🇫🇷🇨🇭| PhD student @ Uni Freiburg 🇩🇪 | Generative Vision | 3D understanding | #QueerInAI 🏳️🌈
Freiburg im Breisgau, Germany
Joined June 2021
- Tweets48
- Following139
- Followers68
- Likes489
Artur Jesslen retweeted
🚀 We're hiring multiple fully funded PhD students through the #ELLIS PhD Program!
Join us to work on generative AI, world models, and AI safety.
genintel.de
Apply by Oct 31 via apply.ellis.eu
Spread the word!
After a challenging Neurips rebuttal, it feels nice to be recognized as Outstanding Reviewer at #ECCV2026 , looking forward to attend the conference!
See you in Malmö!
Thank you to all our #ECCV2026 reviewers. Special thanks to the Outstanding Reviewers for their exceptional contributions! 👏
eccv.ecva.net/Conferences/20…
We are grateful to all of the 17,491 reviewers who helped make #CVPR2026 possible. We are especially pleased to recognize the following Outstanding Reviewers, whose high-quality reviews (as judged by their Area Chairs) placed them among the top 5% of reviewers.
Artur Jesslen retweeted
Or we leave the image plane entirely.
In Morpheus [Sommer, Jesslen et al., 2026] we predict dense correspondences directly in 3D camera space, by learning a morphable category prior.
Dense 3D correspondences emerge from the shape prior during training.
genintel.github.io/HouseCorr…
Artur Jesslen retweeted
Can we enhance the geometry gap?
In [Jesslen et al., 2026]: we use 3D foundation priors — SAM-3D, PartField — to generate dense, 3D-aware pseudo-correspondences. No human annotations.
A small adapter trained on these labels sets a new SOTA on SPair-71k.
genintel.github.io/3D-SC
Artur Jesslen retweeted
Robust classifiers are great. Interpretable models are great. But why do we still have to choose between the two?
🎉 Excited to share our paper "Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning" has been accepted to #ICLR2026 @iclr_conf !
Really loved to see people excited about our research!
We will also be presenting our 3D representation in the context of incremental learning on Friday at 10:30 @ Poster 140! 🤩
Was great to see a large turnout at Artur‘s paper 🎉 make sure to check it out if you missed it! @eccvconf
Our second talk from @JiahuiLiu_ is staring now 🤩
Tomorrow, our great @eccvconf workshop on OOD generalization in Computer Vision Foundation Models is finally taking place! Join us from 9AM to hear great insights from our guest speakers 🤩
📍Location: Brown 1
More info: ood-cv.org
Tomorrow, our great @eccvconf workshop on OOD generalization in Computer Vision Foundation Models is finally taking place! Join us from 9AM to hear great insights from our guest speakers 🤩
📍Location: Brown 1
More info: ood-cv.org
@JiahuiLiu_ will explain what can foundation models teach to object detectors (⚠️ Note the time change!) #ECCV2024
And finally, @zsoltkira will be talking about robust fine-tuning of foundations models (⚠️ Note the time change!) #ECCV2024
Excited to be talking about robust fine-tuning of foundation models (including VLMs) at the @eccvconf OOD-CV workshop tomorrow (09/30)! Check it out at Room Brown 1 at 11am Italy time.
(Note my talk has shifted due to hurricane-related travel changes!)
Our ECCV Workshop OOD-CV generalization in Computer Vision Foundation Models will be taking place on monday at @eccvconf ! We will have diverse and wonderful talks so don't hesitate to join us!
Date: Sep. 30th, Monday
Time: 9:00-13:00
Room: Brown 1
Link: ood-cv.org
Here you can find the full workshop program 📅
Looking forward to seeing you there! 🤩
Big thanks to all co-organizers @AdamKortylewski @BingchenZhao @wufeima @jiahaowg @Sagar_Vaze @CCVLatJHU and others
Artur Jesslen retweeted
Call for papers! Join us at the OOD-CV workshop @eccvconf. We invite long and short papers on the topic of OOD generalizations in computer vision and host two challenges on the Semantic Shift Benchmark and the UNICORN benchmark.
More details at ood-cv.org/
#ECCV2024
Received a negative response for your #ECCV2024 paper? Or have groundbreaking findings on OOD generalization to share? Submit your work to the OOD-CV workshop @eccvconf! We welcome long and short papers, and host two challenges. More details at ood-cv.org!
Thanks to all co-organizer: @AdamKortylewski, @wufeima, @BingchenZhao, @jiahaowg, @Sagar_Vaze, @kaihan_vis, etc
Hey @eccvconf , will there be free passes available for workshop organisers like last year at @ICCVConference ? When will information about this be available ?
Thanks again to all the great speakers who presented their work about OoD generalisation this morning in the OoD-CV workshop! Looking forward for this afternoon already 🤩 We will be hearing from @mariojfritz, @kate_saenko_ and @YuilleAlan . Room S01 from 1:30pm @ICCVConference