ELLIS header
University of Stuttgart Logo
Max Planck Institute for Intelligent Systems Logo

On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation

Nghiem T. Diep, Huy Nguyen, Chau Nguyen, Minh Le, Duy M. H. Nguyen, Daniel Sonntag, Mathias Niepert, Nhat Ho

, , 2025.


Abstract


Links


BibTeX

@article{diep2025zeroinitializedattentionoptimalprompt, title = {On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation}, author = {Diep, Nghiem T. and Nguyen, Huy and Nguyen, Chau and Le, Minh and Nguyen, Duy M. H. and Sonntag, Daniel and Niepert, Mathias and Ho, Nhat}, year = {2025}, eprint = {2502.03029}, archiveprefix = {arXiv}, primaryclass = {cs.LG}, url = {https://arxiv.org/abs/2502.03029} }