3 papers
cs.LG2026
MoRE: Mixture of Reused Experts
Eric S. Qiu, Utku Umur Acikalin, Justin Lovelace +4
Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly with the number of experts. Rec…
cs.IR2022
Patent Search Using Triplet Networks Based Fine-Tuned SciBERT
Utku Umur Acikalin, Mucahid Kutlu
In this paper, we propose a novel method for the prior-art search task. We fine-tune SciBERT transformer model using Triplet Network approach, allowing us to represent each patent…
cs.NE2022
Multilevel Memetic Hypergraph Partitioning with Greedy Recombination
Utku Umur Acikalin, Bugra Caskurlu
The Hypergraph Partitioning (HGP) problem is a well-studied problem that finds applications in a variety of domains. The literature on the HGP problem has heavily focused on develo…