2 papers
math.OC2025
Achieving Universal Approximation and Universal Interpolation via Nonlinearity of Control Families
Yongqiang Cai, Yifei Duan
A significant connection exists between the controllability of dynamical systems and the approximation capabilities of neural networks, where residual networks and vanilla feedforw…
cs.CL2025
Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition
Yifei Duan, Raphael Shang, Deng Liang +1
Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neu…