语言大模型 / LLM

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

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

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

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

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

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)

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

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

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

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

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

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

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

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)

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

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

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

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

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

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

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

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

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

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

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

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

Leveraging Knowledge Graph Embeddings to Enhance Contextual Representations for Relation Extraction

Fréjus A. A. Laleye, Loïc Rakotoson, Sylvain Massip

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

Comments 15 pages, 1 figures, The 17th International Conference on Document Analysis and Recognition

Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate

Michela Lorandi, Anya Belz

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

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

Seungju Han, Jack Hessel, Nouha Dziri, Yejin Choi, Youngjae Yu

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

Comments ICCV 2023, Project page: https://seungjuhan.me/champagne

GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking

Jiaqi Bai, Hongcheng Guo, Jiaheng Liu, Jian Yang, Xinnian Liang, Zhao Yan, Zhoujun Li

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

Comments CIKM 2023