Alert button

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

Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite

Dec 20, 2022
Xun Wang, Tao Ge, Allen Mao, Yuki Li, Furu Wei, Si-Qing Chen

Figure 1 for Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
Figure 2 for Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
Figure 3 for Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
Figure 4 for Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
Viaarxiv icon

A Simple Feature Method for Prosody Rhythm Comparison

Dec 20, 2022
Mariana Julião, Alberto Abad, Helena Moniz

Figure 1 for A Simple Feature Method for Prosody Rhythm Comparison
Figure 2 for A Simple Feature Method for Prosody Rhythm Comparison
Figure 3 for A Simple Feature Method for Prosody Rhythm Comparison
Figure 4 for A Simple Feature Method for Prosody Rhythm Comparison
Viaarxiv icon

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

Dec 20, 2022
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal

Figure 1 for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
Figure 2 for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
Figure 3 for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
Figure 4 for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
Viaarxiv icon

Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment

Dec 20, 2022
Rohan Pandey, Rulin Shao, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency

Figure 1 for Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment
Figure 2 for Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment
Figure 3 for Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment
Figure 4 for Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment
Viaarxiv icon

Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks

Dec 20, 2022
Daniel F. S. Santos, Rafael G. Pires, Danilo Colombo, João P. Papa

Figure 1 for Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
Figure 2 for Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
Figure 3 for Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
Figure 4 for Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
Viaarxiv icon

COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics

Mar 27, 2022
Lianhui Qin, Sean Welleck, Daniel Khashabi, Yejin Choi

Figure 1 for COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
Figure 2 for COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
Figure 3 for COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
Figure 4 for COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
Viaarxiv icon

Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety

Dec 13, 2022
Joshua Albrecht, Ellie Kitanidis, Abraham J. Fetterman

Figure 1 for Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety
Figure 2 for Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety
Figure 3 for Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety
Figure 4 for Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety
Viaarxiv icon

LADIS: Language Disentanglement for 3D Shape Editing

Dec 09, 2022
Ian Huang, Panos Achlioptas, Tianyi Zhang, Sergey Tulyakov, Minhyuk Sung, Leonidas Guibas

Figure 1 for LADIS: Language Disentanglement for 3D Shape Editing
Figure 2 for LADIS: Language Disentanglement for 3D Shape Editing
Figure 3 for LADIS: Language Disentanglement for 3D Shape Editing
Figure 4 for LADIS: Language Disentanglement for 3D Shape Editing
Viaarxiv icon

Dynamic Contrastive Distillation for Image-Text Retrieval

Jul 04, 2022
Jun Rao, Liang Ding, Shuhan Qi, Meng Fang, Yang Liu, Li Shen, Dacheng Tao

Figure 1 for Dynamic Contrastive Distillation for Image-Text Retrieval
Figure 2 for Dynamic Contrastive Distillation for Image-Text Retrieval
Figure 3 for Dynamic Contrastive Distillation for Image-Text Retrieval
Figure 4 for Dynamic Contrastive Distillation for Image-Text Retrieval
Viaarxiv icon

1st Place Solutions for UG2+ Challenge 2022 ATMOSPHERIC TURBULENCE MITIGATION

Oct 30, 2022
Zhuang Liu, Zhichao Zhao, Ye Yuan, Zhi Qiao, Jinfeng Bai, Zhilong Ji

Figure 1 for 1st Place Solutions for UG2+ Challenge 2022 ATMOSPHERIC TURBULENCE MITIGATION
Figure 2 for 1st Place Solutions for UG2+ Challenge 2022 ATMOSPHERIC TURBULENCE MITIGATION
Figure 3 for 1st Place Solutions for UG2+ Challenge 2022 ATMOSPHERIC TURBULENCE MITIGATION
Figure 4 for 1st Place Solutions for UG2+ Challenge 2022 ATMOSPHERIC TURBULENCE MITIGATION
Viaarxiv icon