Mete Ozay

11

Papers

7

Total Citations

Papers (11)

LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation

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

HOP to the Next Tasks and Domains for Continual Learning in NLP

Feature Quantization for Defending Against Distortion of Images

Bring Evanescent Representations to Life in Lifelong Class Incremental Learning

Compositional Hierarchical Representation of Shape Manifolds for Classification of Non-Manifold Shapes

Truncating Wide Networks Using Binary Tree Architectures

Conceptual and Hierarchical Latent Space Decomposition for Face Editing

DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching

Fine-grained Optimization of Deep Neural Networks

Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search