Enis Simsar
@enisimsar
PhD at @ETH_en, Ex. ML Intern @Apple, MSc. Student at @TU_Muenchen
Excited to share that our paper, LoRACLR, has been accepted to #CVPR2025! 🎉 Huge thanks to my amazing advisors @THofmann2017, @fedassa, and @PINguAR for their guidance. Looking forward to presenting in Nashville—see you there!
🚀 Excited to share our preprint LoRACLR! TL;DR: LoRACLR merges multiple LoRA models into a unified diffusion model for seamless, high-fidelity multi-concept image synthesis with minimal interference. Thanks to @THofmann2017, @fedassa, and @PINguAR! 🙌
ICCV decisions are out — if your paper didn’t make it, don’t worry! Submit your work to the P13N Workshop instead! Let’s push the frontier of personalized generative AI together!💡 #ICCV2025 #P13NWorkshop #Personalization @ICCVConference More info: p13n-workshop.github.io
Presenting LoRACLR today at @CVPR, contrastive learning meets LoRA merging. Poster 242, ExHall D, 10:30–12:30. Come by and chat!
Excited to share that our paper, LoRACLR, has been accepted to #CVPR2025! 🎉 Huge thanks to my amazing advisors @THofmann2017, @fedassa, and @PINguAR for their guidance. Looking forward to presenting in Nashville—see you there!
📢 The first Personalization Workshop: P13N at @ICCVConference! 🎤 We’re honored to host an outstanding speaker lineup, including @AbermanKfir @natanielruizg @junyanz89 @YVinker @imisra_ @hila_chefer, and panelists @davidbau @jampani_varun @gorkemyurt!
Super happy to announce that Stylebreeder🎨 has been accepted to NeurIPS! Congratulations to the incredible students Matt (who worked on this as an undergrad at VT), Enis @enisimsar, Hidir @d_yesiltepe, and our collaborators @fedassa and @_joelsimon! stylebreeder.github.io
New preprint! Today we introduce GANTASTIC, where we transfer latent directions from pretrained GANs to pretrained diffusion models without any finetuning! Big thanks to my advisor @PINguAR and my co-author @d_yesiltepe! Check it out: gantastic.github.io
Hello academic X 🙌 Excited to present CLoRA, our novel method for composing multiple LoRAs in a single image, all without retraining! Big thanks to my co-author @enisimsar and our advisors @fedassa & @PINguAR You can check it out 👇 clora-diffusion.github.io
📣 Google/ETH PhD position available The group of Prof Schindler at ETH offers a fully funded PhD position in collaboration with our team at Google on the topic of 3D computer vision and generative models. For more details (including how to apply): jobs.ethz.ch/job/view/JOPG_…
Stylebreeder Exploring and Democratizing Artistic Styles through Text-to-Image Models Text-to-image models are becoming increasingly popular, revolutionizing the landscape of digital art creation by enabling highly detailed and creative visual content generation. These