Picture for Joan Nwatu

Joan Nwatu

CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

Jun 10, 2024
Viaarxiv icon

Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost

Add code
Mar 12, 2024
Figure 1 for Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost
Figure 2 for Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost
Figure 3 for Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost
Figure 4 for Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost
Viaarxiv icon

Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models

Add code
Nov 09, 2023
Figure 1 for Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models
Figure 2 for Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models
Figure 3 for Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models
Figure 4 for Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models
Viaarxiv icon

A PhD Student's Perspective on Research in NLP in the Era of Very Large Language Models

May 21, 2023
Viaarxiv icon