Shelly Golan

I'm a PhD student at Tel Aviv University, advised by Dr. Or Patashnik. I obtained my MSc at the Technion under the supervision of Prof. Michael Elad.

I work on image and video generation, creative synthesis, and post-training alignment of generative models — aiming to make visual content creation more controllable and expressive.

Away from the screen, you'll find me shaping clay at the pottery wheel or out on mountain trails.

Diffusion Models
Generative AI
Creative Generation
RL Post-Training

Publications

ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control

Shelly Golan, Michael Finkelson, Ariel Bereslavsky, Yotam Nitzan, Or Patashnik

NeurIPS 2026 Oral

arXiv Code Project page

VLM-Guided Adaptive Negative Prompting for Creative Generation

Shelly Golan, Yotam Nitzan, Zongze Wu, Or Patashnik

ICLR 2026

arXiv Code Project page

Advancing Image Classification with Discrete Diffusion Classification Modeling

Omer Belhasin, Shelly Golan, Ran El-Yaniv, Michael Elad

CVPR 2026 Oral

arXiv Code Project page

Consistency-based image generation thumbnail

Enhancing Consistency-Based Image Generation via Adversarially-Trained Classification and Energy-Based Discrimination

Shelly Golan, Roy Ganz, Michael Elad

NeurIPS 2024

arXiv Code