2023.04.03 ArXiv精選
關(guān)注領(lǐng)域:
AIGC
3D computer vision learning
Fine-grained learning
GNN
其他
聲明
論文較多,時(shí)間有限,本專(zhuān)欄無(wú)法做文章的講解,只挑選出符合PaperABC研究興趣和當(dāng)前熱點(diǎn)問(wèn)題相關(guān)的論文,如果你的research topic和上述內(nèi)容有關(guān),那本專(zhuān)欄可作為你的論文更新源或Paper reading list.

Paper list:
今日ArXiv共更新85篇
VLP
Towards Flexible Multi-modal Document Models
https://arxiv.org/pdf/2303.18248.pdf

面向文檔數(shù)據(jù)的多模態(tài)模型.
DIME-FM : DIstilling Multimodal and Efficient Foundation Models
https://arxiv.org/pdf/2303.18232.pdf

來(lái)自Meta的工作.探討了如何將large的多模態(tài)模型高效蒸餾給小的foundation model.
CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
https://arxiv.org/pdf/2303.17948.pdf

廈門(mén)大學(xué)發(fā)布的人體climbing數(shù)據(jù)集,算是一個(gè)新坑.
標(biāo)簽: