Yiğit Ekin — accepted AI-conference papers

2025

RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers

Ahmet Berke Gökmen, Yiğit Ekin, Bahri Batuhan Bilecen, Aysegul Dundar

NeurIPS 2025poster

We propose RoPECraft, a training-free video motion transfer method for diffusion transformers that operates solely by modifying their rotary positional embeddings (RoPE). We first extract dense optical flow from a reference video, and utilize the resulting motion offsets to warp the complex-exponent…

Cited by 0 Source ↗Scholar ↗

2024

CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models

Yiğit Ekin, Ahmet Burak Yildirim, Erdem Eren Caglar, Aykut Erdem, Erkut Erdem, Aysegul Dundar

NeurIPS 2024poster

Advanced image editing techniques, particularly inpainting, are essential for seamlessly removing unwanted elements while preserving visual integrity. Traditional GAN-based methods have achieved notable success, but recent advancements in diffusion models have produced superior results due to their…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