Martin Nicolas Everaert

#06 Écrire avec des algorithmes | La Grange - Centre / Arts et Sciences | UNIL D'où vient le mot algorithme ? Cette performance propose de voyager dans le temps, guidéexs par la mathématicienne Ada Lovelace, sur les traces des pio ...

🔗 More about the project (in French): www.grange-unil.ch/evenement/06...

🆕 achievement unlocked in my PhD: presenting diffusion models live on stage during a theater performance 🎭

🎨 I generated some visuals for the performance "Écrire avec des algorithmes" by Marielle Pinsard & Quinté+, presented in March at La Grange (UNIL), then I explained how these AI models work 💻

📝 Peer reviewing is often an invisible part of research. It's 🧠-demanding and ⏳-consuming, but essential to maintain/improve the quality/rigor of our fields.

⭐️🎉 Glad to be recognized as a Top Reviewer at #NeurIPS2024 and Outstanding Reviewer at #CVPR2025

The International Conference on Computational Imaging (ICCP) is coming to my hometown, #Toronto! Excited to serve as a social media co-chair for such a fantastic event.

With an incredible organizing committee and an amazing city to host, how could I say no?

The February issue of the PAMI-TC newsletter is out: tinyurl.com/4ur2pweu

There are a bunch of open calls related to #CVPR2025, #ICCV2025, and #WACV2025. Don't forget that WACV is right around the corner --- I need any proposed motions for the TC meeting by 2/15.

📣 We're now on BlueSky! 🌟 Join us for live event coverage, important news, and updates from the IC School. Stay connected and be part of our journey! 🎓✨ #ICFaculty #ICSchool #StayUpdated

I've put together a starter pack of EPFL researchers across all labs and domains! 🇨🇭 Would love to expand this list and showcase more amazing work happening at EPFL. Drop a reply to be added!
#EPFL #academicsky

go.bsky.app/73zdbtp

👋 Thanks for the list! Would love to be in too

Started a list of some researchers working on image/video generation. (Not comprehensive at all)

Reply with a paper link and TLDR to get added to the list! I request all grad students to not feel imposter-y and just reply if you work in this field!

#computervision #diffusion

go.bsky.app/SP1uWoE

👋 Thanks for the list! Would love to be added, working on diffusion models scholar.google.com/citations?us...

My growing list of #computervision researchers on Bsky.

Missed you? Let me know.

go.bsky.app/M7HGC3Y

👋 Working on diffusion models :-)

Had a fantastic time at #ICVSS2024 last week in Sicily! Presented my poster, enjoyed the classes, etc.
Great to reconnect with conference friends and make new ones. Also, my first time in Italy despite being in Lausanne for almost 5 years! 🇮🇹 Big thanks to the organizers too!

I meant to share this sooner (almost 2 months ago), but forgot 🙈
Received an incredibly kind email from the AC appreciating my review work. It feels great to be acknowledged. Kudos to @eccvconf for selecting such supportive area chairs! Thank you too, anonymous AC!
#ECCV2024

It was a pleasure to demo my work "Signal-Leak Bias in Diffusion Models" at the AI Tinkerers Lausanne inaugural meetup today! A huge thank you to the organizers @EricBezzam @ThomVett @ArnoutDevos for putting together this event 🙏 (📸 taken by @vinitra_s and Adrian)

AI4VA@ECCV 2024 - Participation The event is arranged in two parts 1) Workshop and 2) Challenges. Each of these has separate participation and submission instructions as follows.

📢 My colleagues are organizing the AI4VA workshop @ #ECCV2024 and *actively* looking for papers, extended abstracts, and challenge participation.
Deadline (papers): July 25th
➡️ Details: https://t.co/ZNad3TwoD3

@AI4VAECCV24 @ECCVconf @deblinaforAI @Baharay21 @TongZhang1024 https://t.co/uKIiVHq6yM

🔥 Just released the code for our #WACV2024 paper "Exploiting the Signal-Leak Bias in Diffusion Models" 📄
🔗 Project page: https://ivrl.github.io/signal-leak-bias
👩‍💻 Code: https://github.com/IVRL/signal-leak-bias https://twitter.com/EveraertMartin/status/1734853622121312331

Very grateful to have received a TA award from @ICepfl 🙏🏆

✨ Excited to share our work “Exploiting the Signal-Leak Bias in Diffusion Models”!
🖼️ We turn a bias contained in diffusion models into a method to generate images in a desired style or color, or with a more natural color distribution.
https://ivrl.github.io/signal-leak-bias/
(1/8) ⬇️

I presented our paper VETIM at #BMVC2023 three weeks ago!
🔍 It is possible to learn a single token representing a concept in Stable Diffusion using supervision only at the CLIP output and without mimicking visual features from sample images.
Check it out: https://ivrl.github.io/vetim/

🌟 Excited to be presenting our work "Diffusion in Style" at @ICCVConference! Join us with @rk_epfl for our poster presentation today from 10:30 AM to 12:30 PM in Room "Foyer Sud," poster number 016! 🎨 #ICCV2023 https://twitter.com/EveraertMartin/status/1707865246763741484

🔍 Trying to fine-tune Stable Diffusion on images with a specific style? You'll get better results by also adapting the noise distribution to the style! Check our #ICCV2023 paper: 📑https://t.co/crHmbec0jZ Collaboration with @LargoAI, Dr. @rk_epfl and Prof. @ssusstrunk