2 papers
cs.LG2026
One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-Thought
Lyumin Wu, Yuan Cao
Chain-of-Thought (CoT) enables transformers to solve complex reasoning tasks by generating intermediate reasoning steps. Despite strong empirical success, the mechanisms by which s…
cs.LG2026
Looped Transformers with Layer Normalization Provably Learn the Power Method
Lyumin Wu, Chenyang Zhang, Yuan Cao
Transformers have achieved remarkable success across a wide range of applications, and a growing body of work suggests that part of their strength comes from their ability to learn…