For a full list, see my Google Scholar.


Preprints

Machine-Learning Adaptivity, DFT-Level Accuracy, and Semi-Empirical Quantum-Chemistry Speed with Neural-Network Extended Tight-Binding
Yufan Xia, Albert Thie, Joshua Soon, Giuseppe Maria Junior Barca
ChemRxiv, 2025
[Preprint]

NN-xTB augments GFN2-xTB with neural-network-predicted parameter shifts, achieving DFT-like accuracy (WTMAD-2 of 4 kcal/mol on GMTKN55) at near semi-empirical cost.


Conference Papers

Machine-Learning-Driven Runtime Optimization of BLAS Level 3 on Modern Multi-Core Systems
Yufan Xia, Giuseppe Maria Junior Barca
IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2024
[Poster] [Demo] | Best Poster Award

ADSALA uses ML to predict optimal thread counts for all BLAS Level 3 operations, achieving 1.5-3.0x speedups on Intel and AMD multi-core systems.

A Machine Learning Approach Towards Runtime Optimisation of Matrix Multiplication
Yufan Xia, Marco De La Pierre, Amanda S Barnard, Giuseppe Maria Junior Barca
IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2023
[Paper]

Proof-of-concept for the ADSALA library: on-the-fly ML-based thread selection for GEMM, tested on Intel Cascade Lake and AMD architectures.


Journal Papers

Manuscripts in preparation.