语言大模型 / LLM - arXivDaily 专题

2109.04275 2022-04-05 cs.CV cs.MM 78%

M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining

Xiao Dong, Xunlin Zhan, Yangxin Wu, Yunchao Wei, Michael C. Kampffmeyer, Xiaoyong Wei, Minlong Lu, Yaowei Wang, Xiaodan Liang

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

Comments CVPR2022

2203.15788 2022-03-30 cs.RO 78%

COMPASS: Contrastive Multimodal Pretraining for Autonomous Systems

Shuang Ma, Sai Vemprala, Wenshan Wang, Jayesh K. Gupta, Yale Song, Daniel McDuff, Ashish Kapoor

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

2112.00496 2022-03-29 cs.CV 78%

Revisiting the Transferability of Supervised Pretraining: an MLP Perspective

Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang

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

Comments Accepted by CVPR 2022. [camera ready with supplement]

2104.04687 2021-12-28 cs.CV 78%

Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining

Yueh-Cheng Liu, Yu-Kai Huang, Hung-Yueh Chiang, Hung-Ting Su, Zhe-Yu Liu, Chin-Tang Chen, Ching-Yu Tseng, Winston H. Hsu

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

2101.12482 2021-12-06 cs.CV 78%

Self-Supervised Pretraining for RGB-D Salient Object Detection

Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Xiang Ruan

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

Comments This work was accepted by AAAI 2022

2106.02637 2021-10-26 cs.CV 78%

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Fangyun Wei, Yue Gao, Zhirong Wu, Han Hu, Stephen Lin

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

Comments Accepted by NeurIPS 2021 (spotlight), code is availabel at https://github.com/hologerry/SoCo

2106.03373 2021-10-19 cs.IR 78%

Pre-trained Language Model for Web-scale Retrieval in Baidu Search

Yiding Liu, Guan Huang, Jiaxiang Liu, Weixue Lu, Suqi Cheng, Yukun Li, Daiting Shi, Shuaiqiang Wang, Zhicong Cheng, Dawei Yin

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

Comments Accepted by KDD 2021

2110.01710 2021-10-06 cs.SE 78%

PyTorrent: A Python Library Corpus for Large-scale Language Models

Mehdi Bahrami, N. C. Shrikanth, Shade Ruangwan, Lei Liu, Yuji Mizobuchi, Masahiro Fukuyori, Wei-Peng Chen, Kazuki Munakata, Tim Menzies

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

Comments 10 pages, 2 figures, 5 tables

2109.13228 2021-09-28 cs.CV cs.CY 78%

PASS: An ImageNet replacement for self-supervised pretraining without humans

Yuki M. Asano, Christian Rupprecht, Andrew Zisserman, Andrea Vedaldi

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

Comments Accepted to NeurIPS Track on Datasets and Benchmarks 2021. Webpage: https://www.robots.ox.ac.uk/~vgg/research/pass/

2108.07582 2021-08-18 cs.CV 78%

Self-Supervised Pretraining and Controlled Augmentation Improve Rare Wildlife Recognition in UAV Images

Xiaochen Zheng, Benjamin Kellenberger, Rui Gong, Irena Hajnsek, Devis Tuia

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

Comments accepted by 2021 IEEE/CVF International Conference on Computer Vision (ICCV) Workshops

2011.11479 2021-08-18 cs.CV 78%

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

Humam Alwassel, Silvio Giancola, Bernard Ghanem

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

Comments Accepted to ICCV 2021 workshops proceedings

2108.04026 2021-08-10 cs.IR 78%

IntenT5: Search Result Diversification using Causal Language Models

Sean MacAvaney, Craig Macdonald, Roderick Murray-Smith, Iadh Ounis

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

2107.14572 2021-08-10 cs.CV 78%

Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining

Xunlin Zhan, Yangxin Wu, Xiao Dong, Yunchao Wei, Minlong Lu, Yichi Zhang, Hang Xu, Xiaodan Liang

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

2103.10957 2021-08-06 cs.CV 78%

Efficient Visual Pretraining with Contrastive Detection

Olivier J. Hénaff, Skanda Koppula, Jean-Baptiste Alayrac, Aaron van den Oord, Oriol Vinyals, João Carreira

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

Comments Technical report

2106.13497 2021-06-28 cs.CV 78%

On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy

Vignesh Srinivasan, Nils Strodthoff, Jackie Ma, Alexander Binder, Klaus-Robert Müller, Wojciech Samek

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

2102.08318 2021-04-07 cs.CV 78%

Instance Localization for Self-supervised Detection Pretraining

Ceyuan Yang, Zhirong Wu, Bolei Zhou, Stephen Lin

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

Comments To appear in CVPR 2021. Code is available at https://github.com/limbo0000/InstanceLoc

2103.12718 2021-03-26 cs.CV 78%

Self-Supervised Pretraining Improves Self-Supervised Pretraining

Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi, Vivek Vijaykumar, Richard Mao, Bo Li, Shanghang Zhang, Devin Guillory, Sean Metzger, Kurt Keutzer, Trevor Darrell

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

2103.09423 2021-03-18 cs.SE 78%

Towards a question answering assistant for software development using a transformer-based language model

