Spyros Gidaris
@spyrosgidaris.bsky.social
Senior Research Scientist at Valeo.ai (@valeoai.bsky.social)
https://gidariss.github.io/
https://gidariss.github.io/
Reposted by Spyros Gidaris
Congratulations to our lab colleagues who have been named Outstanding Reviewers at #ICCV2025 👏
Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
2025 ICCV Program Committee
iccv.thecvf.com
October 2, 2025 at 3:28 PM
Congratulations to our lab colleagues who have been named Outstanding Reviewers at #ICCV2025 👏
Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
Reposted by Spyros Gidaris
Update: ResearchGate has investigated the case, and, as far as I can see, all the suspicious papers (~200) have now been removed. Many thanks to the @researchgate.bsky.social team!
Discovered that our RangeViT paper keeps being cited in what might be LLM-generated papers. Number of citations increased rapidly in the last weeks. Too good to be true.
Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks.
[1/]
Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks.
[1/]
September 24, 2025 at 12:23 PM
Update: ResearchGate has investigated the case, and, as far as I can see, all the suspicious papers (~200) have now been removed. Many thanks to the @researchgate.bsky.social team!
Three papers accepted to #NeurIPS2025 (one spotlight)! 🎉
Awesome works in generative modeling, multi-token prediction, and future prediction.
Congratulations to all collaborators!
@nasosger.bsky.social, sta8is.bsky.social, @nicolabourbaki.bsky.social, @ikakogeorgiou.bsky.social & N. Komodakis!
Awesome works in generative modeling, multi-token prediction, and future prediction.
Congratulations to all collaborators!
@nasosger.bsky.social, sta8is.bsky.social, @nicolabourbaki.bsky.social, @ikakogeorgiou.bsky.social & N. Komodakis!
September 23, 2025 at 8:11 AM
Three papers accepted to #NeurIPS2025 (one spotlight)! 🎉
Awesome works in generative modeling, multi-token prediction, and future prediction.
Congratulations to all collaborators!
@nasosger.bsky.social, sta8is.bsky.social, @nicolabourbaki.bsky.social, @ikakogeorgiou.bsky.social & N. Komodakis!
Awesome works in generative modeling, multi-token prediction, and future prediction.
Congratulations to all collaborators!
@nasosger.bsky.social, sta8is.bsky.social, @nicolabourbaki.bsky.social, @ikakogeorgiou.bsky.social & N. Komodakis!
Reposted by Spyros Gidaris
Discovered that our RangeViT paper keeps being cited in what might be LLM-generated papers. Number of citations increased rapidly in the last weeks. Too good to be true.
Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks.
[1/]
Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks.
[1/]
September 16, 2025 at 10:20 AM
Discovered that our RangeViT paper keeps being cited in what might be LLM-generated papers. Number of citations increased rapidly in the last weeks. Too good to be true.
Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks.
[1/]
Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks.
[1/]
Reposted by Spyros Gidaris
1/ Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research.
July 21, 2025 at 2:47 PM
1/ Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research.
Reposted by Spyros Gidaris
1/ New & old work on self-supervised representation learning (SSL) with ViTs:
MOCA ☕ - Predicting Masked Online Codebook Assignments w/ @spyrosgidaris.bsky.social O. Simeoni, A. Vobecky, @matthieucord.bsky.social, N. Komodakis, @ptrkprz.bsky.social #TMLR #ICLR2025
Grab a ☕ & brace for a story & a🧵
MOCA ☕ - Predicting Masked Online Codebook Assignments w/ @spyrosgidaris.bsky.social O. Simeoni, A. Vobecky, @matthieucord.bsky.social, N. Komodakis, @ptrkprz.bsky.social #TMLR #ICLR2025
Grab a ☕ & brace for a story & a🧵
June 27, 2025 at 7:33 AM
1/ New & old work on self-supervised representation learning (SSL) with ViTs:
MOCA ☕ - Predicting Masked Online Codebook Assignments w/ @spyrosgidaris.bsky.social O. Simeoni, A. Vobecky, @matthieucord.bsky.social, N. Komodakis, @ptrkprz.bsky.social #TMLR #ICLR2025
Grab a ☕ & brace for a story & a🧵
MOCA ☕ - Predicting Masked Online Codebook Assignments w/ @spyrosgidaris.bsky.social O. Simeoni, A. Vobecky, @matthieucord.bsky.social, N. Komodakis, @ptrkprz.bsky.social #TMLR #ICLR2025
Grab a ☕ & brace for a story & a🧵
Reposted by Spyros Gidaris
1/n 🚀New paper out - accepted at #ICCV2025!
