AI/image generation 🤖
#EPFL #CentraleSupélec #LyceeSaintLouis alumni
Reposts ≠ Endorsement
https://martin-ev.github.io/
🔗 Project page: https://ivrl.github.io/signal-leak-bias
👩💻 Code: https://github.com/IVRL/signal-leak-bias https://twitter.com/EveraertMartin/status/1734853622121312331
🎨 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 💻
🎨 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 💻
⭐️🎉 Glad to be recognized as a Top Reviewer at #NeurIPS2024 and Outstanding Reviewer at #CVPR2025
⭐️🎉 Glad to be recognized as a Top Reviewer at #NeurIPS2024 and Outstanding Reviewer at #CVPR2025
With an incredible organizing committee and an amazing city to host, how could I say no?
With an incredible organizing committee and an amazing city to host, how could I say no?
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.
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.
#EPFL #academicsky
go.bsky.app/73zdbtp
#EPFL #academicsky
go.bsky.app/73zdbtp
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
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
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!
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!
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
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
Deadline (papers): July 25th
➡️ Details: https://t.co/ZNad3TwoD3
@AI4VAECCV24 @ECCVconf @deblinaforAI @Baharay21 @TongZhang1024 https://t.co/uKIiVHq6yM
Deadline (papers): July 25th
➡️ Details: https://t.co/ZNad3TwoD3
@AI4VAECCV24 @ECCVconf @deblinaforAI @Baharay21 @TongZhang1024 https://t.co/uKIiVHq6yM
🔗 Project page: https://ivrl.github.io/signal-leak-bias
👩💻 Code: https://github.com/IVRL/signal-leak-bias https://twitter.com/EveraertMartin/status/1734853622121312331
🔗 Project page: https://ivrl.github.io/signal-leak-bias
👩💻 Code: https://github.com/IVRL/signal-leak-bias https://twitter.com/EveraertMartin/status/1734853622121312331
🖼️ 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) ⬇️
🖼️ 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) ⬇️
🔍 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/
🔍 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/