"attention approximation" Papers
2 papers found
Conference
Streaming Attention Approximation via Discrepancy Theory
Ekaterina Kochetkova, Kshiteej Jitesh Sheth, Insu Han et al.
NEURIPS 2025spotlightarXiv:2502.07861
2
citations
PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels
Praneeth Kacham, Vahab Mirrokni, Peilin Zhong
ICML 2024arXiv:2310.01655
23
citations