Pinar Yanardag

A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Steering Vectors in Large Language Models

LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers

Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Dynamic View Synthesis as an Inverse Problem

CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation

CLoRA: A Contrastive Approach to Compose Multiple LoRA Models

LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors