Alert button

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

Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization

May 24, 2023
Xiaochu Li, Minqian Liu, Zhiyang Xu, Lifu Huang

Figure 1 for Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization
Figure 2 for Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization
Figure 3 for Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization
Figure 4 for Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization
Viaarxiv icon

Album Storytelling with Iterative Story-aware Captioning and Large Language Models

May 24, 2023
Munan Ning, Yujia Xie, Dongdong Chen, Zeyin Song, Lu Yuan, Yonghong Tian, Qixiang Ye, Li Yuan

Figure 1 for Album Storytelling with Iterative Story-aware Captioning and Large Language Models
Figure 2 for Album Storytelling with Iterative Story-aware Captioning and Large Language Models
Figure 3 for Album Storytelling with Iterative Story-aware Captioning and Large Language Models
Figure 4 for Album Storytelling with Iterative Story-aware Captioning and Large Language Models
Viaarxiv icon

Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions

May 19, 2023
Shiyao Ding, Takayuki Ito

Figure 1 for Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions
Figure 2 for Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions
Figure 3 for Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions
Figure 4 for Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions
Viaarxiv icon

Language Model Tokenizers Introduce Unfairness Between Languages

May 17, 2023
Aleksandar Petrov, Emanuele La Malfa, Philip H. S. Torr, Adel Bibi

Figure 1 for Language Model Tokenizers Introduce Unfairness Between Languages
Figure 2 for Language Model Tokenizers Introduce Unfairness Between Languages
Figure 3 for Language Model Tokenizers Introduce Unfairness Between Languages
Figure 4 for Language Model Tokenizers Introduce Unfairness Between Languages
Viaarxiv icon

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

May 17, 2023
Songwei Ge, Seungjun Nah, Guilin Liu, Tyler Poon, Andrew Tao, Bryan Catanzaro, David Jacobs, Jia-Bin Huang, Ming-Yu Liu, Yogesh Balaji

Figure 1 for Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
Figure 2 for Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
Figure 3 for Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
Figure 4 for Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
Viaarxiv icon

From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?

May 17, 2023
Jordan Coil, Vered Shwartz

Figure 1 for From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?
Figure 2 for From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?
Figure 3 for From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?
Figure 4 for From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?
Viaarxiv icon

ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance

Apr 06, 2023
Ziyu Guo, Yiwen Tang, Renrui Zhang, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li

Figure 1 for ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
Figure 2 for ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
Figure 3 for ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
Figure 4 for ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
Viaarxiv icon

Downstream Task-Oriented Neural Tokenizer Optimization with Vocabulary Restriction as Post Processing

Apr 21, 2023
Tatsuya Hiraoka, Tomoya Iwakura

Figure 1 for Downstream Task-Oriented Neural Tokenizer Optimization with Vocabulary Restriction as Post Processing
Figure 2 for Downstream Task-Oriented Neural Tokenizer Optimization with Vocabulary Restriction as Post Processing
Figure 3 for Downstream Task-Oriented Neural Tokenizer Optimization with Vocabulary Restriction as Post Processing
Figure 4 for Downstream Task-Oriented Neural Tokenizer Optimization with Vocabulary Restriction as Post Processing
Viaarxiv icon

SimVTP: Simple Video Text Pre-training with Masked Autoencoders

Dec 07, 2022
Yue Ma, Tianyu Yang, Yin Shan, Xiu Li

Figure 1 for SimVTP: Simple Video Text Pre-training with Masked Autoencoders
Figure 2 for SimVTP: Simple Video Text Pre-training with Masked Autoencoders
Figure 3 for SimVTP: Simple Video Text Pre-training with Masked Autoencoders
Figure 4 for SimVTP: Simple Video Text Pre-training with Masked Autoencoders
Viaarxiv icon

Using Language Models on Low-end Hardware

May 03, 2023
Fabian Ziegner, Janos Borst, Andreas Niekler, Martin Potthast

Figure 1 for Using Language Models on Low-end Hardware
Figure 2 for Using Language Models on Low-end Hardware
Viaarxiv icon