Liliane do Nascimento Vale, Marcelo de Almeida Maia

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

2101.00529 2021-03-11 cs.CV cs.AI cs.CL cs.LG 78%

VinVL: Revisiting Visual Representations in Vision-Language Models

Pengchuan Zhang, Xiujun Li, Xiaowei Hu, Jianwei Yang, Lei Zhang, Lijuan Wang, Yejin Choi, Jianfeng Gao

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

Journal ref CVPR 2021

2101.02691 2021-01-08 cs.CV 78%

Self-Supervised Pretraining of 3D Features on any Point-Cloud

Zaiwei Zhang, Rohit Girdhar, Armand Joulin, Ishan Misra

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

2012.14631 2021-01-01 cs.SE 78%

Multi-task Learning based Pre-trained Language Model for Code Completion

Fang Liu, Ge Li, Yunfei Zhao, Zhi Jin

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

Comments Accepted by International Conference on Automated Software Engineering (ASE 2020)

2012.07101 2020-12-15 cs.CV 78%

Learning Heatmap-Style Jigsaw Puzzles Provides Good Pretraining for 2D Human Pose Estimation

Kun Zhang, Rui Wu, Ping Yao, Kai Deng, Ding Li, Renbiao Liu, Chuanguang Yang, Ge Chen, Min Du, Tianyao Zheng

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

2012.04446 2020-12-09 cs.MM 78%

LAMP: Label Augmented Multimodal Pretraining

Jia Guo, Chen Zhu, Yilun Zhao, Heda Wang, Yao Hu, Xiaofei He, Deng Cai

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

2007.13135 2020-07-28 cs.CV eess.IV 78%

Contrastive Visual-Linguistic Pretraining

Lei Shi, Kai Shuang, Shijie Geng, Peng Su, Zhengkai Jiang, Peng Gao, Zuohui Fu, Gerard de Melo, Sen Su

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

1803.03481 2020-02-11 cs.RO cs.AI cs.CL cs.LG 78%

Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping

Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi, Tetsunari Inamura

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

Comments Accepted to Autonomous Robots (24 January 2020)

1911.07781 2019-11-19 cs.SE 78%

Combining Program Analysis and Statistical Language Model for Code Statement Completion

Son Nguyen, Tien N. Nguyen, Yi Li, Shaohua Wang

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

Comments Proceedings of the 34th IEEE/ACM International Conference on Automated Software Engineering Conference (ASE 2019)

1902.03751 2019-10-29 cs.CV 78%

Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded

Ramprasaath R. Selvaraju, Stefan Lee, Yilin Shen, Hongxia Jin, Shalini Ghosh, Larry Heck, Dhruv Batra, Devi Parikh

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

Comments Published at ICCV'2019

Journal ref The IEEE International Conference on Computer Vision (ICCV) 2019

1806.08724 2018-06-25 cs.SD eess.AS 78%

Evaluating language models of tonal harmony

David R. W. Sears, Filip Korzeniowski, Gerhard Widmer

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

Comments 7 pages, 4 figures, 3 tables. To appear in Proceedings of the 19th International Society for Music Information Retrieval Conference (ISMIR), Paris, France

1805.00932 2018-05-03 cs.CV 78%

Exploring the Limits of Weakly Supervised Pretraining

Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He, Manohar Paluri, Yixuan Li, Ashwin Bharambe, Laurens van der Maaten

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

Comments Technical report

1802.10038 2018-03-01 cs.CV 78%

Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning

Christian Reul, Uwe Springmann, Christoph Wick, Frank Puppe

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

Comments Submitted to JLCL Volume 33 (2018), Issue 1: Special Issue on Automatic Text and Layout Recognition

1. 预训练与数据 12429 篇

M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining

COMPASS: Contrastive Multimodal Pretraining for Autonomous Systems

Revisiting the Transferability of Supervised Pretraining: an MLP Perspective

Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining

Self-Supervised Pretraining for RGB-D Salient Object Detection

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Pre-trained Language Model for Web-scale Retrieval in Baidu Search

PyTorrent: A Python Library Corpus for Large-scale Language Models

PASS: An ImageNet replacement for self-supervised pretraining without humans

Self-Supervised Pretraining and Controlled Augmentation Improve Rare Wildlife Recognition in UAV Images

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

IntenT5: Search Result Diversification using Causal Language Models

Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining

Efficient Visual Pretraining with Contrastive Detection

On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy

Instance Localization for Self-supervised Detection Pretraining

Self-Supervised Pretraining Improves Self-Supervised Pretraining

Towards a question answering assistant for software development using a transformer-based language model

VinVL: Revisiting Visual Representations in Vision-Language Models

Self-Supervised Pretraining of 3D Features on any Point-Cloud

Multi-task Learning based Pre-trained Language Model for Code Completion

Learning Heatmap-Style Jigsaw Puzzles Provides Good Pretraining for 2D Human Pose Estimation

LAMP: Label Augmented Multimodal Pretraining

Contrastive Visual-Linguistic Pretraining

Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping

Combining Program Analysis and Statistical Language Model for Code Statement Completion

Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded

Evaluating language models of tonal harmony

Exploring the Limits of Weakly Supervised Pretraining

Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning