activity
20242026
collaborators

6 papers

math.NA2026

Sharp Sobolev Sandwich and Approximation Rates of Radon-Domain Ridge Integral Spaces for ReLU Networks

Juncai He, Zitong Tian

We develop the space and approximation theory for shallow neural networks with activations. The central object is the Radon-domain space $\mathcal{R}L…

cs.LG2026

Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations

Shuang Chen, Juncai He, Xue-Cheng Tai

We introduce an abstract neural flow framework for neural networks and neural operators. The framework contains two continuous-depth models, namely neural flows with composition an…

math.NA2026

Divergence-free Linearized Neural Networks: Integral Representation and Optimal Approximation Rates

Juncai He, Xinliang Liu, Zitong Tian

This paper studies the numerical approximation of divergence-free vector fields by linearized shallow neural networks, also referred to as random feature models or finite neuron sp…

cs.CL2025

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion

Jianqing Zhu, Huang Huang, Zhihang Lin +18

This paper addresses the critical need for democratizing large language models (LLM) in the Arab world, a region that has seen slower progress in developing models comparable to st…

cs.LG2025

Self-composing neural operators for high-frequency and multiscale PDE surrogates

Juncai He, Xinliang Liu, Jinchao Xu

Addressing the computational challenges of high-frequency and multiscale partial differential equations (PDEs), this work introduces a self-composing neural operator (SC-NO) framew…

cs.CL2024

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

Juhao Liang, Zhenyang Cai, Jianqing Zhu +9

The alignment of large language models (LLMs) is critical for developing effective and safe language models. Traditional approaches focus on aligning models during the instruction…