Introducing DIP: unsupervised post-training that enhances dense features in pretrained ViTs for dense in-context scene understanding
Below: Low-shot in-context semantic segmentation examples. DIP features outperform DINOv2!
Introducing DIP: unsupervised post-training that enhances dense features in pretrained ViTs for dense in-context scene understanding
Below: Low-shot in-context semantic segmentation examples. DIP features outperform DINOv2!
June 25, 2025 at 7:21 PM
1/n 🚀New paper out - accepted at #ICCV2025!
Introducing DIP: unsupervised post-training that enhances dense features in pretrained ViTs for dense in-context scene understanding
Below: Low-shot in-context semantic segmentation examples. DIP features outperform DINOv2!
Introducing DIP: unsupervised post-training that enhances dense features in pretrained ViTs for dense in-context scene understanding
Below: Low-shot in-context semantic segmentation examples. DIP features outperform DINOv2!
Reposted by Spyros Gidaris
🚀Thrilled to introduce JAFAR—a lightweight, flexible, plug-and-play module that upsamples features from any Foundation Vision Encoder to any desired output resolution (1/n)
Paper : arxiv.org/abs/2506.11136
Project Page: jafar-upsampler.github.io
Github: github.com/PaulCouairon...
Paper : arxiv.org/abs/2506.11136
Project Page: jafar-upsampler.github.io
Github: github.com/PaulCouairon...
June 16, 2025 at 1:59 PM
🚀Thrilled to introduce JAFAR—a lightweight, flexible, plug-and-play module that upsamples features from any Foundation Vision Encoder to any desired output resolution (1/n)
Paper : arxiv.org/abs/2506.11136
Project Page: jafar-upsampler.github.io
Github: github.com/PaulCouairon...
Paper : arxiv.org/abs/2506.11136
Project Page: jafar-upsampler.github.io
Github: github.com/PaulCouairon...
Reposted by Spyros Gidaris
Are you at @cvprconference.bsky.social? Come by our poster!
📅 Sat 14/6, 10:30-12:30
📍 Poster #395, ExHall D
📅 Sat 14/6, 10:30-12:30
📍 Poster #395, ExHall D
June 13, 2025 at 5:09 AM
Are you at @cvprconference.bsky.social? Come by our poster!
📅 Sat 14/6, 10:30-12:30
📍 Poster #395, ExHall D
📅 Sat 14/6, 10:30-12:30
📍 Poster #395, ExHall D
I am at #CVPR2025 this week in Nashville!
Presenting "Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers" on multi-modal semantic future prediction.
Come discuss!
Fri 13 Jun 10:30-12:30, poster #345
bsky.app/profile/sta8...
Presenting "Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers" on multi-modal semantic future prediction.
Come discuss!
Fri 13 Jun 10:30-12:30, poster #345
bsky.app/profile/sta8...
🧵 Excited to share our latest work: FUTURIST - A unified transformer architecture for multimodal semantic future prediction, is accepted to #CVPR2025! Here's how it works (1/n)
👇 Links to the arxiv and github below
👇 Links to the arxiv and github below
June 13, 2025 at 12:39 PM
I am at #CVPR2025 this week in Nashville!
Presenting "Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers" on multi-modal semantic future prediction.
Come discuss!
Fri 13 Jun 10:30-12:30, poster #345
bsky.app/profile/sta8...
Presenting "Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers" on multi-modal semantic future prediction.
Come discuss!
Fri 13 Jun 10:30-12:30, poster #345
bsky.app/profile/sta8...
