Da Xiao 0001, Qingye Meng, Shengping Li, Xingyuan Yuan. MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025. OpenReview.net, 2025. [doi]
Abstract is missing.