Vicky Kalogeiton
@vickykalogeiton.bsky.social
Assistant Professor at Ecole Polytechnique, IP_Paris// Before: Oxford_VGG, Inria Grenoble // multimodality, genAI enthusiast // happy mum+dog_mum // opinions: mine
Happy to be here and interact with the rich research ecosystem in the Netherlands!!
Honered to get a selfie with our Netherlands Conference on Computer Vision (NCCV) keynote speaker! The brilliant @vickykalogeiton.bsky.social
Two zealots of the Data efficiency church in the Religion of Scaling AI 🙏
Two zealots of the Data efficiency church in the Religion of Scaling AI 🙏
June 18, 2026 at 10:53 AM
Happy to be here and interact with the rich research ecosystem in the Netherlands!!
Reposted by Vicky Kalogeiton
🎉 Our work MIRO is accepted to #ICML2026 @icmlconf.bsky.social
We integrate human preferences directly during pretraining with multi-reward conditioning.
⚡MIRO is 19x faster than baselines and 370x cheaper at inference!
🤗 Try out the models: huggingface.co/spaces/nicol...
See you in Seoul 🇰🇷 !
We integrate human preferences directly during pretraining with multi-reward conditioning.
⚡MIRO is 19x faster than baselines and 370x cheaper at inference!
🤗 Try out the models: huggingface.co/spaces/nicol...
See you in Seoul 🇰🇷 !
May 21, 2026 at 7:29 AM
🎉 Our work MIRO is accepted to #ICML2026 @icmlconf.bsky.social
We integrate human preferences directly during pretraining with multi-reward conditioning.
⚡MIRO is 19x faster than baselines and 370x cheaper at inference!
🤗 Try out the models: huggingface.co/spaces/nicol...
See you in Seoul 🇰🇷 !
We integrate human preferences directly during pretraining with multi-reward conditioning.
⚡MIRO is 19x faster than baselines and 370x cheaper at inference!
🤗 Try out the models: huggingface.co/spaces/nicol...
See you in Seoul 🇰🇷 !
Reposted by Vicky Kalogeiton
🥳Accepted to ICML, by the way!
Old paper here: arxiv.org/abs/2510.25897 (new version up soon)
Going to pressure @nicolasdufour.bsky.social to release the code and models! 😅
Old paper here: arxiv.org/abs/2510.25897 (new version up soon)
Going to pressure @nicolasdufour.bsky.social to release the code and models! 😅
We introduce MIRO: a new paradigm for T2I model alignment integrating reward conditioning into pretraining, eliminating the need for separate fine-tuning/RL stages. This single-stage approach offers unprecedented efficiency and control.
- 19x faster convergence ⚡
- 370x less FLOPS than FLUX-dev 📉
- 19x faster convergence ⚡
- 370x less FLOPS than FLUX-dev 📉
May 3, 2026 at 4:23 PM
🥳Accepted to ICML, by the way!
Old paper here: arxiv.org/abs/2510.25897 (new version up soon)
Going to pressure @nicolasdufour.bsky.social to release the code and models! 😅
Old paper here: arxiv.org/abs/2510.25897 (new version up soon)
Going to pressure @nicolasdufour.bsky.social to release the code and models! 😅
So honored and humbled to have won this award! Thanks David ☺️
Huge congrats @vickykalogeiton.bsky.social for being awarded the médaille de bronze in Computer Science!👏🥳🎉🍾
Very well deserved for all the hard work and fantastic ideas!
www.ins2i.cnrs.fr/fr/talents/c...
@cnrsinformatics.bsky.social @ipparis.bsky.social @ecolepolytechnique.bsky.social
Very well deserved for all the hard work and fantastic ideas!
www.ins2i.cnrs.fr/fr/talents/c...
@cnrsinformatics.bsky.social @ipparis.bsky.social @ecolepolytechnique.bsky.social
May 15, 2026 at 6:13 PM
So honored and humbled to have won this award! Thanks David ☺️
Very proud of our recent work, kudos to the team! Read @davidpicard.bsky.social’s excellent post for more details or the paper arxiv.org/pdf/2502.21318
October 8, 2025 at 9:19 PM
Very proud of our recent work, kudos to the team! Read @davidpicard.bsky.social’s excellent post for more details or the paper arxiv.org/pdf/2502.21318
Reposted by Vicky Kalogeiton
The Visual Recognition Group at CTU in Prague organizes the 50th Pattern Recognition and Computer Vision Colloquium with
Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann.
On Thursday Oct 9, 11:00-17:00.
cmp.felk.cvut.cz/colloquium/
Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann.
On Thursday Oct 9, 11:00-17:00.
cmp.felk.cvut.cz/colloquium/
October 6, 2025 at 3:13 PM
The Visual Recognition Group at CTU in Prague organizes the 50th Pattern Recognition and Computer Vision Colloquium with
Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann.
On Thursday Oct 9, 11:00-17:00.
cmp.felk.cvut.cz/colloquium/
Torsten Sattler, Paul-Edouard Sarlin, Vicky Kalogeiton, Spyros Gidaris, Anna Kukleva, and Lukas Neumann.
