collaborators

5 papers

cs.LG2026

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

Lin Huang, Chengxiang Huang, Ziang Wang +7

Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems. However, mainstream architectures face critical scalability bottlene…

cs.LG2026

Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force Fields

Yunyang Li, Lin Huang, Luojia Xia +2

Generative models for 3D molecular conformations must respect Euclidean symmetries and concentrate probability mass on thermodynamically favorable, mechanically stable structures.…

cs.LG2025

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products

Yunyang Li, Lin Huang, Zhihao Ding +10

Equivariant Graph Neural Networks (EGNNs) have demonstrated significant success in modeling microscale systems, including those in chemistry, biology and materials science. However…

cs.LG2025

Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity

Erpai Luo, Xinran Wei, Lin Huang +7

Hamiltonian matrix prediction is pivotal in computational chemistry, serving as the foundation for determining a wide range of molecular properties. While SE(3) equivariant graph n…

physics.chem-ph2025

Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems

Yunyang Li, Zaishuo Xia, Lin Huang +8

Density Functional Theory (DFT) is a pivotal method within quantum chemistry and materials science, with its core involving the construction and solution of the Kohn-Sham Hamiltoni…