1 citations · 1 across the 1 of their papers we have counts for
3 papers
cs.CV2024★ 1 cited
Multi LoRA Meets Vision: Merging multiple adapters to create a multi task model
Ege Kesim, Selahattin Serdar Helli
Parameter efficient finetuning (PEFT) methods are widely used in LLMs and generative models in computer vision. Especially one can use multiple of these during inference to change…
cs.LG2023
A Comparison of Time-based Models for Multimodal Emotion Recognition
Ege Kesim, Selahattin Serdar Helli, Sena Nur Cavsak
Emotion recognition has become an important research topic in the field of human-computer interaction. Studies on sound and videos to understand emotions focused mainly on analyzin…
cs.CL2023
Named entity recognition in resumes
Ege Kesim, Aysu Deliahmetoglu
Named entity recognition (NER) is used to extract information from various documents and texts such as names and dates. It is important to extract education and work experience inf…