Picture for Amita Kamath

Amita Kamath

Matryoshka Query Transformer for Large Vision-Language Models

Add code
May 29, 2024
Figure 1 for Matryoshka Query Transformer for Large Vision-Language Models
Figure 2 for Matryoshka Query Transformer for Large Vision-Language Models
Figure 3 for Matryoshka Query Transformer for Large Vision-Language Models
Figure 4 for Matryoshka Query Transformer for Large Vision-Language Models
Viaarxiv icon

What's "up" with vision-language models? Investigating their struggle with spatial reasoning

Add code
Oct 30, 2023
Viaarxiv icon

Text encoders are performance bottlenecks in contrastive vision-language models

Add code
May 24, 2023
Figure 1 for Text encoders are performance bottlenecks in contrastive vision-language models
Figure 2 for Text encoders are performance bottlenecks in contrastive vision-language models
Figure 3 for Text encoders are performance bottlenecks in contrastive vision-language models
Figure 4 for Text encoders are performance bottlenecks in contrastive vision-language models
Viaarxiv icon

Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models

Add code
Mar 28, 2023
Figure 1 for Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Figure 2 for Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Figure 3 for Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Figure 4 for Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Viaarxiv icon

Webly Supervised Concept Expansion for General Purpose Vision Models

Add code
Feb 04, 2022
Figure 1 for Webly Supervised Concept Expansion for General Purpose Vision Models
Figure 2 for Webly Supervised Concept Expansion for General Purpose Vision Models
Figure 3 for Webly Supervised Concept Expansion for General Purpose Vision Models
Figure 4 for Webly Supervised Concept Expansion for General Purpose Vision Models
Viaarxiv icon

Towards General Purpose Vision Systems

Add code
Apr 01, 2021
Figure 1 for Towards General Purpose Vision Systems
Figure 2 for Towards General Purpose Vision Systems
Figure 3 for Towards General Purpose Vision Systems
Figure 4 for Towards General Purpose Vision Systems
Viaarxiv icon

Selective Question Answering under Domain Shift

Add code
Jun 16, 2020
Figure 1 for Selective Question Answering under Domain Shift
Figure 2 for Selective Question Answering under Domain Shift
Figure 3 for Selective Question Answering under Domain Shift
Figure 4 for Selective Question Answering under Domain Shift
Viaarxiv icon