Author

Mete Ozay

Observed name: Ozay, Mete

ORCID: 0000-0002-2515-1062

Observed ORCID: 0000-0002-2515-1062

OpenAlex ID: A5123882727

Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation

2025 · Andrea Maracani, Savas Ozkan, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 6

PDF

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

2026 · Junyi Zhu, Ruicong Yao, et al. · IEEE Winter Conference on Applications of Computer Vision · 1

Efficient and Accurate Scene Text Recognition with Cascaded-Transformers

2025 · Savas Ozkan, Andrea Maracani, et al. · ACM Multimedia Systems Conference (MMSys) · 1

Feature-Space Generative Models for One-Shot Class-Incremental Learning

2026 · Jack Foster, Kirill Paramonov, et al. · Proceedings - International Conference on Image Processing

PDF

Improving Privacy-Utility Trade-Off with Learnable Privacy Mechanism in Machine Learning Tasks

2026 · Savas Ozkan, Sinan Mutlu, et al. · Proceedings - International Conference on Image Processing

DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation

2026 · Hosseini, Peyman, Bohdal, Ondrej, et al. · arXiv (Cornell University)

PDF

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

2026 · Association for Computational Linguistics 2026, Bohdal, Ondrej, et al. · Underline Science Inc.

Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

2026 · Association for Computational Linguistics 2026, Maracani, Andrea, et al. · Underline Science Inc.

DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning

2026 · Mehmood, Haaris, Tatsis, Giorgos, et al. · arXiv (Cornell University)

PDF

DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models

2026 · Mehmood, Haaris, Xu, Jie, et al. · arXiv (Cornell University)

PDF

Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation

2026 · Xu, Jie, Mehmood, Haaris, et al. · arXiv (Cornell University)

PDF

Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

2026 · Maracani, Andrea, Ozkan, Savas, et al. · arXiv (Cornell University)

PDF

DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning

2026 · Mehmood, Haaris, Tatsis, Giorgos, et al. · Zenodo (CERN European Organization for Nuclear Research)

Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs

2026 · Sinan Mutlu, Georgios F. Angelis, et al. · IEEE Winter Conference on Applications of Computer Vision

Diffusion Alignment Beyond KL: Variance Minimisation as Effective Policy Optimiser

2026 · Ou, Zijing, Si, Jacob, et al. · arXiv (Cornell University)

PDF

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

2026 · Bohdal, Ondrej, Ceritli, Taha, et al. · arXiv (Cornell University)

PDF

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

2026 · Bohdal, Ondrej, Saha, Pramit, et al. · arXiv (Cornell University)

PDF

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

2026 · Peyman Hosseini, Ondrej Bohdal, et al. · Transactions of the Association for Computational Linguistics

Geometrically Consistent Multi-view Scene Generation from Freehand Sketches

2026 · Ahmed Bourouis, Savas Ozkan, et al. · Lecture notes in computer science

PDF

Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

2026 · Andrea Maracani, Savas Ozkan, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

PDF

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

2025 · Zhu, Junyi, Yao, Ruicong, et al. · Lirias

Efficient 3D Full-Body Motion Generation from Sparse Tracking Inputs with Temporal Windows

2025 · Angelis, Georgios Fotios, Ozkan, Savas, et al. · arXiv (Cornell University)

PDF

Works count: 22

Citation count: 8

H-index: 1

I10-index: