Ziyue Liu

Orcid: 0000-0001-9538-5350

Affiliations:
  • University of California Santa Barbara, Department of Statistics and Applied Probability, CA, USA


According to our database1, Ziyue Liu authored at least 14 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization.
CoRR, May, 2026

Muon<sup>2</sup>: Boosting Muon via Adaptive Second-Moment Preconditioning.
CoRR, April, 2026

TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training.
CoRR, January, 2026

2025
DeepOHeat-v1: Efficient Operator Learning for Fast and Trustworthy Thermal Simulation and Optimization in 3D-IC Design.
CoRR, April, 2025

Scalable Back-Propagation-Free Training of Optical Physics-Informed Neural Networks.
CoRR, February, 2025

QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Enhanced Operator Learning for Scalable and Ultra-fast Thermal Simulation in 3D-IC Design.
Proceedings of the 30th Asia and South Pacific Design Automation Conference, 2025

2024
Separable Operator Networks.
Trans. Mach. Learn. Res., 2024

Real-Time FJ/MAC PDE Solvers via Tensorized, Back-Propagation-Free Optical PINN Training.
CoRR, 2024

2023
Tensor-Compressed Back-Propagation-Free Training for (Physics-Informed) Neural Networks.
CoRR, 2023

PIFON-EPT: MR-Based Electrical Property Tomography Using Physics-Informed Fourier Networks.
CoRR, 2023

DeepOHeat: Operator Learning-based Ultra-fast Thermal Simulation in 3D-IC Design.
Proceedings of the 60th ACM/IEEE Design Automation Conference, 2023

2022
MR-Based Electrical Property Reconstruction Using Physics-Informed Neural Networks.
CoRR, 2022

TT-PINN: A Tensor-Compressed Neural PDE Solver for Edge Computing.
CoRR, 2022


  Loading...