语言大模型 / LLM - arXivDaily 专题

2304.06212 2023-04-14 cs.CV 50%

[CLS] Token is All You Need for Zero-Shot Semantic Segmentation

Letian Wu, Wenyao Zhang, Tengping Jiang, Wankou Yang, Xin Jin, Wenjun Zeng

专题命中知识编辑与模型理解：language model(abstract)

Comments 8 pages,6 figures

2301.03410 2023-04-13 cs.CV 50%

In Defense of Structural Symbolic Representation for Video Event-Relation Prediction

Andrew Lu, Xudong Lin, Yulei Niu, Shih-Fu Chang

专题命中知识编辑与模型理解：pretraining(abstract)

Comments CVPRW 23, Learning with Limited Labelled Data

2210.03879 2023-04-11 cs.CV 50%

Improving Data-Efficient Fossil Segmentation via Model Editing

Indu Panigrahi, Ryan Manzuk, Adam Maloof, Ruth Fong

专题命中知识编辑与模型理解：language model(abstract)

Comments CVPR 2023 Workshop on Learning with Limited Labelled Data for Image and Video Understanding

2302.12248 2023-03-30 cs.CV 50%

Learning Visual Representations via Language-Guided Sampling

Mohamed El Banani, Karan Desai, Justin Johnson

专题命中知识编辑与模型理解：language model(abstract)

Comments Accepted to CVPR 2023. v2 is camera-ready version with additional ImageNet evaluations. Project page: https://github.com/mbanani/lgssl

2303.09252 2023-03-17 cs.CV 50%

GridCLIP: One-Stage Object Detection by Grid-Level CLIP Representation Learning

Jiayi Lin, Shaogang Gong

专题命中知识编辑与模型理解：foundation model(abstract)

2202.00924 2023-03-16 math.DS cs.NA cs.SY eess.SY math.NA 50%

Designing Social Distancing Policies for the COVID-19 Pandemic: A probabilistic model predictive control approach

Antonis Armaou, Bryce Katch, Lucia Russo, Constantinos Siettos

专题命中知识编辑与模型理解：prompting(abstract)

Journal ref Mathematical Biosciences and Engineering, 19, 8804-8832, 2022

2209.06430 2023-03-03 cs.CV 50%

CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment

Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, Jiebo Luo

专题命中知识编辑与模型理解：pretraining(abstract)

Comments Accepted by ICLR 2023

2302.11349 2023-02-23 cs.CV 50%

Steerable Equivariant Representation Learning

Sangnie Bhardwaj, Willie McClinton, Tongzhou Wang, Guillaume Lajoie, Chen Sun, Phillip Isola, Dilip Krishnan

专题命中知识编辑与模型理解：post-training(abstract)

2301.09072 2023-01-24 cs.SE 50%

ContraBERT: Enhancing Code Pre-trained Models via Contrastive Learning

Shangqing Liu, Bozhi Wu, Xiaofei Xie, Guozhu Meng, Yang Liu

专题命中知识编辑与模型理解：language model(abstract)

2212.11030 2022-12-22 cs.CV 50%

Deep set conditioned latent representations for action recognition

Akash Singh, Tom De Schepper, Kevin Mets, Peter Hellinckx, Jose Oramas, Steven Latre

专题命中知识编辑与模型理解：pretraining(abstract)

Comments Conference VISAPP 2022, 11 pages,5 figures, 2 Tables, 6 plots

Journal ref In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-555-5; ISSN 2184-4321, year 2022, pages 456-466

2208.11821 2022-12-22 cs.CV 50%

Refine and Represent: Region-to-Object Representation Learning

Akash Gokul, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Kazuki Kozuka, Trevor Darrell, Colorado J Reed

专题命中知识编辑与模型理解：pretraining(abstract)

2212.01893 2022-12-06 cs.CV 50%

Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering

Duy M. H. Nguyen, Hoang Nguyen, Mai T. N. Truong, Tri Cao, Binh T. Nguyen, Nhat Ho, Paul Swoboda, Shadi Albarqouni, Pengtao Xie, Daniel Sonntag

