comments Accepted to AAAI 2023 (Oral)

1506.06646 2023-01-18 cs.AI cs.CL cs.LG stat.ML 67%

Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition from Continuous Speech Signals

Tadahiro Taniguchi, Ryo Nakashima, Shogo Nagasaka

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

Comments 15 pages, 7 figures, Draft submitted to IEEE Transactions on Autonomous Mental Development (TAMD)

Journal ref IEEE Transactions on Cognitive and Developmental Systems, vol. 8, no. 3, pp. 171-185, 2016

2301.01949 2023-01-06 cs.CL cs.AI cs.CV cs.LG cs.MM 67%

SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph

Yuxing Long, Binyuan Hui, Fulong Ye, Yanyang Li, Zhuoxin Han, Caixia Yuan, Yongbin Li, Xiaojie Wang

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

Comments AAAI 2023

2301.00395 2023-01-03 cs.CL cs.AI cs.CY cs.LG 67%

CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation

Ge Zhang, Yizhi Li, Yaoyao Wu, Linyuan Zhang, Chenghua Lin, Jiayi Geng, Shi Wang, Jie Fu

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

2212.08167 2022-12-19 cs.CL cs.AI cs.IR cs.LG 67%

Evaluation of Synthetic Datasets for Conversational Recommender Systems

Harsh Lara, Manoj Tiwari

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

2212.01757 2022-12-06 cs.CL cs.AI cs.LG 67%

Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer

Benjamin Muller, Deepanshu Gupta, Siddharth Patwardhan, Jean-Philippe Fauconnier, David Vandyke, Sachin Agarwal

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

Comments In NeurIPS Workshop on Transfer Learning for Natural Language Processing, 2022, New Orleans. 15 pages, 8 figures, 5 tables

2211.13972 2022-11-28 cs.LG cs.AI cs.CL cs.CV cs.CY 67%

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

Rishi Bommasani, Kathleen A. Creel, Ananya Kumar, Dan Jurafsky, Percy Liang

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

Comments Published at NeurIPS 2022, presented at EAAMO 2022

2207.05359 2022-11-15 cs.CV 67%

CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm

Mingye Xu, Yali Wang, Yihao Liu, Tong He, Yu Qiao

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

2211.02816 2022-11-08 cs.CL cs.AI cs.LG 67%

PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training

Zihui Gu, Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du

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

Comments EMNLP 2022

2211.02709 2022-11-08 cs.SE 67%

A Prompt-based Few-shot Learning Approach to Software Conflict Detection

Robert K. Helmeczi, Mucahit Cevik, Savas Yıldırım

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

Comments 9 pages; 4 figures. To be published In Proceedings of 32nd Annual International Conference on Computer Science and Software Engineering (CASCON '22)

2201.03533 2022-10-13 cs.CL cs.AI cs.LG stat.ML 67%

SCROLLS: Standardized CompaRison Over Long Language Sequences

Uri Shaham, Elad Segal, Maor Ivgi, Avia Efrat, Ori Yoran, Adi Haviv, Ankit Gupta, Wenhan Xiong, Mor Geva, Jonathan Berant, Omer Levy

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

Comments EMNLP 2022

2203.17247 2022-08-24 cs.CV cs.AI cs.CL cs.LG 67%

VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers

Estelle Aflalo, Meng Du, Shao-Yen Tseng, Yongfei Liu, Chenfei Wu, Nan Duan, Vasudev Lal

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

Comments Best Demo Award at CVPR 2022

2208.02816 2022-08-05 cs.CV 67%

Expanding Language-Image Pretrained Models for General Video Recognition

Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, Haibin Ling

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

Comments Accepted by ECCV2022, Oral

2207.01084 2022-07-05 cs.SE 67%

Enhancing Automated Software Traceability by Transfer Learning from Open-World Data

Jinfeng Lin, Amrit Poudel, Wenhao Yu, Qingkai Zeng, Meng Jiang, Jane Cleland-Huang