On Thursday Oct 9, 11:00-17:00.
cmp.felk.cvut.cz/colloquium/
Reposted by Vicky Kalogeiton
As an SAC for @neuripsconf.bsky.social, I don't agree with PCs approach to reject papers based on ranking.
I ranked my accepted papers as requested and explicitly stated that I support the acceptance of all papers.
I was not given an explanation of why papers at the end of the rank were rejected.
I ranked my accepted papers as requested and explicitly stated that I support the acceptance of all papers.
I was not given an explanation of why papers at the end of the rank were rejected.
September 19, 2025 at 7:49 PM
As an SAC for @neuripsconf.bsky.social, I don't agree with PCs approach to reject papers based on ranking.
I ranked my accepted papers as requested and explicitly stated that I support the acceptance of all papers.
I was not given an explanation of why papers at the end of the rank were rejected.
I ranked my accepted papers as requested and explicitly stated that I support the acceptance of all papers.
I was not given an explanation of why papers at the end of the rank were rejected.
Reposted by Vicky Kalogeiton
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
July 16, 2025 at 10:01 PM
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
Reposted by Vicky Kalogeiton
Update on hidden prompts in papers targeting LLM reviews: ICML 2025 PCs react.
icml.cc/Conferences/...
icml.cc/Conferences/...
July 23, 2025 at 12:07 PM
Update on hidden prompts in papers targeting LLM reviews: ICML 2025 PCs react.
icml.cc/Conferences/...
icml.cc/Conferences/...
Reposted by Vicky Kalogeiton
#ICCV2025 is deeply committed to promoting diversity, equity, and inclusion within our community. As part of this commitment, travel support is available to help broaden participation.
Applications will be reviewed on a rolling basis until August 20, 2025 (anywhere on Earth).
Applications will be reviewed on a rolling basis until August 20, 2025 (anywhere on Earth).
July 20, 2025 at 9:14 PM
#ICCV2025 is deeply committed to promoting diversity, equity, and inclusion within our community. As part of this commitment, travel support is available to help broaden participation.
Applications will be reviewed on a rolling basis until August 20, 2025 (anywhere on Earth).
Applications will be reviewed on a rolling basis until August 20, 2025 (anywhere on Earth).
Reposted by Vicky Kalogeiton
Come see us in poster 186 to see our poster Around the World in 80 timesteps: A generative Approach to Global Visual Geolocation!
Cc @loicland.bsky.social @davidpicard.bsky.social @vickykalogeiton.bsky.social
Cc @loicland.bsky.social @davidpicard.bsky.social @vickykalogeiton.bsky.social
June 15, 2025 at 3:30 PM
Come see us in poster 186 to see our poster Around the World in 80 timesteps: A generative Approach to Global Visual Geolocation!
Cc @loicland.bsky.social @davidpicard.bsky.social @vickykalogeiton.bsky.social
Cc @loicland.bsky.social @davidpicard.bsky.social @vickykalogeiton.bsky.social
Reposted by Vicky Kalogeiton
CVPR@Paris opening speech at Sorbonne University by @davidpicard.bsky.social , @vickykalogeiton.bsky.social and Matthieu Cord.
Great location!
❤️
(also: free food as at 'real' CVPR)
Great location!
❤️
(also: free food as at 'real' CVPR)
June 6, 2025 at 8:02 AM
CVPR@Paris opening speech at Sorbonne University by @davidpicard.bsky.social , @vickykalogeiton.bsky.social and Matthieu Cord.
Great location!
❤️
(also: free food as at 'real' CVPR)
Great location!
❤️
(also: free food as at 'real' CVPR)
Reposted by Vicky Kalogeiton
#cvpr2025 in Paris satellite event kicking off!
Thanks so much for organizing! @davidpicard.bsky.social @vickykalogeiton.bsky.social and @matthieucord.bsky.social
Thanks so much for organizing! @davidpicard.bsky.social @vickykalogeiton.bsky.social and @matthieucord.bsky.social
June 6, 2025 at 8:05 AM
#cvpr2025 in Paris satellite event kicking off!
Thanks so much for organizing! @davidpicard.bsky.social @vickykalogeiton.bsky.social and @matthieucord.bsky.social
Thanks so much for organizing! @davidpicard.bsky.social @vickykalogeiton.bsky.social and @matthieucord.bsky.social
Reposted by Vicky Kalogeiton
Masked Diffusion Models (MDMs) are a hot topic in generative AI 🔥 — powerful but slow due to multiple sampling steps.
We @polytechniqueparis.bsky.social and @inria-grenoble.bsky.social introduce Di[M]O — a novel approach to distill MDMs into a one-step generator without sacrificing quality.
We @polytechniqueparis.bsky.social and @inria-grenoble.bsky.social introduce Di[M]O — a novel approach to distill MDMs into a one-step generator without sacrificing quality.
March 21, 2025 at 3:36 PM
Masked Diffusion Models (MDMs) are a hot topic in generative AI 🔥 — powerful but slow due to multiple sampling steps.
