COMM (which has already been on Arxiv on 2023.10 https://arxiv.org/pdf/2310.08825.pdf) already proposed to merge the features of CLIP and DINOv2 to realize MLLM, maybe this paper should cite this reference.

FudanNLPLAB / MouSi

Apache License 2.0

65 stars 0 forks source link

COMM (which has already been on Arxiv on 2023.10 https://arxiv.org/pdf/2310.08825.pdf) already proposed to merge the features of CLIP and DINOv2 to realize MLLM, maybe this paper should cite this reference. #4

Open YuchenLiu98 opened 2 weeks ago

YuchenLiu98 commented 2 weeks ago

Many thanks for your excellent work! COMM (which has already been on Arxiv on 2023.10 https://arxiv.org/pdf/2310.08825.pdf) already proposed to merge the features of CLIP and DINOv2 to realize MLLM, maybe this paper should cite this reference.

cnxupupup commented 2 weeks ago

Thank you for your insightful suggestion and valuable feedback! We will cite this important reference in the related work section of our future versions.