Alert button

"Text": models, code, and papers
Alert button

Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner

May 19, 2023
Zikang Liu, Sihan Chen, Longteng Guo, Handong Li, Xingjian He, Jing Liu

Figure 1 for Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner
Figure 2 for Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner
Figure 3 for Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner
Figure 4 for Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner
Viaarxiv icon

How learners produce data from text in classifying clickbait

Jan 28, 2023
Nicholas J. Horton, Jie Chao, Phebe Palmer, William Finzer

Viaarxiv icon

Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval

Jan 30, 2023
Yizhen Chen, Jie Wang, Lijian Lin, Zhongang Qi, Jin Ma, Ying Shan

Figure 1 for Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval
Figure 2 for Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval
Figure 3 for Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval
Figure 4 for Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval
Viaarxiv icon

Surfacing Biases in Large Language Models using Contrastive Input Decoding

May 12, 2023
Gal Yona, Or Honovich, Itay Laish, Roee Aharoni

Figure 1 for Surfacing Biases in Large Language Models using Contrastive Input Decoding
Figure 2 for Surfacing Biases in Large Language Models using Contrastive Input Decoding
Figure 3 for Surfacing Biases in Large Language Models using Contrastive Input Decoding
Figure 4 for Surfacing Biases in Large Language Models using Contrastive Input Decoding
Viaarxiv icon

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training

Jun 02, 2023
Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, Hannaneh Hajishirzi

Figure 1 for Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Figure 2 for Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Figure 3 for Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Figure 4 for Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Viaarxiv icon

AI Imagery and the Overton Window

Jun 02, 2023
Sarah K. Amer

Viaarxiv icon

Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach

Jan 05, 2023
Miao Chen, Xinjiang Lu, Tong Xu, Yanyan Li, Jingbo Zhou, Dejing Dou, Hui Xiong

Figure 1 for Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach
Figure 2 for Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach
Figure 3 for Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach
Figure 4 for Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach
Viaarxiv icon

Text-Visual Prompting for Efficient 2D Temporal Video Grounding

Mar 09, 2023
Yimeng Zhang, Xin Chen, Jinghan Jia, Sijia Liu, Ke Ding

Figure 1 for Text-Visual Prompting for Efficient 2D Temporal Video Grounding
Figure 2 for Text-Visual Prompting for Efficient 2D Temporal Video Grounding
Figure 3 for Text-Visual Prompting for Efficient 2D Temporal Video Grounding
Figure 4 for Text-Visual Prompting for Efficient 2D Temporal Video Grounding
Viaarxiv icon

Text-driven Visual Synthesis with Latent Diffusion Prior

Feb 16, 2023
Ting-Hsuan Liao, Songwei Ge, Yiran Xu, Yao-Chih Lee, Badour AlBahar, Jia-Bin Huang

Figure 1 for Text-driven Visual Synthesis with Latent Diffusion Prior
Figure 2 for Text-driven Visual Synthesis with Latent Diffusion Prior
Figure 3 for Text-driven Visual Synthesis with Latent Diffusion Prior
Figure 4 for Text-driven Visual Synthesis with Latent Diffusion Prior
Viaarxiv icon

Better Aligning Text-to-Image Models with Human Preference

Mar 25, 2023
Xiaoshi Wu, Keqiang Sun, Feng Zhu, Rui Zhao, Hongsheng Li

Figure 1 for Better Aligning Text-to-Image Models with Human Preference
Figure 2 for Better Aligning Text-to-Image Models with Human Preference
Figure 3 for Better Aligning Text-to-Image Models with Human Preference
Figure 4 for Better Aligning Text-to-Image Models with Human Preference
Viaarxiv icon