Alert button

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

On Robustness in Multimodal Learning

Apr 11, 2023
Brandon McKinzie, Joseph Cheng, Vaishaal Shankar, Yinfei Yang, Jonathon Shlens, Alexander Toshev

Figure 1 for On Robustness in Multimodal Learning
Figure 2 for On Robustness in Multimodal Learning
Figure 3 for On Robustness in Multimodal Learning
Figure 4 for On Robustness in Multimodal Learning
Viaarxiv icon

CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition

Mar 20, 2023
Deepti Hegde, Jeya Maria Jose Valanarasu, Vishal M. Patel

Figure 1 for CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
Figure 2 for CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
Figure 3 for CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
Figure 4 for CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
Viaarxiv icon

Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition

Oct 31, 2022
Suyoun Kim, Ke Li, Lucas Kabela, Rongqing Huang, Jiedan Zhu, Ozlem Kalinli, Duc Le

Figure 1 for Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
Figure 2 for Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
Figure 3 for Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
Figure 4 for Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
Viaarxiv icon

Pre-Training With Scientific Text Improves Educational Question Generation

Dec 07, 2022
Hamze Muse, Sahan Bulathwela, Emine Yilmaz

Figure 1 for Pre-Training With Scientific Text Improves Educational Question Generation
Figure 2 for Pre-Training With Scientific Text Improves Educational Question Generation
Viaarxiv icon

TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation

Apr 15, 2023
Jingyao Li, Pengguang Chen, Shengju Qian, Jiaya Jia

Figure 1 for TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation
Figure 2 for TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation
Figure 3 for TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation
Figure 4 for TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation
Viaarxiv icon

A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models

Mar 18, 2023
Junjie Ye, Xuanting Chen, Nuo Xu, Can Zu, Zekai Shao, Shichun Liu, Yuhan Cui, Zeyang Zhou, Chao Gong, Yang Shen, Jie Zhou, Siming Chen, Tao Gui, Qi Zhang, Xuanjing Huang

Figure 1 for A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Figure 2 for A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Figure 3 for A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Figure 4 for A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
Viaarxiv icon

Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries

Aug 19, 2022
Hai Dang, Karim Benharrak, Florian Lehmann, Daniel Buschek

Figure 1 for Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries
Figure 2 for Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries
Figure 3 for Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries
Figure 4 for Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries
Viaarxiv icon

Using Language Models For Knowledge Acquisition in Natural Language Reasoning Problems

Apr 04, 2023
Fangzhen Lin, Ziyi Shou, Chengcai Chen

Viaarxiv icon

DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion

Apr 12, 2023
Johanna Karras, Aleksander Holynski, Ting-Chun Wang, Ira Kemelmacher-Shlizerman

Figure 1 for DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion
Figure 2 for DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion
Figure 3 for DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion
Figure 4 for DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion
Viaarxiv icon

GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering

Mar 24, 2023
Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck, Chris Biemann

Figure 1 for GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
Figure 2 for GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
Figure 3 for GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
Figure 4 for GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
Viaarxiv icon