2 papers
cs.LG2024
SAMSA: Efficient Transformer for Many Data Modalities
Minh Lenhat, Viet Anh Nguyen, Khoa Nguyen +3
The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training…
cs.LG2024
Sampling Foundational Transformer: A Theoretical Perspective
Viet Anh Nguyen, Minh Lenhat, Khoa Nguyen +3
The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training…