Or Patashnik

Computer Science · Physical Sciences

16h-index2.7kcitations84works3.12yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Generative Adversarial Networks and Image Synthesis(47), Computer Graphics and Visualization Techniques(15), Image Retrieval and Classification Techniques(14), Multimodal Machine Learning Applications(13), Video Analysis and Summarization(11)

Publications84 total

SemanticMoments: Training-Free Motion Similarity via Third Moment Features
arXiv (Cornell University)·2026Open Access
SemanticMoments: Training-Free Motion Similarity via Third Moment Features
ArXiv.org·2026Open Access
Untwisting RoPE: Frequency Control for Shared Attention in DiTs
ArXiv.org·2026Open Access
Untwisting RoPE: Frequency Control for Shared Attention in DiTs
arXiv (Cornell University)·2026Open Access
Continuous Control of Editing Models via Adaptive-Origin Guidance
arXiv (Cornell University)·2026Open Access
Continuous Control of Editing Models via Adaptive-Origin Guidance
arXiv (Cornell University)·2026Open Access
JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion
ArXiv.org·2026Open Access
JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion
arXiv (Cornell University)·2026Open Access
Tuning-free Visual Effect Transfer across Videos
arXiv (Cornell University)·2026Open Access
Tuning-free Visual Effect Transfer across Videos
ArXiv.org·2026Open Access
LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
arXiv (Cornell University)·2026Open Access
LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
ArXiv.org·2026Open Access
Object-level Visual Prompts for Compositional Image Generation
2025· 3 citedOpen Access
Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA
2025
In-Context Sync-LoRA for Portrait Video Editing
arXiv (Cornell University)·2025Open Access
Tight Inversion: Image-Conditioned Inversion for Real Image Editing
2025
DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models
arXiv (Cornell University)·2025Open Access
NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models
arXiv (Cornell University)·2025Open Access
SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder
arXiv (Cornell University)·2025Open Access
Scaling Group Inference for Diverse and High-Quality Generation
arXiv (Cornell University)·2025Open Access
page 1 of 5Next →

Frequent Co-authors

Daniel Cohen‐Or(47), Yuval Alaluf(16), Rinon Gal(9), Dani Lischinski(7), Daniel Garibi(7), Kfir Aberman(7), Yotam Nitzan(6), Amit H. Bermano(6), Omer Tov(5), Hadar Averbuch‐Elor(5), Gal Chechik(4), Elad Richardson(4), Jun-Yan Zhu(4), Daniil Ostashev(4), Kuan-Chieh Wang(4), Eli Shechtman(3), Sergey Tulyakov(3), Gaurav Parmar(3), Haggai Maron(2), Gal Metzer(2)