collaborators

6 papers

cs.LG2025

Softmax Linear: Transformers may learn to classify in-context by kernel gradient descent

Sara Dragutinović, Andrew M. Saxe, Aaditya K. Singh

The remarkable ability of transformers to learn new concepts solely by reading examples within the input prompt, termed in-context learning (ICL), is a crucial aspect of intelligen…

cs.LG2025

Distinct Computations Emerge From Compositional Curricula in In-Context Learning

Jin Hwa Lee, Andrew K. Lampinen, Aaditya K. Singh +1

In-context learning (ICL) research often considers learning a function in-context through a uniform sample of input-output pairs. Here, we investigate how presenting a compositiona…

cs.CL2025

The broader spectrum of in-context learning

Andrew Kyle Lampinen, Stephanie C. Y. Chan, Aaditya K. Singh +1

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervis…

cs.LG2025

Training Dynamics of In-Context Learning in Linear Attention

Yedi Zhang, Aaditya K. Singh, Peter E. Latham +1

While attention-based models have demonstrated the remarkable ability of in-context learning (ICL), the theoretical understanding of how these models acquired this ability through…

cs.LG2025

Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

Aaditya K. Singh, Ted Moskovitz, Sara Dragutinovic +3

In-context learning (ICL) is a powerful ability that emerges in transformer models, enabling them to learn from context without weight updates. Recent work has established emergent…

cs.LG2024

HARP: A challenging human-annotated math reasoning benchmark

Albert S. Yue, Lovish Madaan, Ted Moskovitz +2

Math reasoning is becoming an ever increasing area of focus as we scale large language models. However, even the previously-toughest evals like MATH are now close to saturated by f…