search

cambrian-mllm / cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
https://cambrian-mllm.github.io/
Apache License 2.0
1.4k stars 88 forks source link

Question About Table 4 #23

Closed homiec closed 2 days ago

homiec commented 2 days ago

Thank you for your great work.

Regarding the experiments in Table 4, I would like to ask if there are any direct comparisons to the experimental results of LLaVA (Vicuna-1.5-7B base LLM)? I'm curious about the experimental results of SVA compared with a single vision encoder?

penghao-wu commented 2 days ago

The results in Table 4 can be directly compared with Table 12 with single vision encoder.

homiec commented 2 days ago

Thanks