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

2206.07190 2022-06-16 cs.CL cs.AI cs.LG 67%

Codec at SemEval-2022 Task 5: Multi-Modal Multi-Transformer Misogynous Meme Classification Framework

Ahmed Mahran, Carlo Alessandro Borella, Konstantinos Perifanos

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

Comments Accepted for publication at the 16th International Workshop on Semantic Evaluation, Task 5: MAMI - Multimedia Automatic Misogyny Identification co-located with NAACL 2022

2201.10963 2022-05-31 cs.CV cs.MM 67%

Learning to Compose Diversified Prompts for Image Emotion Classification

Sinuo Deng, Lifang Wu, Ge Shi, Lehao Xing, Meng Jian, Ye Xiang

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

Comments 10 pages, 5 figures

2205.11378 2022-05-24 cs.CV cs.AI cs.CL cs.CY cs.LG 67%

Markedness in Visual Semantic AI

Robert Wolfe, Aylin Caliskan

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

Comments To be published at ACM FAccT 2022

2205.01818 2022-05-06 cs.LG cs.AI cs.CL cs.CV eess.AS 67%

i-Code: An Integrative and Composable Multimodal Learning Framework

Ziyi Yang, Yuwei Fang, Chenguang Zhu, Reid Pryzant, Dongdong Chen, Yu Shi, Yichong Xu, Yao Qian, Mei Gao, Yi-Ling Chen, Liyang Lu, Yujia Xie, Robert Gmyr, Noel Codella, Naoyuki Kanda, Bin Xiao, 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

2203.16691 2022-04-01 eess.AS cs.AI cs.CL cs.LG cs.SD 67%

MAE-AST: Masked Autoencoding Audio Spectrogram Transformer

Alan Baade, Puyuan Peng, David Harwath

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

Comments Submitted to INTERSPEECH. 5 pages, 2 figures, 5 tables

2110.05909 2022-03-30 cs.CV 67%

Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes

Christoph Wick, Jochen Zöllner, Tobias Grüning

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

Comments 15 pages, 6 tables, 3 figures

2202.06769 2022-02-15 cs.CL cs.AI cs.LG 67%

Punctuation restoration in Swedish through fine-tuned KB-BERT

John Björkman Nilsson

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

Journal ref TRITA-EECS-EX ; 2021:526

1907.10761 2021-12-28 cs.CL cs.AI cs.LG 67%

Bilingual Lexicon Induction through Unsupervised Machine Translation

Mikel Artetxe, Gorka Labaka, Eneko Agirre

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

Comments ACL 2019

1. 预训练与数据 12486 篇

Turning a CLIP Model into a Scene Text Detector

Multi-Modal Few-Shot Temporal Action Detection

Optical Character Recognition and Transcription of Berber Signs from Images in a Low-Resource Language Amazigh

CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge

SimpleClick: Interactive Image Segmentation with Simple Vision Transformers

disco: a toolkit for Distributional Control of Generative Models

Learning from Multiple Sources for Data-to-Text and Text-to-Data

Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision

Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval

Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition from Continuous Speech Signals

SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph

CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation

Evaluation of Synthetic Datasets for Conversational Recommender Systems

Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm

PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training

A Prompt-based Few-shot Learning Approach to Software Conflict Detection

SCROLLS: Standardized CompaRison Over Long Language Sequences

VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers

Expanding Language-Image Pretrained Models for General Video Recognition

Enhancing Automated Software Traceability by Transfer Learning from Open-World Data

Codec at SemEval-2022 Task 5: Multi-Modal Multi-Transformer Misogynous Meme Classification Framework

Learning to Compose Diversified Prompts for Image Emotion Classification

Markedness in Visual Semantic AI

i-Code: An Integrative and Composable Multimodal Learning Framework

MAE-AST: Masked Autoencoding Audio Spectrogram Transformer

Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes

Punctuation restoration in Swedish through fine-tuned KB-BERT

Bilingual Lexicon Induction through Unsupervised Machine Translation