valeo.ai
@valeoai.bsky.social
We are a research team on artificial intelligence for automotive applications working toward assisted and autonomous driving.
--> https://valeoai.github.io/ <--
--> https://valeoai.github.io/ <--
Pinned
valeo.ai
@valeoai.bsky.social
· 23d
1/🧵 Q: Can we have both a simple and SOTA architecture in autonomous driving?
R: Yes! 😍
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how 👇
R: Yes! 😍
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how 👇
Reposted by valeo.ai
The unreasonable magic of simplicity!
Meet DrivoR (Driving on Registers): our latest end2end autonomous driving model.
We teared down complex dependencies & modules from current models to
obtain a pure Transformer-based SOTA driving agent (NAVSIM v1 & v2, HUGSIM).
Find out more 👇
Meet DrivoR (Driving on Registers): our latest end2end autonomous driving model.
We teared down complex dependencies & modules from current models to
obtain a pure Transformer-based SOTA driving agent (NAVSIM v1 & v2, HUGSIM).
Find out more 👇
1/🧵 Q: Can we have both a simple and SOTA architecture in autonomous driving?
R: Yes! 😍
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how 👇
R: Yes! 😍
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how 👇
January 9, 2026 at 5:02 PM
The unreasonable magic of simplicity!
Meet DrivoR (Driving on Registers): our latest end2end autonomous driving model.
We teared down complex dependencies & modules from current models to
obtain a pure Transformer-based SOTA driving agent (NAVSIM v1 & v2, HUGSIM).
Find out more 👇
Meet DrivoR (Driving on Registers): our latest end2end autonomous driving model.
We teared down complex dependencies & modules from current models to
obtain a pure Transformer-based SOTA driving agent (NAVSIM v1 & v2, HUGSIM).
Find out more 👇
1/🧵 Q: Can we have both a simple and SOTA architecture in autonomous driving?
R: Yes! 😍
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how 👇
R: Yes! 😍
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how 👇
January 9, 2026 at 4:55 PM
1/🧵 Q: Can we have both a simple and SOTA architecture in autonomous driving?
R: Yes! 😍
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how 👇
R: Yes! 😍
Introducing Driving on Registers (DrivoR):
a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation.
Here is how 👇
Our @spyrosgidaris.bsky.social is speaking this morning (Wed, Dec 10th, 11:00 am Paris time) about "Latent Representations for Better Generative Image Modeling" in the Hi! PARIS - ELLIS monthly seminar.
The talk will be live-streamed: www.hi-paris.fr/2025/09/26/a...
The talk will be live-streamed: www.hi-paris.fr/2025/09/26/a...
AI Seminar Cycle – Hi! PARIS
www.hi-paris.fr
December 10, 2025 at 9:15 AM
Our @spyrosgidaris.bsky.social is speaking this morning (Wed, Dec 10th, 11:00 am Paris time) about "Latent Representations for Better Generative Image Modeling" in the Hi! PARIS - ELLIS monthly seminar.
The talk will be live-streamed: www.hi-paris.fr/2025/09/26/a...
The talk will be live-streamed: www.hi-paris.fr/2025/09/26/a...
Perfect timing for this keynote on open, re-purposable foundation models at #aiPULSE2025
@abursuc.bsky.social taking the stage this afternoon! 👇
@abursuc.bsky.social taking the stage this afternoon! 👇
I'm speaking at #aiPULSE2025 today on Open & re-purposable foundation models for the automotive industry.
The morning keynotes talked a lot about open source so my slide here might be timely.
The morning keynotes talked a lot about open source so my slide here might be timely.
December 4, 2025 at 12:14 PM
Perfect timing for this keynote on open, re-purposable foundation models at #aiPULSE2025
@abursuc.bsky.social taking the stage this afternoon! 👇
@abursuc.bsky.social taking the stage this afternoon! 👇
Check out our works at @NeurIPSConf #NeurIPS2025 this week!
We present 5 full papers + 1 workshop about:
💡 self-supervised & representation learning
🖼️ generative image models
🧠 finetuning and understanding LLMs & multimodal LLMs
🔎 feature upsampling
valeoai.github.io/posts/neurip...
We present 5 full papers + 1 workshop about:
💡 self-supervised & representation learning
🖼️ generative image models
🧠 finetuning and understanding LLMs & multimodal LLMs
🔎 feature upsampling
valeoai.github.io/posts/neurip...
December 3, 2025 at 10:50 PM
Check out our works at @NeurIPSConf #NeurIPS2025 this week!
We present 5 full papers + 1 workshop about:
💡 self-supervised & representation learning
🖼️ generative image models
🧠 finetuning and understanding LLMs & multimodal LLMs
🔎 feature upsampling
valeoai.github.io/posts/neurip...
We present 5 full papers + 1 workshop about:
💡 self-supervised & representation learning
🖼️ generative image models
🧠 finetuning and understanding LLMs & multimodal LLMs
🔎 feature upsampling
valeoai.github.io/posts/neurip...
Reposted by valeo.ai
We fermented our thoughts on understanding LoRA & ended up with IPA🍺
We found an asymmetry in LoRA: during training, A changes little & B eats most task-specific adaptation.
So we pre-train A to preserve information before adaptation w/ excellent parameter efficiency #NeurIPS2025 #CCFM 👇
We found an asymmetry in LoRA: during training, A changes little & B eats most task-specific adaptation.
So we pre-train A to preserve information before adaptation w/ excellent parameter efficiency #NeurIPS2025 #CCFM 👇
1/Serve your PEFT with a fresh IPA!🍺
Finetuning large models is cheaper thanks to LoRA, but is its random init optimal?🤔
Meet IPA: a feature-aware alternative to random projections
#NeurIPS2025 WS #CCFM Oral+Best Paper
Work w/
S. Venkataramanan @tuanhungvu.bsky.social @abursuc.bsky.social M. Cord
🧵
Finetuning large models is cheaper thanks to LoRA, but is its random init optimal?🤔
Meet IPA: a feature-aware alternative to random projections
#NeurIPS2025 WS #CCFM Oral+Best Paper
Work w/
S. Venkataramanan @tuanhungvu.bsky.social @abursuc.bsky.social M. Cord
🧵
December 2, 2025 at 11:16 AM
We fermented our thoughts on understanding LoRA & ended up with IPA🍺
We found an asymmetry in LoRA: during training, A changes little & B eats most task-specific adaptation.
So we pre-train A to preserve information before adaptation w/ excellent parameter efficiency #NeurIPS2025 #CCFM 👇
We found an asymmetry in LoRA: during training, A changes little & B eats most task-specific adaptation.
So we pre-train A to preserve information before adaptation w/ excellent parameter efficiency #NeurIPS2025 #CCFM 👇
Reposted by valeo.ai
1/Serve your PEFT with a fresh IPA!🍺
Finetuning large models is cheaper thanks to LoRA, but is its random init optimal?🤔
Meet IPA: a feature-aware alternative to random projections
#NeurIPS2025 WS #CCFM Oral+Best Paper
Work w/
S. Venkataramanan @tuanhungvu.bsky.social @abursuc.bsky.social M. Cord
🧵
Finetuning large models is cheaper thanks to LoRA, but is its random init optimal?🤔
Meet IPA: a feature-aware alternative to random projections
#NeurIPS2025 WS #CCFM Oral+Best Paper
Work w/
S. Venkataramanan @tuanhungvu.bsky.social @abursuc.bsky.social M. Cord
🧵
December 2, 2025 at 11:11 AM
1/Serve your PEFT with a fresh IPA!🍺
Finetuning large models is cheaper thanks to LoRA, but is its random init optimal?🤔
Meet IPA: a feature-aware alternative to random projections
#NeurIPS2025 WS #CCFM Oral+Best Paper
Work w/
S. Venkataramanan @tuanhungvu.bsky.social @abursuc.bsky.social M. Cord
🧵
Finetuning large models is cheaper thanks to LoRA, but is its random init optimal?🤔
Meet IPA: a feature-aware alternative to random projections
#NeurIPS2025 WS #CCFM Oral+Best Paper
Work w/
S. Venkataramanan @tuanhungvu.bsky.social @abursuc.bsky.social M. Cord
🧵
Reposted by valeo.ai
That was a cool project brillantly led by Ellington Kirby during his internship.
We were curious if we could train diffusion models on sets of point coordinates.
