3 papers
cs.CL2026
REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling
Devrim Çavuşoğlu, Emre Akbaş
Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models reach 32K tokens only through…
cs.CL2024
A multi-level multi-label text classification dataset of 19th century Ottoman and Russian literary and critical texts
Gokcen Gokceoglu, Devrim Cavusoglu, Emre Akbas +1
This paper introduces a multi-level, multi-label text classification dataset comprising over 3000 documents. The dataset features literary and critical texts from 19th-century Otto…
cs.CV2024
DroBoost: An Intelligent Score and Model Boosting Method for Drone Detection
Ogulcan Eryuksel, Kamil Anil Ozfuttu, Fatih Cagatay Akyon +4
Drone detection is a challenging object detection task where visibility conditions and quality of the images may be unfavorable, and detections might become difficult due to comple…