| 2026 | ACL | Decoding Text Spans for Efficient and Accurate Named-Entity Recognition. | Andrea Maracani, Savas zkan, Junyi Zhu, Sinan Mutlu, Mete Ozay |
| 2026 | ACL | 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 |
| 2026 | WACV | Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs. | Sinan Mutlu, Georgios-Fotios Angelis, Savas zkan, Paul Wisbey, Anastasios Drosou, Mete Ozay |
| 2026 | WACV | Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models. | Junyi Zhu, Ruicong Yao, Taha Ceritli, Savas zkan, Matthew B. Blaschko, Eunchung Noh, Jeongwon Min, Cho Jung Min, Mete Ozay |
| 2025 | CVPR | DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching. | Emanuele Aiello, Umberto Michieli, Diego Valsesia, Mete Ozay, Enrico Magli |
| 2025 | CVPR | Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation. | Andrea Maracani, Savas zkan, Sijun Cho, Hyowon Kim, Eunchung Noh, Jeongwon Min, Cho Jung Min, Dookun Park, Mete Ozay |
| 2025 | EMNLP | Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER. | Junyi Zhu, Savas zkan, Andrea Maracani, Sinan Mutlu, Cho Jung Min, Mete Ozay |
| 2025 | EMNLP | Efficient Compositional Multi-tasking for On-device Large Language Models. | Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli |
| 2025 | EMNLP | On-device System of Compositional Multi-tasking in Large Language Models. | Ondrej Bohdal, Konstantinos Theodosiadis, Asterios Mpatziakas, Dimitrios Filippidis, Iro Spyrou, Christos Zonios, Anastasios Drosou, Dimosthenis Ioannidis, Kyeng-Hun Lee, Jijoong Moon, Hyeonmok Ko, Mete Ozay, Umberto Michieli |
| 2025 | EMNLP | 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 |
| 2025 | ICASSP | ValSub: Subsampling Validation Data to Mitigate Forgetting during ASR Personalization. | Haaris Mehmood, Karthikeyan Saravanan, Pablo Peso Parada, David Tuckey, Mete Ozay, Gil Ho Lee, Jungin Lee, Seokyeong Jung |
| 2025 | ICASSP | A Study of Improving The Privacy-Utility Trade-off of Task-specific Models with Learnable Privacy. | Savas zkan, Taha Ceritli, Jeongwon Min, Eunchung Noh, Jung Min Cho, Dookun Park, Mete Ozay |
| 2025 | ICASSP | Hyper-Refinement for Low-Rank Adaptation. | Savas zkan, Taha Ceritli, Jeongwon Min, Eunchung Noh, Jung Min Cho, Dookun Park, Mete Ozay |
| 2025 | ICASSP | persoDA: Personalized Data Augmentation for Personalized ASR. | Pablo Peso Parada, Spyros Fontalis, Md Asif Jalal, Karthikeyan Saravanan, Anastasios Drosou, Mete Ozay, Gil Ho Lee, Jungin Lee, Seokyeong Jung |
| 2025 | ICASSP | Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning. | Kirill Paramonov, Mete Ozay, Eunju Yang, Jijoong Moon, Umberto Michieli |
| 2025 | ICCV | LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation. | Donald Shenaj, Ondrej Bohdal, Mete Ozay, Pietro Zanuttigh, Umberto Michieli |
| 2025 | MMSys | Efficient and Accurate Scene Text Recognition with Cascaded-Transformers. | Savas zkan, Andrea Maracani, Mete Ozay, Hyowon Kim, Sijun Cho, Eunchung Noh, Jeongwon Min, Jung Min Cho |
| 2025 | MMSys | Continual Error Correction on Low-Resource Devices. | Kirill Paramonov, Mete Ozay, Aristeidis Mystakidis, Nikolaos Tsalikidis, Dimitrios Sotos, Anastasios Drosou, Dimitrios Tzovaras, Hyunjun Kim, Kiseok Chang, Sangdok Mo, Namwoong Kim, Woojong Yoo, Ji Joong Moon, Umberto Michieli |
| 2024 | AAAI | HOP to the Next Tasks and Domains for Continual Learning in NLP. | Umberto Michieli, Mete Ozay |
| 2024 | EMNLP | A Study of Parameter Efficient Fine-tuning by Learning to Efficiently Fine-Tune. | Taha Ceritli, Savas zkan, Jeongwon Min, Eunchung Noh, Cho Min, Mete Ozay |
| 2024 | EMNLP | LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models. | Hayder Elesedy, Pedro M. Esperana, Silviu Vlad Oprea, Mete Ozay |
| 2024 | EMNLP | Model Merging and Safety Alignment: One Bad Model Spoils the Bunch. | Hasan Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, Mete Ozay |
| 2024 | ICASSP | Deep Neural Network Models Trained with a Fixed Random Classifier Transfer Better Across Domains. | Hafiz Tiomoko Ali, Umberto Michieli, Ji Joong Moon, Daehyun Kim, Mete Ozay |
| 2024 | ICASSP | FFT-Based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images. | Elena Camuffo, Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay |
| 2024 | ICASSP | Object-Conditioned Bag of Instances for Few-Shot Personalized Instance Recognition. | Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay |
| 2024 | ICASSP | Joint Embedding Learning and Latent Subspace Probing for Cross-Domain Few-Shot Keyword Spotting. | Mete Ozay |
| 2024 | ICASSP | Texture and Normal Map Estimation for 3D Face Reconstruction. | Savas zkan, Mete Ozay, Tom Robinson |
| 2024 | IROS | Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection. | Francesco Barbato, Umberto Michieli, Jijoong Moon, Pietro Zanuttigh, Mete Ozay |
| 2024 | IROS | Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics. | Elena Camuffo, Umberto Michieli, Simone Milani, Jijoong Moon, Mete Ozay |
| 2024 | IROS | Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search. | Kirill Paramonov, Jia-Xing Zhong, Umberto Michieli, Jijoong Moon, Mete Ozay |
| 2024 | MMSys | A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation. | Francesco Barbato, Umberto Michieli, Mehmet Kerim Yucel, Pietro Zanuttigh, Mete Ozay |
| 2023 | CVPR | Data-Free Model Pruning at Initialization via Expanders. | James Stewart, Umberto Michieli, Mete Ozay |
| 2023 | Interspeech | A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization. | Edward Fish, Umberto Michieli, Mete Ozay |
| 2023 | Interspeech | On-Device Speaker Anonymization of Acoustic Embeddings for ASR based on Flexible Location Gradient Reversal Layer. | Md Asif Jalal, Pablo Peso Parada, Jisi Zhang, Mete Ozay, Karthikeyan Saravanan, Myoungji Han, Jungin Lee, Seokyeong Jung |
| 2023 | Interspeech | Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics. | Umberto Michieli, Pablo Peso Parada, Mete Ozay |
| 2023 | IROS | Online Continual Learning for Robust Indoor Object Recognition. | Umberto Michieli, Mete Ozay |
| 2023 | WACV | LRA&LDRA: Rethinking Residual Predictions for Efficient Shadow Detection and Removal. | Mehmet Kerim Ycel, Valia Dimaridou, Bruno Manganelli, Mete Ozay, Anastasios Drosou, Albert Sa-Garriga |
| 2022 | CVPR | Bring Evanescent Representations to Life in Lifelong Class Incremental Learning. | Marco Toldo, Mete Ozay |
| 2022 | ICLR | Feature Kernel Distillation. | Bobby He, Mete Ozay |
| 2022 | ICML | Exploring the Gap between Collapsed & Whitened Features in Self-Supervised Learning. | Bobby He, Mete Ozay |
| 2022 | Interspeech | FedNST: Federated Noisy Student Training for Automatic Speech Recognition. | Haaris Mehmood, Agnieszka Dobrowolska, Karthikeyan Saravanan, Mete Ozay |
| 2022 | Interspeech | pMCT: Patched Multi-Condition Training for Robust Speech Recognition. | Pablo Peso Parada, Agnieszka Dobrowolska, Karthikeyan Saravanan, Mete Ozay |
| 2021 | BMVC | A Mixed Quantization Network for Efficient Mobile Inverse Tone Mapping. | Juan Borrego-Carazo, Mete Ozay, Frederik Laboyrie, Paul Wisbey |
| 2021 | CVPR | Are All Users Treated Fairly in Federated Learning Systems? | Umberto Michieli, Mete Ozay |
| 2021 | IJCNN | A New Approach to Design Symmetry Invariant Neural Networks. | Piotr Kicki, Piotr Skrzypczynski, Mete Ozay |
| 2019 | WACV | Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries. | Junjie Hu, Mete Ozay, Yan Zhang, Takayuki Okatani |
| 2018 | CVPR | Feature Quantization for Defending Against Distortion of Images. | Zhun Sun, Mete Ozay, Yan Zhang, Xing Liu, Takayuki Okatani |
| 2018 | ICML | Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search. | Masanori Suganuma, Mete Ozay, Takayuki Okatani |
| 2018 | ICPR | Deep Structured Energy-Based Image Inpainting. | Fazil Altinel, Mete Ozay, Takayuki Okatani |
| 2017 | ICCV | Truncating Wide Networks Using Binary Tree Architectures. | Yan Zhang, Mete Ozay, Shuohao Li, Takayuki Okatani |
| 2016 | ECCV | Design of Kernels in Convolutional Neural Networks for Image Classification. | Zhun Sun, Mete Ozay, Takayuki Okatani |
| 2016 | ICPR | Integrating deep features for material recognition. | Yan Zhang, Mete Ozay, Xing Liu, Takayuki Okatani |
| 2015 | ICCV | Compositional Hierarchical Representation of Shape Manifolds for Classification of Non-manifold Shapes. | Mete Ozay, mit Rusen Aktas, Jeremy L. Wyatt, Ales Leonardis |
| 2014 | ECCV | A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model. | mit Rusen Aktas, Mete Ozay, Ales Leonardis, Jeremy L. Wyatt |
| 2014 | ICPR | Modeling the Brain Connectivity for Pattern Analysis. | Itir Onal, Emre Aksan, Burak Velioglu, Orhan Firat, Mete Ozay, Ilke ztekin, Fatos T. Yarman-Vural |
| 2014 | ICPR | Semi-supervised Segmentation Fusion of Multi-spectral and Aerial Images. | Mete Ozay |
| 2014 | ICRA | A hierarchical approach for joint multi-view object pose estimation and categorization. | Mete Ozay, Krzysztof Walas, Ales Leonardis |
| 2013 | BIBE | An information theoretic approach to classify cognitive states using fMRI. | Itir Onal, Mete Ozay, Orhan Firat, Ilke ztekin, Fatos T. Yarman-Vural |
| 2013 | ICIP | Mesh learning for object classification using fMRI measurements. | Omer Ekmekci, Orhan Firat, Mete Ozay, Ilke ztekin, Fatos T. Yarman-Vural, Uygar ztekin |
| 2013 | ICIP | Fusion of image segmentation algorithms using consensus clustering. | Mete Ozay, Fatos T. Yarman-Vural, Sanjeev R. Kulkarni, H. Vincent Poor |
| 2012 | IGARSS | Automatic building detection with feature space fusion using ensemble learning. | aglar Senaras, Baris Yksel, Mete Ozay, Fatos T. Yarman-Vural |
| 2009 | ICIP | A new decision fusion technique for image classification. | Mete Ozay, Fatos Tnay Yarman Vural |