3 papers
cs.IR2026
Controllable and Content-Based Recommendations
Fırat Ãncel, Jihoon Jeong, Emiliano Penaloza +3
Traditional recommendation systems rely on latent (dense) representations, making them difficult to interpret and control. We propose the Controllable and Content-Based Recommendat…
cs.IR2025
Audio Prototypical Network For Controllable Music Recommendation
Fırat Ãncel, Emiliano Penaloza, Haolun Wu +4
Traditional recommendation systems represent user preferences in dense representations obtained through black-box encoder models. While these models often provide strong recommenda…
cs.CL2024
Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
Fırat Ãncel, Matthias Bethge, Beyza Ermis +3
In the last decade, the generalization and adaptation abilities of deep learning models were typically evaluated on fixed training and test distributions. Contrary to traditional d…