语言大模型 / LLM - arXivDaily 专题

2306.10159 2024-03-22 cs.CV 82%

Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos

Md Zahid Hasan, Jiajing Chen, Jiyang Wang, Mohammed Shaiqur Rahman, Ameya Joshi, Senem Velipasalar, Chinmay Hegde, Anuj Sharma, Soumik Sarkar

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

Comments 15 pages, 7 figures

2403.12918 2024-03-20 cs.CL cs.AI cs.LG 82%

Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts

Sai Ashish Somayajula, Youwei Liang, Abhishek Singh, Li Zhang, Pengtao Xie

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

Comments Accepted as a long paper to NAACL 2024 Main Conference; 18 pages, 11 tables, 3 figures

2403.02330 2024-03-05 cs.CV 82%

RegionGPT: Towards Region Understanding Vision Language Model

Qiushan Guo, Shalini De Mello, Hongxu Yin, Wonmin Byeon, Ka Chun Cheung, Yizhou Yu, Ping Luo, Sifei Liu

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

Comments Accepted by CVPR 2024

2403.00236 2024-03-04 cs.CL cs.AI cs.LG 82%

Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance

Rachith Aiyappa, Shruthi Senthilmani, Jisun An, Haewoon Kwak, Yong-Yeol Ahn

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

2011.00890 2024-02-16 cs.CL cs.AI cs.LG 82%

Emergent Communication Pretraining for Few-Shot Machine Translation

Yaoyiran Li, Edoardo M. Ponti, Ivan Vulić, Anna Korhonen

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

Journal ref Proceedings of the 28th International Conference on Computational Linguistics (2020) pages 4716-4731

2311.17776 2023-11-30 cs.CV 82%

One-Shot Open Affordance Learning with Foundation Models

Gen Li, Deqing Sun, Laura Sevilla-Lara, Varun Jampani

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

2306.15063 2023-11-09 cs.LG cs.AI cs.CL 82%

Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression

Allan Raventós, Mansheej Paul, Feng Chen, Surya Ganguli

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

Comments The first two authors contributed equally

2307.15936 2023-11-07 cs.LG cs.AI cs.CL stat.ML 82%

A Theory for Emergence of Complex Skills in Language Models

Sanjeev Arora, Anirudh Goyal

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

2112.12938 2023-10-17 cs.CL cs.AI cs.LG 82%

Counterfactual Memorization in Neural Language Models

Chiyuan Zhang, Daphne Ippolito, Katherine Lee, Matthew Jagielski, Florian Tramèr, Nicholas Carlini

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

Comments NeurIPS 2023; 42 pages, 33 figures

2305.08732 2023-10-12 cs.CL cs.AI cs.IR cs.LG 82%

Knowledge Rumination for Pre-trained Language Models

Yunzhi Yao, Peng Wang, Shengyu Mao, Chuanqi Tan, Fei Huang, Huajun Chen, Ningyu Zhang

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

Comments EMNLP 2023

2305.16183 2023-10-03 cs.LG cs.AI cs.CL 82%

Passive learning of active causal strategies in agents and language models

Andrew Kyle Lampinen, Stephanie C Y Chan, Ishita Dasgupta, Andrew J Nam, Jane X Wang

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

Comments Advances in Neural Information Processing Systems (NeurIPS 2023). 10 pages main text

2309.06809 2023-09-14 cs.CV 82%

TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification

M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Horst Possegger, Rogerio Feris, Horst Bischof

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

Comments Code is available at: https://github.com/jmiemirza/TAP

2308.13676 2023-08-29 cs.CL cs.AI cs.LG 82%

Rethinking Language Models as Symbolic Knowledge Graphs

Vishwas Mruthyunjaya, Pouya Pezeshkpour, Estevam Hruschka, Nikita Bhutani

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

2308.10445 2023-08-22 cs.CV 82%

When Prompt-based Incremental Learning Does Not Meet Strong Pretraining

Yu-Ming Tang, Yi-Xing Peng, Wei-Shi Zheng

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

Comments Accepted to ICCV 2023

2308.10061 2023-08-22 cs.CV 82%

DPL: Decoupled Prompt Learning for Vision-Language Models

Chen Xu, Yuhan Zhu, Guozhen Zhang, Haocheng Shen, Yixuan Liao, Xiaoxin Chen, Gangshan Wu, Limin Wang

