Mete Ozay

Venues

Frequent coauthors

Papers

1. Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
   ACL 2026 ·

   Andrea Maracani

   DBLP profile ↗ORCID search ↗
2. Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models
   WACV 2026 ·

   Junyi Zhu

   DBLP profile ↗ORCID search ↗
3. K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
   ACL 2026 ·

   Donald Shenaj

   DBLP profile ↗ORCID search ↗
4. Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs
   WACV 2026 ·

   Sinan Mutlu

   DBLP profile ↗ORCID search ↗
5. Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
   CVPR 2025 ·

   Andrea Maracani

   DBLP profile ↗ORCID search ↗
6. DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
   CVPR 2025 ·

   Emanuele Aiello

   DBLP profile ↗ORCID search ↗
7. Efficient Compositional Multi-tasking for On-device Large Language Models
   EMNLP 2025 ·

   Ondrej Bohdal

   DBLP profile ↗ORCID search ↗
8. HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging
   EMNLP 2025 ·

   Taha Ceritli

   DBLP profile ↗ORCID search ↗
9. LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
   ICCV 2025 ·

   Donald Shenaj

   DBLP profile ↗ORCID search ↗
10. Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER
    EMNLP 2025 ·

    Junyi Zhu

    DBLP profile ↗ORCID search ↗
11. On-device System of Compositional Multi-tasking in Large Language Models
    EMNLP 2025 ·

    Ondrej Bohdal

    DBLP profile ↗ORCID search ↗
12. A Study of Parameter Efficient Fine-tuning by Learning to Efficiently Fine-Tune
    EMNLP 2024 ·

    Taha Ceritli

    DBLP profile ↗ORCID search ↗
13. Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection
    IROS 2024 ·

    Francesco Barbato

    DBLP profile ↗ORCID search ↗
14. Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics
    IROS 2024 ·

    Elena Camuffo

    DBLP profile ↗ORCID search ↗
15. HOP to the Next Tasks and Domains for Continual Learning in NLP
    AAAI 2024 ·

    Umberto Michieli

    DBLP profile ↗ORCID search ↗
16. LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models
    EMNLP 2024 ·

    Hayder Elesedy

    DBLP profile ↗ORCID search ↗
17. Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
    EMNLP 2024 ·

    Hasan Hammoud

    DBLP profile ↗ORCID search ↗
18. Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search
    IROS 2024 ·

    Kirill Paramonov

    DBLP profile ↗ORCID search ↗