3 papers
cs.LG2026
Spatial Induction Heads: In-Context Learning of Multidimensional Cellular Automata
Kimia Kazemian, Menghan Xu, John Thickstun +1
Induction heads provide a mechanistic account of in-context learning in sequential data, but existing theory largely assumes that the context relevant to a prediction forms a conti…
cs.LG2025
Benchmark Datasets for Lead-Lag Forecasting on Social Platforms
Kimia Kazemian, Zhenzhen Liu, Yangfanyu Yang +9
Social and collaborative platforms emit multivariate time-series traces in which early interactions -- such as views, likes, or downloads -- are followed, sometimes months or years…
cs.LG2024
Random Features Approximation for Control-Affine Systems
Kimia Kazemian, Yahya Sattar, Sarah Dean
Modern data-driven control applications call for flexible nonlinear models that are amenable to principled controller synthesis and realtime feedback. Many nonlinear dynamical syst…