ziqipang / LM4VisualEncoding

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

https://arxiv.org/abs/2310.12973

ziqipang/LM4VisualEncoding Issues

Sharing experiments in lung sound abnormal detection, and suggestion, add random initialization weights of LLM layer experiments.
Closed 6 months ago
2D VQA and Image-Text Retrieval
Updated 6 months ago1
Some questions about ViT-Small-LLaMA
Closed 7 months ago1
About importing pre-trained weights for the LLaMA model
Closed 7 months ago2
Is there any ablation studies on the number of LLM layers inserted between the visual encoder and classifiers?
Closed 8 months ago1