srymaker

STAGE 1 TRAINING

1

Thank you for your great work! In the stage 1 training mentioned in the paper, is the input of llm images and text，because the description ‘After the pretraining stage, the...

About the ID interpolation code

3

Thank you for your greate job! I wanna know the operating principle of ID interpolation. Can you provide some pseudocode or descriptive text？

About the raw token lens

2

Thanks for your great work! I wanna know how you compute the raw token lens, just like the 729 in the image.

Problem about the recall@20

2

What a great benchmark! I have a problem about the recall@20 metric. In the article, you said that recall@k = 20 is used, and the VSS + LLM Reranker baseline...