专题命中知识编辑与模型理解：language model(abstract)

Comments Accepted at AAAI 2023

2212.01568 2022-12-06 cs.CV 50%

Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation

En Yu, Songtao Liu, Zhuoling Li, Jinrong Yang, Zeming li, Shoudong Han, Wenbing Tao

专题命中知识编辑与模型理解：prompting(abstract)

Comments Accepted by AAAI2023

2211.09529 2022-11-18 cs.CV 50%

InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges

Guo Chen, Sen Xing, Zhe Chen, Yi Wang, Kunchang Li, Yizhuo Li, Yi Liu, Jiahao Wang, Yin-Dong Zheng, Bingkun Huang, Zhiyu Zhao, Junting Pan, Yifei Huang, Zun Wang, Jiashuo Yu, Yinan He, Hongjie Zhang, Tong Lu, Yali Wang, Limin Wang, Yu Qiao

专题命中知识编辑与模型理解：foundation model(abstract)

Comments Technical report in 2nd International Ego4D Workshop@ECCV 2022. Code will be released at https://github.com/OpenGVLab/ego4d-eccv2022-solutions

2211.08533 2022-11-17 cs.CV 50%

A Point in the Right Direction: Vector Prediction for Spatially-aware Self-supervised Volumetric Representation Learning

Yejia Zhang, Pengfei Gu, Nishchal Sapkota, Hao Zheng, Peixian Liang, Danny Z. Chen

专题命中知识编辑与模型理解：pretraining(abstract)

2211.05636 2022-11-11 cs.CV 50%

Rare Wildlife Recognition with Self-Supervised Representation Learning

Xiaochen Zheng

专题命中知识编辑与模型理解：pretraining(abstract)

Comments A dissertation submitted to attain the degree of Master of Sciences of ETH Zurich in August 2021. Code is available at: https://github.com/xcvil/self-rare-wildlife

2211.04861 2022-11-10 cs.CV 50%

ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation

Bin Shan, Yaqian Han, Weichong Yin, Shuohuan Wang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

专题命中知识编辑与模型理解：language model(abstract)

Comments 13 pages, 2 figures

2210.15187 2022-10-28 cs.CV 50%

Learning Joint Representation of Human Motion and Language

Jihoon Kim, Youngjae Yu, Seungyoun Shin, Taehyun Byun, Sungjoon Choi

专题命中知识编辑与模型理解：language model(abstract)

2209.03592 2022-10-18 cs.CV 50%

Multi-Granularity Prediction for Scene Text Recognition

Peng Wang, Cheng Da, Cong Yao

专题命中知识编辑与模型理解：language model(abstract)

Comments Accepted by ECCV2022

2210.06886 2022-10-14 cs.CV 50%

ImaginaryNet: Learning Object Detectors without Real Images and Annotations

Minheng Ni, Zitong Huang, Kailai Feng, Wangmeng Zuo

专题命中知识编辑与模型理解：language model(abstract)

Comments 12 pages, 6 figures

2210.04154 2022-10-11 cs.CV 50%

Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

Haosen Yang, Deng Huang, Bin Wen, Jiannan Wu, Hongxun Yao, Yi Jiang, Xiatian Zhu, Zehuan Yuan

专题命中知识编辑与模型理解：pretraining(abstract)

Comments 17 pages, 6 figures

2209.13853 2022-09-29 cs.CV 50%

Thinking Hallucination for Video Captioning

Nasib Ullah, Partha Pratim Mohanta

专题命中知识编辑与模型理解：language model(abstract)

Comments 18 pages

2208.10043 2022-08-23 cs.CV 50%

Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning

Hualiang Wang, Siming Fu, Xiaoxuan He, Hangxiang Fang, Zuozhu Liu, Haoji Hu

专题命中知识编辑与模型理解：post-training(abstract)

