LM4VisualEncoding icon indicating copy to clipboard operation
LM4VisualEncoding copied to clipboard

verified publisher icon ziqipang
→

Metadata

[ICLR 2024 (Spotlight)] "Frozen Transformers in Language Models are Effective Visual Encoder Layers"

Results 3 LM4VisualEncoding issues
Sort by recently updated
recently updated
newest added

2D VQA and Image-Text Retrieval

3 comment

Hope to access the 2D VQA and Image-Text Retrieval Task

xvolica avatar xvolica

About Motion Forecasting

Thanks for your excellent work, I am wondering when the code for motion forecasting will be released?

Zbozhou avatar Zbozhou

Influence of ViT

1 comment

Thank you for your insightful discovery. I have a question regarding the influence of ViT. If you use a pre-trained ViT and freeze it, then only train the added adapter...

jiazhen-code avatar jiazhen-code

← Metadata

194
Stars
5
Forks
Watchers

Owner

verified publisher icon ziqipang

Metadata

[ICLR 2024 (Spotlight)] "Frozen Transformers in Language Models are Effective Visual Encoder Layers"

Back