He, Tianyu
28 publications
NeurIPS
2024
Learning to Grok: Emergence of In-Context Learning and Skill Composition in Modular Arithmetic Tasks
ICMLW
2024
Learning to Grok: Emergence of In-Context Learning and Skill Composition in Modular Arithmetic Tasks
NeurIPSW
2024
Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos
NeurIPS
2023
Critical Initialization of Wide and Deep Neural Networks Using Partial Jacobians: General Theory and Applications