Journal ref ECCV2022

2208.09846 2022-08-23 cs.IR 50%

A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval

Xinyu Ma, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng

专题命中知识编辑与模型理解：language model(abstract)

Comments Accepted by CIKM2022

2208.07654 2022-08-17 cs.CV 50%

Matching Multiple Perspectives for Efficient Representation Learning

Omiros Pantazis, Mathew Salvaris

专题命中知识编辑与模型理解：pretraining(abstract)

Comments ECCVW 2022

2207.11100 2022-07-29 cs.CV 50%

Zero-Shot Video Captioning with Evolving Pseudo-Tokens

Yoad Tewel, Yoav Shalev, Roy Nadler, Idan Schwartz, Lior Wolf

专题命中知识编辑与模型理解：language model(abstract)

Comments preprint

2207.08525 2022-07-19 cs.CV 50%

Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration

Bohua Peng, Mobarakol Islam, Mei Tu

专题命中知识编辑与模型理解：post-training(abstract)

Comments 13 pages

2201.10990 2022-06-20 cs.CV 50%

Learning To Recognize Procedural Activities with Distant Supervision

Xudong Lin, Fabio Petroni, Gedas Bertasius, Marcus Rohrbach, Shih-Fu Chang, Lorenzo Torresani

专题命中知识编辑与模型理解：language model(abstract)

Comments CVPR 2022. Code will be released here https://github.com/facebookresearch/video-distant-supervision

2206.02221 2022-06-07 physics.optics quant-ph 50%

Ultrafast Transverse Modulation of Free Electrons by Interaction with Shaped Optical Fields

I. Madan, V. Leccese, A. Mazur, F. Barantani, T. La Grange, A. Sapozhnik, S. Gargiulo, E. Rotunno, J. -C. Olaya, I. Kaminer, V. Grillo, F. J. García de Abajo, F. Carbone, G. M. Vanacore

专题命中知识编辑与模型理解：SLM(abstract)

Comments 21 pages, 5 figures

2205.15071 2022-05-31 physics.chem-ph cond-mat.mtrl-sci 50%

Incorporation of density scaling constraint in density functional design via contrastive representation learning

Weiyi Gong, Tao Sun, Hexin Bai, Shah Tanvir ur Rahman Chowdhury, Peng Chu, Anoj Aryal, Jie Yu, Haibin Ling, John P. Perdew, Qimin Yan

专题命中知识编辑与模型理解：pretraining(abstract)

1. 知识编辑与模型理解 7608 篇

[CLS] Token is All You Need for Zero-Shot Semantic Segmentation

In Defense of Structural Symbolic Representation for Video Event-Relation Prediction

Improving Data-Efficient Fossil Segmentation via Model Editing

Learning Visual Representations via Language-Guided Sampling

GridCLIP: One-Stage Object Detection by Grid-Level CLIP Representation Learning

Designing Social Distancing Policies for the COVID-19 Pandemic: A probabilistic model predictive control approach

CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment

Steerable Equivariant Representation Learning

ContraBERT: Enhancing Code Pre-trained Models via Contrastive Learning

Deep set conditioned latent representations for action recognition

Refine and Represent: Region-to-Object Representation Learning

Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering

Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation

InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges

A Point in the Right Direction: Vector Prediction for Spatially-aware Self-supervised Volumetric Representation Learning

Rare Wildlife Recognition with Self-Supervised Representation Learning

ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation

Learning Joint Representation of Human Motion and Language

Multi-Granularity Prediction for Scene Text Recognition

ImaginaryNet: Learning Object Detectors without Real Images and Annotations

Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

Thinking Hallucination for Video Captioning

Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning

A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval

Matching Multiple Perspectives for Efficient Representation Learning

Zero-Shot Video Captioning with Evolving Pseudo-Tokens

Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration

Learning To Recognize Procedural Activities with Distant Supervision

Ultrafast Transverse Modulation of Free Electrons by Interaction with Shaped Optical Fields

Incorporation of density scaling constraint in density functional design via contrastive representation learning