3 papers
cs.CV2026
Matryoshka Gaussian Splatting
Zhilin Guo, Boqiao Zhang, Hakan Aktas +11
The ability to render scenes at adjustable fidelity from a single model, known as level of detail (LoD), is crucial for practical deployment of 3D Gaussian Splatting (3DGS). Existi…
cs.LG2025
Sheaves Reloaded: A Directional Awakening
Stefano Fiorini, Hakan Aktas, Iulia Duta +4
Sheaf Neural Networks (SNNs) represent a powerful generalization of Graph Neural Networks (GNNs) that significantly improve our ability to model complex relational data. While dire…
cs.AR2023
Design optimization for high-performance computing using FPGA
Murat Isik, Kayode Inadagbo, Hakan Aktas
Reconfigurable architectures like Field Programmable Gate Arrays (FPGAs) have been used for accelerating computations in several domains because of their unique combination of flex…