Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

@article{pub17525,
    author = {



Nguyen, Gia-Binh
 and 



Ho, Trong-Bao
 and 



Ha, Thien-Loc
 and 



Vo, Khoa
 and 



Møller, Philip Lund
 and 



Nguyen, Quang T.
 and 



Dinh, Long
 and 



Luu, Tung M.
 and 



Dam, Tuan Quang
 and 



Duong, Vu
 and 



Le, Trung
 and 



Bui, Nghi D. Q.
 and 



Vu, Minh
 and 



Le, Tran Nguyen
 and 



Le, An Thai
 and 



Le, Hong Anh
 and 



Sonntag, Daniel
 and 



Zou, James
 and 



Peters, Jan
 and 



Nguyen, Duy M. H.
 and 



Vien, Ngo Anh
},
    title = {Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think},
    year = {2026},
    volume = {abs/2606.20246},
    pages = {1--16},
    journal = {Computing Research Repository eprint Journal (CoRR)},
    publisher = {arXiv}
}