We @polytechniqueparis.bsky.social and @inria-grenoble.bsky.social introduce Di[M]O — a novel approach to distill MDMs into a one-step generator without sacrificing quality.
We @polytechniqueparis.bsky.social and @inria-grenoble.bsky.social introduce Di[M]O — a novel approach to distill MDMs into a one-step generator without sacrificing quality.
Join us at CVPR@Paris on June 6th!
It's a local alternative to CVPR, aiming at addressing some sustainability and inclusivity concerns. All students and researchers are welcome to attend!
Registration free: cvprinparis.github.io/CVPR2025InPa...
It's a local alternative to CVPR, aiming at addressing some sustainability and inclusivity concerns. All students and researchers are welcome to attend!
Registration free: cvprinparis.github.io/CVPR2025InPa...
March 21, 2025 at 5:05 PM
Join us at CVPR@Paris on June 6th!
It's a local alternative to CVPR, aiming at addressing some sustainability and inclusivity concerns. All students and researchers are welcome to attend!
Registration free: cvprinparis.github.io/CVPR2025InPa...
It's a local alternative to CVPR, aiming at addressing some sustainability and inclusivity concerns. All students and researchers are welcome to attend!
Registration free: cvprinparis.github.io/CVPR2025InPa...
Text-to-image models are trained on billions of data.
But, is it necessary?
Our "How far can we go with ImageNet for T2I generation?" @lucasdegeorge.bsky.social @arrijitghosh.bsky.social @nicolasdufour.bsky.social @davidpicard.bsky.social shows that no, if we are careful arxiv.org/abs/2502.21318
But, is it necessary?
Our "How far can we go with ImageNet for T2I generation?" @lucasdegeorge.bsky.social @arrijitghosh.bsky.social @nicolasdufour.bsky.social @davidpicard.bsky.social shows that no, if we are careful arxiv.org/abs/2502.21318
March 4, 2025 at 8:26 AM
Text-to-image models are trained on billions of data.
But, is it necessary?
Our "How far can we go with ImageNet for T2I generation?" @lucasdegeorge.bsky.social @arrijitghosh.bsky.social @nicolasdufour.bsky.social @davidpicard.bsky.social shows that no, if we are careful arxiv.org/abs/2502.21318
But, is it necessary?
Our "How far can we go with ImageNet for T2I generation?" @lucasdegeorge.bsky.social @arrijitghosh.bsky.social @nicolasdufour.bsky.social @davidpicard.bsky.social shows that no, if we are careful arxiv.org/abs/2502.21318
Similar for Polytechnique, part of Institut Polytechnique de Paris: future open positions in AI for junior researchers. They come with a good starting package and research independence.
Contact me by email or DM even for informal discussions.
Contact me by email or DM even for informal discussions.
🚨 Future open positions in AI at my home institution* targeted towards young researchers. These are tenure track positions with a good starting package, aimed at guiding you towards an ERC StG within 4 years.
Feel free to contact me in DM.
*ENPC, part of Institut Polytechnique de Paris
Feel free to contact me in DM.
*ENPC, part of Institut Polytechnique de Paris
February 28, 2025 at 11:40 PM
Similar for Polytechnique, part of Institut Polytechnique de Paris: future open positions in AI for junior researchers. They come with a good starting package and research independence.
Contact me by email or DM even for informal discussions.
Contact me by email or DM even for informal discussions.
Reposted by Vicky Kalogeiton
📣 The following conference is not the ECVA-sponsored ECCV 📣 Please see our official website eccv.ecva.net/Conferences/... or follow @eccv.bsky.social for updates on #ECCV2026
February 7, 2025 at 5:09 PM
📣 The following conference is not the ECVA-sponsored ECCV 📣 Please see our official website eccv.ecva.net/Conferences/... or follow @eccv.bsky.social for updates on #ECCV2026
Great day today at LVMH at AI Action Summit, quoting @gabrielpeyre.bsky.social “diffusion is great” 😀
@vickykalogeiton.bsky.social and @davidpicard.bsky.social updating live there slides to quote my talk just before ... next level presentation!
February 7, 2025 at 12:14 PM
Great day today at LVMH at AI Action Summit, quoting @gabrielpeyre.bsky.social “diffusion is great” 😀
Welcome Philippe!
I am a bit late to the party, but extremely happy to have finally created my account here, and to see that the community seems more active here than at the "other place" now :)
December 2, 2024 at 7:38 PM
Welcome Philippe!
Reposted by Vicky Kalogeiton
As I haven't found it out there yet, I made the Women in computer vision started pack.
Many more missing, please let me know how is already in bsky to add them!
go.bsky.app/BowzivT
Many more missing, please let me know how is already in bsky to add them!
go.bsky.app/BowzivT
November 22, 2024 at 11:43 PM
As I haven't found it out there yet, I made the Women in computer vision started pack.
Many more missing, please let me know how is already in bsky to add them!
go.bsky.app/BowzivT
Many more missing, please let me know how is already in bsky to add them!
go.bsky.app/BowzivT
Hello 🦋 world!
November 24, 2024 at 4:15 AM
Hello 🦋 world!