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

Comments 11 pages, 5 figures, 8 tables

2308.08774 2023-08-21 cs.CL cs.AI cs.CR cs.LG 82%

Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models

Phillip Rust, Anders Søgaard

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

Comments ICML 2023

2308.07791 2023-08-16 cs.CL cs.AI cs.LG 82%

Informed Named Entity Recognition Decoding for Generative Language Models

Tobias Deußer, Lars Hillebrand, Christian Bauckhage, Rafet Sifa

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

Comments 12 pages, 2 figures, 4 tables

2206.00621 2023-06-13 cs.CL cs.AI cs.CV cs.LG 82%

Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training

Yan Zeng, Wangchunshu Zhou, Ao Luo, Ziming Cheng, Xinsong Zhang

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

Comments ACL 2023

2306.03932 2023-06-08 cs.CV 82%

Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

Zaid Khan, Vijay Kumar BG, Samuel Schulter, Xiang Yu, Yun Fu, Manmohan Chandraker

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

Comments CVPR 2023

2303.14302 2023-06-06 cs.CV 82%

VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining

Junjie Ke, Keren Ye, Jiahui Yu, Yonghui Wu, Peyman Milanfar, Feng Yang

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

Comments CVPR 2023, https://github.com/google-research/google-research/tree/master/vila

2302.04460 2023-06-02 cs.CL cs.AI cs.CR cs.LG 82%

Bag of Tricks for Training Data Extraction from Language Models

Weichen Yu, Tianyu Pang, Qian Liu, Chao Du, Bingyi Kang, Yan Huang, Min Lin, Shuicheng Yan

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

Comments ICML 2023

2208.08241 2023-06-01 cs.LG cs.AI cs.CL cs.CV cs.HC 82%

ILLUME: Rationalizing Vision-Language Models through Human Interactions

Manuel Brack, Patrick Schramowski, Björn Deiseroth, Kristian Kersting

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

Comments Proceedings of the 40th International Conference on Machine Learning (ICML), 2023

2212.01349 2023-05-29 cs.CL cs.AI cs.LG 82%

Nonparametric Masked Language Modeling

Sewon Min, Weijia Shi, Mike Lewis, Xilun Chen, Wen-tau Yih, Hannaneh Hajishirzi, Luke Zettlemoyer

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

Comments 20 pages; 9 figures. Published at ACL 2023 Findings. Code available at https://github.com/facebookresearch/NPM

2304.13130 2023-04-27 cs.CV 82%

Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining

Giacomo Nebbia, Adriana Kovashka

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

2211.16594 2023-04-20 cs.CV 82%

Exploiting Category Names for Few-Shot Classification with Vision-Language Models

Taihong Xiao, Zirui Wang, Liangliang Cao, Jiahui Yu, Shengyang Dai, Ming-Hsuan Yang

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

2302.03241 2023-04-13 cs.CL cs.AI cs.LG cs.NE 82%

Continual Pre-training of Language Models

Zixuan Ke, Yijia Shao, Haowei Lin, Tatsuya Konishi, Gyuhak Kim, Bing Liu

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

Comments https://github.com/UIC-Liu-Lab/ContinualLM

Journal ref ICLR 2023

2304.03580 2023-04-10 cs.CV 82%

Language-aware Multiple Datasets Detection Pretraining for DETRs

Jing Hao, Song Chen, Xiaodi Wang, Shumin Han

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

2304.02853 2023-04-07 cs.CV 82%

Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce

Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

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

Comments 16 pages, 10 figures, accepted by CVPR 2023

2303.12417 2023-03-28 cs.CV 82%

CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data

Yihan Zeng, Chenhan Jiang, Jiageng Mao, Jianhua Han, Chaoqiang Ye, Qingqiu Huang, Dit-Yan Yeung, Zhen Yang, Xiaodan Liang, Hang Xu

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

Comments To appear at CVPR 2023

2303.13009 2023-03-24 cs.CV 82%

MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models

Dohwan Ko, Joonmyung Choi, Hyeong Kyu Choi, Kyoung-Woon On, Byungseok Roh, Hyunwoo J. Kim

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

Comments Accepted paper at CVPR 2023

1. 预训练与数据 12393 篇

Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos

Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts

RegionGPT: Towards Region Understanding Vision Language Model

Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance

Emergent Communication Pretraining for Few-Shot Machine Translation

One-Shot Open Affordance Learning with Foundation Models

Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression

A Theory for Emergence of Complex Skills in Language Models

Counterfactual Memorization in Neural Language Models

Knowledge Rumination for Pre-trained Language Models

Passive learning of active causal strategies in agents and language models

TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification

Rethinking Language Models as Symbolic Knowledge Graphs

When Prompt-based Incremental Learning Does Not Meet Strong Pretraining

DPL: Decoupled Prompt Learning for Vision-Language Models

Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models

Informed Named Entity Recognition Decoding for Generative Language Models

Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training

Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining

Bag of Tricks for Training Data Extraction from Language Models

ILLUME: Rationalizing Vision-Language Models through Human Interactions

Nonparametric Masked Language Modeling

Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining

Exploiting Category Names for Few-Shot Classification with Vision-Language Models

Continual Pre-training of Language Models

Language-aware Multiple Datasets Detection Pretraining for DETRs

Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce

CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data

MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models