← Search

Xingyu Alice Yang

2 accepted papers

2024

Iteration Head: A Mechanistic Study of Chain-of-Thought

NeurIPS 2024poster

Chain-of-Thought (CoT) reasoning is known to improve Large Language Models both empirically and in terms of theoretical approximation power. However, our understanding of the inner workings and conditions of apparition of CoT capabilities remains limited. This paper helps fill this gap by demonstrat…

2024

The Road Less Scheduled

NeurIPS 2024oral

Existing learning rate schedules that do not require specification of the optimization stopping step $T$ are greatly out-performed by learning rate schedules that depend on $T$. We propose an approach that avoids the need for this stopping time by eschewing the use of schedules entirely, while exhib…