← Search

Minrui Wang

2 accepted papers

2026

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning

ICML 2026poster

Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively explored depth expansion, width expansion remains significantly understudied, with the few existing methods limited to the early stages of training. However, ex…

Cited by 0SourceScholar
2025

Model Merging in Pre-training of Large Language Models

NeurIPS 2025poster

Model merging has emerged as a promising technique for enhancing large language models, though its application in large-scale pre-training remains relatively unexplored. In this paper, we present a comprehensive investigation of model merging techniques during the pre-training process. Through exten…

Cited by 0SourceScholar