语言大模型 / LLM - arXivDaily 专题

2212.08054 2023-11-15 cs.CL cs.LG 62%

DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue

William Held, Christopher Hidey, Fei Liu, Eric Zhu, Rahul Goel, Diyi Yang, Rushin Shah

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

Comments 9 Pages; ACL Main Conference 2023

2311.06239 2023-11-13 cs.CL cs.LG 62%

Argumentation Element Annotation Modeling using XLNet

Christopher Ormerod, Amy Burkhardt, Mackenzie Young, Sue Lottridge

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

Comments 28 pages

2303.05828 2023-11-10 cs.CV cs.AI cs.LG 62%

Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution Detection

Nikolas Adaloglou, Felix Michels, Tim Kaiser, Markus Kollmann

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

Comments version_02

2311.04888 2023-11-09 cs.CV cs.AI cs.LG stat.ML 62%

Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks

Quentin Bouniot

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

Comments PhD Thesis

2301.10884 2023-11-08 cs.CL cs.AI 62%

Break It Down: Evidence for Structural Compositionality in Neural Networks

Michael A. Lepori, Thomas Serre, Ellie Pavlick

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

2309.17425 2023-11-07 cs.AI cs.LG 62%

Data Filtering Networks

Alex Fang, Albin Madappally Jose, Amit Jain, Ludwig Schmidt, Alexander Toshev, Vaishaal Shankar

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

2309.14356 2023-11-01 cs.LG cs.CL cs.CV 62%

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs

Tiep Le, Vasudev Lal, Phillip Howard

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

Comments Accepted to NeurIPS 2023 Datasets and Benchmarks Track

2310.18815 2023-10-31 cs.LG cs.AI cs.CV 62%

Rethinking Semi-Supervised Federated Learning: How to co-train fully-labeled and fully-unlabeled client imaging data

Pramit Saha, Divyanshu Mishra, J. Alison Noble

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

Comments Published in MICCAI 2023 with early acceptance and selected as 1 of the top 20 poster highlights under the category: Which work has the potential to impact other applications of AI and CV

2210.04074 2023-10-31 cs.CL cs.AI 62%

Are All Steps Equally Important? Benchmarking Essentiality Detection of Events

Haoyu Wang, Hongming Zhang, Yueguan Wang, Yuqian Deng, Muhao Chen, Dan Roth

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

Comments EMNLP 2023

2310.16269 2023-10-26 cs.CL cs.AI cs.CY 62%

Multilingual Coarse Political Stance Classification of Media. The Editorial Line of a ChatGPT and Bard Newspaper

Cristina España-Bonet

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

Comments To be published at EMNLP 2023 (Findings)

2305.14879 2023-10-25 cs.CL cs.AI 62%

ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games

Ruoyao Wang, Graham Todd, Eric Yuan, Ziang Xiao, Marc-Alexandre Côté, Peter Jansen

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

Comments Accepted to EMNLP 2023

2305.01278 2023-10-25 cs.CV cs.AI cs.CL 62%

VPGTrans: Transfer Visual Prompt Generator across LLMs

Ao Zhang, Hao Fei, Yuan Yao, Wei Ji, Li Li, Zhiyuan Liu, Tat-Seng Chua

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

Comments Project Website: https://vpgtrans.github.io Code: https://github.com/VPGTrans/VPGTrans NeurIPS 2023

2310.14579 2023-10-24 cs.LG cs.AI 62%

FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clients

Jiyun Shin, Jinhyun Ahn, Honggu Kang, Joonhyuk Kang

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

2306.17020 2023-10-24 cs.CL cs.AI 62%

Classifying Crime Types using Judgment Documents from Social Media

Haoxuan Xu, Zeyu He, Mengfan Shen, Songning Lai, Ziqiang Han, Yifan Peng

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

Comments The paper has no errors; it just needs to be supplemented to become a new article

2310.13526 2023-10-23 cs.CL cs.LG 62%

Controlled Randomness Improves the Performance of Transformer Models

Tobias Deußer, Cong Zhao, Wolfgang Krämer, David Leonhard, Christian Bauckhage, Rafet Sifa

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

Comments Accepted at ICMLA 2023, 10 pages, 2 tables

2310.13267 2023-10-23 cs.CL cs.CV cs.LG cs.SD eess.AS 62%

On the Language Encoder of Contrastive Cross-modal Models

Mengjie Zhao, Junya Ono, Zhi Zhong, Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Wei-Hsiang Liao, Takashi Shibuya, Hiromi Wakaki, Yuki Mitsufuji

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

2310.09263 2023-10-16 cs.CL cs.AI cs.DB 62%

Table-GPT: Table-tuned GPT for Diverse Table Tasks

Peng Li, Yeye He, Dror Yashar, Weiwei Cui, Song Ge, Haidong Zhang, Danielle Rifinski Fainman, Dongmei Zhang, Surajit Chaudhuri

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

2204.07580 2023-10-13 cs.CL cs.AI 62%

mGPT: Few-Shot Learners Go Multilingual

Oleh Shliazhko, Alena Fenogenova, Maria Tikhonova, Vladislav Mikhailov, Anastasia Kozlova, Tatiana Shavrina

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

Comments Accepted for publication at Transactions of the Association for Computational Linguistics (TACL) To be presented at the Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)

2310.05847 2023-10-10 cs.LG cs.AI cs.CR cs.IR 62%

Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems

Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Yizhao Zhang, Zhongxuan Han, Dan Meng, Jun Wang

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

Journal ref Proceedings of the 31st ACM International Conference on Multimedia (MM '23), October 29--November 3, 2023, Ottawa, ON, Canada

2302.08817 2023-10-10 cs.CL cs.AI 62%

Natural Response Generation for Chinese Reading Comprehension

Nuo Chen, Hongguang Li, Yinan Bao, Baoyuan Wang, Jia Li

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

Comments 15 pages

Journal ref EMNLP 2023

2310.00887 2023-10-10 cs.RO cs.AI cs.LG 62%

GRID: A Platform for General Robot Intelligence Development

Sai Vemprala, Shuhang Chen, Abhinav Shukla, Dinesh Narayanan, Ashish Kapoor

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

2309.15564 2023-09-29 cs.LG cs.CL cs.CV 62%

Jointly Training Large Autoregressive Multimodal Models

Emanuele Aiello, Lili Yu, Yixin Nie, Armen Aghajanyan, Barlas Oguz

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

2309.16143 2023-09-29 cs.LG cs.AI cs.CV stat.ML 62%

Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples

Shin'ya Yamaguchi

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

Comments Accepted to the 15th Asian Conference on Machine Learning (ACML2023); a preprint of the camera-ready version

2303.16342 2023-09-26 cs.CV cs.AI cs.CL 62%

Language-Guided Audio-Visual Source Separation via Trimodal Consistency

Reuben Tan, Arijit Ray, Andrea Burns, Bryan A. Plummer, Justin Salamon, Oriol Nieto, Bryan Russell, Kate Saenko

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

Comments Accepted at CVPR 2023

2307.04617 2023-09-20 cs.CV cs.AI cs.LG 62%

Weakly-supervised positional contrastive learning: application to cirrhosis classification

Emma Sarfati, Alexandre Bône, Marc-Michel Rohé, Pietro Gori, Isabelle Bloch

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

Comments MICCAI 2023

2303.01584 2023-09-19 cs.CV cs.AI cs.LG cs.NE 62%

Evolutionary Augmentation Policy Optimization for Self-supervised Learning

Noah Barrett, Zahra Sadeghi, Stan Matwin

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

2309.01740 2023-09-07 eess.IV cs.CL cs.CV cs.LG 62%

An Empirical Analysis for Zero-Shot Multi-Label Classification on COVID-19 CT Scans and Uncurated Reports

Ethan Dack, Lorenzo Brigato, Matthew McMurray, Matthias Fontanellaz, Thomas Frauenfelder, Hanno Hoppe, Aristomenis Exadaktylos, Thomas Geiser, Manuela Funke-Chambour, Andreas Christe, Lukas Ebner, Stavroula Mougiakakou

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

Comments Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops 2023

2309.00775 2023-09-06 cs.CV cs.AI cs.LG 62%

Contrastive Feature Masking Open-Vocabulary Vision Transformer

Dahun Kim, Anelia Angelova, Weicheng Kuo

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

Comments Accepted to ICCV 2023

2308.14759 2023-08-30 physics.chem-ph cs.AI cs.LG q-bio.BM 62%

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

Rui Feng, Qi Zhu, Huan Tran, Binghong Chen, Aubrey Toland, Rampi Ramprasad, Chao Zhang

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

2307.02054 2023-08-29 cs.CL cs.AI 62%

Emoji Prediction in Tweets using BERT

Muhammad Osama Nusrat, Zeeshan Habib, Mehreen Alam, Saad Ahmed Jamal

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

Comments This paper is focused on predicting emojis corresponding to tweets using BERT

1. 预训练与数据 12502 篇

DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue

Argumentation Element Annotation Modeling using XLNet

Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution Detection

Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks

Break It Down: Evidence for Structural Compositionality in Neural Networks

Data Filtering Networks

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs

Rethinking Semi-Supervised Federated Learning: How to co-train fully-labeled and fully-unlabeled client imaging data

Are All Steps Equally Important? Benchmarking Essentiality Detection of Events

Multilingual Coarse Political Stance Classification of Media. The Editorial Line of a ChatGPT and Bard Newspaper

ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games

VPGTrans: Transfer Visual Prompt Generator across LLMs

FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clients

Classifying Crime Types using Judgment Documents from Social Media

Controlled Randomness Improves the Performance of Transformer Models

On the Language Encoder of Contrastive Cross-modal Models

Table-GPT: Table-tuned GPT for Diverse Table Tasks

mGPT: Few-Shot Learners Go Multilingual

Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems

Natural Response Generation for Chinese Reading Comprehension

GRID: A Platform for General Robot Intelligence Development

Jointly Training Large Autoregressive Multimodal Models

Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples

Language-Guided Audio-Visual Source Separation via Trimodal Consistency

Weakly-supervised positional contrastive learning: application to cirrhosis classification

Evolutionary Augmentation Policy Optimization for Self-supervised Learning

An Empirical Analysis for Zero-Shot Multi-Label Classification on COVID-19 CT Scans and Uncurated Reports

Contrastive Feature Masking Open-Vocabulary Vision Transformer

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

Emoji Prediction in Tweets using BERT