Derives transformer-like dual-filter inference layers from first-principles optimal control on nonlinear discrete and linear Gaussian sequence models.
Causal interpretation of self-attention in pre-trained transformers.Advances in Neural Information Processing Systems, 36:31450– 31465, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Transformer-like Inference from Optimal Control
Derives transformer-like dual-filter inference layers from first-principles optimal control on nonlinear discrete and linear Gaussian sequence models.