Principal Scientist at A*STAR - Agency for Science, Technology and Research
Atsushi Nitanda is a Principal Scientist at A*STAR's Centre for Frontier AI Research.
How media typically covers Atsushi Nitanda
Atsushi Nitanda as author
A theoretical framework proves that nonlinear residual transformers perform in-context learning via vector arithmetic, with provable convergence and generalization guarantees including robustness to concept recombination.
“Author of the paper on in-context vector arithmetic”