Enis Simsar

PhD at @ETH_en and @Google, Ex. ML Intern @Apple, MSc. from @TU_Muenchen

[Pinar Yanardag @ICML2026 @PINguAR]

Join us on June 4, 8:30AM–12:30PM, Room 4CD, for the 2nd Personalization in Generative AI Workshop (P13N) at @CVPR! #CVPR2026 #P13N

Talks, posters & a panel on the future of generative AI systems that adapt to users' preferences, identities & contexts!

[Enis Simsar @enisimsar]

(2/2) Join us in Seoul! 🇰🇷 We’re looking for submissions on long-context modeling, interactive control, and trustworthy evaluation.

📅 Paper Deadline: April 30, 2026 (AoE)
🔗 Details: https://t.co/tOZMpqwxZr

Can't wait to see your work! 🚀 #ICML2026 #GenerativeAI #VideoGen

[Enis Simsar @enisimsar]

(1/2) Excited to be part of the team bringing "From Frames to Stories (F2S)" to @ICMLConf 2026! 🎬

We’re diving deep into the future of long-horizon video generation, moving beyond short clips to reliable, controllable storytelling. 🤖📹

[Yu Lu @luyu79797018]

We invite submissions to the ICML 2026 Workshop
From Frames to Stories (F2S): Toward Reliable, Controllable and Trustworthy Long-Horizon Video Generation.

The workshop aims to bring together researchers to advance long-horizon video generation, with a focus on long-context modeling, state representation, interactive control, and trustworthy evaluation.

We welcome submissions of recent work in related areas, including both published and unpublished papers.

For more details, please visit: https://t.co/04mSGcAXTl

[Enis Simsar @enisimsar]

Personalized AI is taking over #CVPR2026! 🚀

Don't miss the 2nd #P13N Workshop. We are officially accepting archival submissions! 📑

📌 Archival Deadline: March 23
🎙️ Featuring an outstanding lineup of guest speakers and experts in the field.

🔗 https://t.co/YPuvozSNfT

[Pinar Yanardag @ICML2026 @PINguAR]

📢 The second Personalization Workshop: P13N, this time at @CVPR! We’re honored to host an outstanding speaker lineup, including @AbermanKfir @natanielruizg @OPatashnik and many more! https://t.co/CIEvEe7u2O #CVPR2026

[Enis Simsar @enisimsar]

Diffusion model attention isn’t just for generation, it hides rich grounding cues.
RefAM turns noise sinks into signal amplifiers with zero retraining.

🌐 Paper + project page:
📄 https://t.co/BkWwVzGHs2
💻 https://t.co/eYv4dgFtaJ

[Enis Simsar @enisimsar]

🚀 Excited to share our new work RefAM: Attention Magnets for Zero-Shot Referral Segmentation, a training-free approach that turns diffusion model attentions into segmentations.

By @anna_kukleva_, me, Alessio Tonioni, @ferjadnaeem, @fedassa, @janericlenssen, Bernt Schiele

[Enis Simsar @enisimsar]

🧪 Ablations show:
- Stop-word magnets > random tokens
- Combining noun-phrase focus + spatial bias improves edges
- Works across different diffusion backbones

[Enis Simsar @enisimsar]

🔄 Our UIP2P paper is accepted to @ICCVConference.

📍 Exhibit Hall I #1750
🗓️ Wed, Oct 22 | 14:30–16:30 HST

@fedassa and I will be at the poster. Visit us to discuss unsupervised instruction-based image editing 🙌🏻

[Enis Simsar @enisimsar]

🚀 Excited to introduce UIP2P: Unsupervised Instruction-Based Image Editing via Cycle Edit Consistency (CEC)!

TL;DR: Scalable instruction-based image editing without paired image data. Works on real-world datasets with robust, reversible edits!

Thanks to Alessio Tonioni, @xyongqin, @THofmann2017, @fedassa!

[Pinar Yanardag @ICML2026 @PINguAR]

Please join our P13N Challenge at ICCV! @ICCVConference Many cash 🏆 prizes! 🥇 $1000 🥈 $500 🥉 $300

[Pinar Yanardag @ICML2026 @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: https://t.co/CIEvEe81Sm

[Enis Simsar @enisimsar]

Presenting LoRACLR today at @CVPR, contrastive learning meets LoRA merging. Poster 242, ExHall D, 10:30–12:30. Come by and chat!

[Enis Simsar @enisimsar]

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!

[Pinar Yanardag @ICML2026 @PINguAR]

📢 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 @gorkem!

[Enis Simsar @enisimsar]

📌 Poster Session 2 - Board #25
🗓 March 1, 2025 | 🕓 16:15 - 18:00 MST
📍 Tucson Ballroom

🌐 Project & Code: https://t.co/8NhrVUXXMS

See you there! 🚀

[Enis Simsar @enisimsar]

🚀 Update: Our work LIME was presented as an oral at #WACV2025! 🎤

Missed it? No worries—join us at our poster session to discuss how LIME enables precise image editing without extra inputs or retraining!

(Details in the next tweet ⬇️)

[Enis Simsar @enisimsar]

🌟 Excited to present LIME, localized image editing via cross-attention regularization without extra data, re-training, or fine-tuning!

Collaboration with Alessio Tonioni, @xyongqin, Thomas Hofmann, @fedassa

📄 Paper: https://t.co/R7zP0xc3LE
🔗 Project: https://t.co/JMuhexRDRs