Reposted by Spyros Gidaris
1/n Introducing ReDi (Representation Diffusion): a new generative approach that leverages a diffusion model to jointly capture
– Low-level image details (via VAE latents)
– High-level semantic features (via DINOv2)🧵
– Low-level image details (via VAE latents)
– High-level semantic features (via DINOv2)🧵
April 25, 2025 at 7:23 AM
1/n Introducing ReDi (Representation Diffusion): a new generative approach that leverages a diffusion model to jointly capture
– Low-level image details (via VAE latents)
– High-level semantic features (via DINOv2)🧵
– Low-level image details (via VAE latents)
– High-level semantic features (via DINOv2)🧵
Reposted by Spyros Gidaris
The @valeoai.bsky.social team is presenting a few exciting works @iclr-conf.bsky.social this year on masked generative transformers, adaptation of VLMs, self-supervised representation learning, neural solvers. #iclr2025
Check them out 👇
Check them out 👇
Our recent research will be presented at #ICLR2025 @iclr_conf: VLMs, LLMs, diffusion models, self-supervised learning, physics-informed learning…
Find out more below 🧵
valeoai.github.io/posts/2025-0...
Find out more below 🧵
valeoai.github.io/posts/2025-0...
April 9, 2025 at 12:48 PM
The @valeoai.bsky.social team is presenting a few exciting works @iclr-conf.bsky.social this year on masked generative transformers, adaptation of VLMs, self-supervised representation learning, neural solvers. #iclr2025
Check them out 👇
Check them out 👇
Reposted by Spyros Gidaris
Nice research work from @nicolabourbaki.bsky.social et al. Enhances latent generative models by regularizing the VAE's latent space with an equivariance loss. The finetuning process is straightforward + demonstrates improvements in just 5 epochs!
📄 arxiv.org/abs/2502.09509
🐍 github.com/zelaki/eqvae
📄 arxiv.org/abs/2502.09509
🐍 github.com/zelaki/eqvae
February 25, 2025 at 7:57 PM
Nice research work from @nicolabourbaki.bsky.social et al. Enhances latent generative models by regularizing the VAE's latent space with an equivariance loss. The finetuning process is straightforward + demonstrates improvements in just 5 epochs!
📄 arxiv.org/abs/2502.09509
🐍 github.com/zelaki/eqvae
📄 arxiv.org/abs/2502.09509
🐍 github.com/zelaki/eqvae
Reposted by Spyros Gidaris
Still mesmerized by this work and its results: a mid-to-end driving agent trained with self-play on just 8 maps on 1.6B km of driving (9500 years of subjective driving experience) smashes in off-the-shelf manner all existing benchmarks (nuPlan, CARLA, Waymax) 😮
Crazily amazing work by @eugenevinitsky.bsky.social @senerozan.bsky.social & team, setting the bar so high for anyone working in autonomous driving these days. Check it out arxiv.org/abs/2502.03349
February 21, 2025 at 10:28 PM
Still mesmerized by this work and its results: a mid-to-end driving agent trained with self-play on just 8 maps on 1.6B km of driving (9500 years of subjective driving experience) smashes in off-the-shelf manner all existing benchmarks (nuPlan, CARLA, Waymax) 😮
Reposted by Spyros Gidaris
EQ-VAE: Such a simple & cool trick to regularize multiple kinds of autoencoders: align reconstruction of transformed latents w/ the corresponding transformed inputs.
🚀REPA: 4x training speedup
🚀MaskGIT: 2x training speedup
🚀DiT-XL/2: 7x faster convergence
Kudos @nicolabourbaki.bsky.social et al.
🚀REPA: 4x training speedup
🚀MaskGIT: 2x training speedup
🚀DiT-XL/2: 7x faster convergence
Kudos @nicolabourbaki.bsky.social et al.
1/n🚀If you’re working on generative image modeling, check out our latest work! We introduce EQ-VAE, a simple yet powerful regularization approach that makes latent representations equivariant to spatial transformations, leading to smoother latents and better generative models.👇
February 21, 2025 at 10:54 PM
EQ-VAE: Such a simple & cool trick to regularize multiple kinds of autoencoders: align reconstruction of transformed latents w/ the corresponding transformed inputs.
🚀REPA: 4x training speedup
🚀MaskGIT: 2x training speedup
🚀DiT-XL/2: 7x faster convergence
Kudos @nicolabourbaki.bsky.social et al.
🚀REPA: 4x training speedup
🚀MaskGIT: 2x training speedup
🚀DiT-XL/2: 7x faster convergence
Kudos @nicolabourbaki.bsky.social et al.
Reposted by Spyros Gidaris
The things I've found hardest about research have all been non-technical: maintaining confidence and self-esteem, not abandoning the work when it's too hard or stressful, finding time to learn new things. In comparison, the technical parts are much easier
February 18, 2025 at 6:27 PM
The things I've found hardest about research have all been non-technical: maintaining confidence and self-esteem, not abandoning the work when it's too hard or stressful, finding time to learn new things. In comparison, the technical parts are much easier
Reposted by Spyros Gidaris
🚨 Just a quick note that following requests, we trained a 512px version of our Coherence-Aware Diffusion model (CVPR'24) and updated the paper on arxiv: arxiv.org/abs/2405.20324
It has a package and pretrained models!
🖥️ nicolas-dufour.github.io/cad.html
🤖 github.com/nicolas-dufo...
It has a package and pretrained models!
🖥️ nicolas-dufour.github.io/cad.html
🤖 github.com/nicolas-dufo...
February 20, 2025 at 6:21 AM
🚨 Just a quick note that following requests, we trained a 512px version of our Coherence-Aware Diffusion model (CVPR'24) and updated the paper on arxiv: arxiv.org/abs/2405.20324
It has a package and pretrained models!
🖥️ nicolas-dufour.github.io/cad.html
🤖 github.com/nicolas-dufo...
It has a package and pretrained models!
🖥️ nicolas-dufour.github.io/cad.html
🤖 github.com/nicolas-dufo...
Reposted by Spyros Gidaris
1/n🚀If you’re working on generative image modeling, check out our latest work! We introduce EQ-VAE, a simple yet powerful regularization approach that makes latent representations equivariant to spatial transformations, leading to smoother latents and better generative models.👇
February 18, 2025 at 2:27 PM
1/n🚀If you’re working on generative image modeling, check out our latest work! We introduce EQ-VAE, a simple yet powerful regularization approach that makes latent representations equivariant to spatial transformations, leading to smoother latents and better generative models.👇
Reposted by Spyros Gidaris
1/n 🚀 Excited to share our latest work: DINO-Foresight, a new framework for predicting the future states of scenes using Vision Foundation Model features!
Links to the arXiv and Github 👇
Links to the arXiv and Github 👇
February 7, 2025 at 5:06 PM
1/n 🚀 Excited to share our latest work: DINO-Foresight, a new framework for predicting the future states of scenes using Vision Foundation Model features!
Links to the arXiv and Github 👇
Links to the arXiv and Github 👇
Reposted by Spyros Gidaris
This amazing team ❤️
We've just had our annual gathering to get together and brainstorm on new exciting ideas and projects ahead -- stay tuned!
This is also an excellent occasion to fit all team members in a photo 📸
This is also an excellent occasion to fit all team members in a photo 📸
January 27, 2025 at 5:01 PM
This amazing team ❤️
Reposted by Spyros Gidaris
Thrilled to announce our workshop on Embodied Intelligence for Autonomous Systems on the Horizon @cvprconference.bsky.social featuring a crazy line-up of speakers and challenges.
Mark it in your agendas and also in your registration #cvpr2025
opendrivelab.com/cvpr2025/wor...
Mark it in your agendas and also in your registration #cvpr2025
opendrivelab.com/cvpr2025/wor...
January 23, 2025 at 9:18 PM
Thrilled to announce our workshop on Embodied Intelligence for Autonomous Systems on the Horizon @cvprconference.bsky.social featuring a crazy line-up of speakers and challenges.
Mark it in your agendas and also in your registration #cvpr2025
opendrivelab.com/cvpr2025/wor...
Mark it in your agendas and also in your registration #cvpr2025
opendrivelab.com/cvpr2025/wor...