Taha Ceritli

According to our database, Taha Ceritli authored at least 19 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Diffusion Alignment Beyond KL: Variance Minimisation as Effective Policy Optimiser.

Zijing Ou, Jacob Si, Junyi Zhu, Ondrej Bohdal, Mete Ozay, Taha Ceritli, Yingzhen Li

CoRR, February, 2026

Clustering-driven Memory Compression for On-device Large Language Models.

Ondrej Bohdal, Pramit Saha, Umberto Michieli, Mete Ozay, Taha Ceritli

CoRR, January, 2026

Data-driven Clustering and Merging of Adapters for On-device Large Language Models.

Ondrej Bohdal, Taha Ceritli, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli

CoRR, January, 2026

Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models.

Junyi Zhu, Ruicong Yao, Taha Ceritli, Savas Özkan, Matthew B. Blaschko, Eunchung Noh, Jeongwon Min, Cho Jung Min, Mete Ozay

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

K-Merge: Online Continual Merging of Adapters for On-device Large Language Models.

Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay, Pietro Zanuttigh, Umberto Michieli

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

MemLoRA: Distilling Expert Adapters for On-Device Memory Systems.

Massimo Bini, Ondrej Bohdal, Umberto Michieli, Zeynep Akata, Mete Ozay, Taha Ceritli

CoRR, December, 2025

CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models.

Peyman Hosseini, Ondrej Bohdal, Taha Ceritli, Ignacio Castro, Matthew Purver, Mete Ozay, Umberto Michieli

CoRR, November, 2025

Unlocking the Value of Decentralized Data: A Federated Dual Learning Approach for Model Aggregation.

Junyi Zhu, Ruicong Yao, Taha Ceritli, Savas Özkan, Matthew B. Blaschko, Eunchung Noh, Jeongwon Min, Cho Jung Min, Mete Ozay

CoRR, March, 2025

Hyper-Refinement for Low-Rank Adaptation.

Savas Özkan, Taha Ceritli, Jeongwon Min, Eunchung Noh, Jung Min Cho, Dookun Park, Mete Ozay

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

A Study of Improving The Privacy-Utility Trade-off of Task-specific Models with Learnable Privacy.

Savas Özkan, Taha Ceritli, Jeongwon Min, Eunchung Noh, Jung Min Cho, Dookun Park, Mete Ozay

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging.

Taha Ceritli, Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation.

Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud, Taha Ceritli, Hayder Elesedy, Mete Ozay, Peter Richtárik

CoRR, 2024

A Study of Parameter Efficient Fine-tuning by Learning to Efficiently Fine-Tune.

Taha Ceritli, Savas Özkan, Jeongwon Min, Eunchung Noh, Cho Min, Mete Ozay

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023

AI Assistants: A Framework for Semi-Automated Data Wrangling.

Tomas Petricek, Gerrit J. J. van den Burg, Alfredo Nazábal, Taha Ceritli, Ernesto Jiménez-Ruiz, Christopher K. I. Williams

IEEE Trans. Knowl. Data Eng., September, 2023

Synthesizing Mixed-type Electronic Health Records using Diffusion Models.

Taha Ceritli, Ghadeer O. Ghosheh, Vinod Kumar Chauhan, Tingting Zhu, Andrew P. Creagh, David A. Clifton

CoRR, 2023

2022

Mixture of Input-Output Hidden Markov Models for Heterogeneous Disease Progression Modeling.

Taha Ceritli, Andrew P. Creagh, David A. Clifton

Proceedings of the IEEE-EMBS International Conference on Biomedical and Health Informatics, 2022

2021

Identifying the Units of Measurement in Tabular Data.

Taha Ceritli, Christopher K. I. Williams

CoRR, 2021

ptype-cat: Inferring the Type and Values of Categorical Variables.

Taha Ceritli, Christopher K. I. Williams

CoRR, 2021

2020

ptype: probabilistic type inference.

Taha Ceritli, Christopher K. I. Williams, James Geddes

Data Min. Knowl. Discov., 2020