Check out our website and follow the workshop’s official page for more updates on deadlines, challenges, and prizes! #ICCV2025 🌺

Submission deadline for Personalization workshop at ICCV #ICCV2025

👨‍🎨 LoRAShop is now out! We introduce LoRAShop, that enables both generation and editing with multiple personalized concepts (no training), pushing the boundaries of the task of image editing! Kudos to my long time collaborator Hidir Yesiltepe and my advisor Pinar Yanardag !

GEM Lab 💎 will be at #CVPR, presenting 3 papers! Drop me a DM if you’d like to meet! We will be presenting Fluxspace (Poster #232), LoRACLR (Poster #242) and Explaining in Diffusion (Poster #397), Session 3, ExHallD! Check out gemlab-vt.github.io for more details! #CVPR2026

Explaining in Diffusion: Explaining a Classifier with Diffusion Semantics Main proceedings Tahira Kazimi Ritika Allada Pinar Yanardag (all VT) arxiv.org/abs/2412.18604 TL;DR: Proposes novel method that leverages capabilities of text-to-image diffusion models to explain classifier decisions.

Check out the amazing work by Hidir Yesiltepe on training-free dynamic novel view synthesis! ✨

Presenting our work Explaining in Diffusion today at poster #397 with Ritika Allada! Project page: cvpr.thecvf.com/virtual/2025/p… #CVPR25 #cvpr #CVPR2026

Yusuf Dalva Tahira Tahira Kazimi and Ritika Ritika Allada are presenting Explaining in Diffusion, a method to explain classifier decisions with diffusion semantics! #CVPR25

So proud of GEM Lab 💎 students! #CVPR2025 #CVPR2026 #CVPR Check out their amazing work at gemlab-vt.github.io.

This dog + its favorite toy = one perfect image. That’s the test. Can your #GenAI model combine two unique subjects without errors? Show us.