For images, this is a step towards spatial diffusion, with pixels reorganizing themselves, instead of diffusing in rgb values space only.
We were curious if we could train diffusion models on sets of point coordinates.
For images, this is a step towards spatial diffusion, with pixels reorganizing themselves, instead of diffusing in rgb values space only.
LOGen: Toward Lidar Object Generation by Point Diffusion
by: E. Kirby, @mickaelchen.bsky.social, R. Marlet, N. Samet
tl;dr: a diffusion-based method producing lidar point clouds of dataset objects, with an extensive control of the generation
📄 arxiv.org/abs/2412.07385
Code: ✅
by: E. Kirby, @mickaelchen.bsky.social, R. Marlet, N. Samet
tl;dr: a diffusion-based method producing lidar point clouds of dataset objects, with an extensive control of the generation
📄 arxiv.org/abs/2412.07385
Code: ✅
November 26, 2025 at 1:19 PM
That was a cool project brillantly led by Ellington Kirby during his internship.
We were curious if we could train diffusion models on sets of point coordinates.
For images, this is a step towards spatial diffusion, with pixels reorganizing themselves, instead of diffusing in rgb values space only.
We were curious if we could train diffusion models on sets of point coordinates.
For images, this is a step towards spatial diffusion, with pixels reorganizing themselves, instead of diffusing in rgb values space only.
Reposted by valeo.ai
Check out NAF: an effective ViT feature upsampler to produce excellent (and eye-candy) pixel-level feature maps.
NAF outperform both VFM-specific upsamplers (FeatUp, JAFAR) and VFM-agnostic methods (JBU, AnyUp) over multiple downstream tasks 👇
NAF outperform both VFM-specific upsamplers (FeatUp, JAFAR) and VFM-agnostic methods (JBU, AnyUp) over multiple downstream tasks 👇
Need pixel-level features from your backbone (DINOv3, CLIP, RADIO, FRANCA...)?
🚀Introducing NAF: A universal, zero-shot feature upsampler.
It turns low-res ViT features into pixel-perfect maps.
-⚡ Model-agnostic
-🥇 SoTA results
-🚀 4× faster than SoTA
-📈 Scales up to 2K res
🚀Introducing NAF: A universal, zero-shot feature upsampler.
It turns low-res ViT features into pixel-perfect maps.
-⚡ Model-agnostic
-🥇 SoTA results
-🚀 4× faster than SoTA
-📈 Scales up to 2K res
November 25, 2025 at 6:36 PM
Check out NAF: an effective ViT feature upsampler to produce excellent (and eye-candy) pixel-level feature maps.
NAF outperform both VFM-specific upsamplers (FeatUp, JAFAR) and VFM-agnostic methods (JBU, AnyUp) over multiple downstream tasks 👇
NAF outperform both VFM-specific upsamplers (FeatUp, JAFAR) and VFM-agnostic methods (JBU, AnyUp) over multiple downstream tasks 👇
Need pixel-level features from your backbone (DINOv3, CLIP, RADIO, FRANCA...)?
🚀Introducing NAF: A universal, zero-shot feature upsampler.
It turns low-res ViT features into pixel-perfect maps.
-⚡ Model-agnostic
-🥇 SoTA results
-🚀 4× faster than SoTA
-📈 Scales up to 2K res
🚀Introducing NAF: A universal, zero-shot feature upsampler.
It turns low-res ViT features into pixel-perfect maps.
-⚡ Model-agnostic
-🥇 SoTA results
-🚀 4× faster than SoTA
-📈 Scales up to 2K res
November 25, 2025 at 10:44 AM
Need pixel-level features from your backbone (DINOv3, CLIP, RADIO, FRANCA...)?
🚀Introducing NAF: A universal, zero-shot feature upsampler.
It turns low-res ViT features into pixel-perfect maps.
-⚡ Model-agnostic
-🥇 SoTA results
-🚀 4× faster than SoTA
-📈 Scales up to 2K res
🚀Introducing NAF: A universal, zero-shot feature upsampler.
It turns low-res ViT features into pixel-perfect maps.
-⚡ Model-agnostic
-🥇 SoTA results
-🚀 4× faster than SoTA
-📈 Scales up to 2K res
The team is at BMVC'25 @bmvcconf.bsky.social
to present three papers tackling challenges in 3D vision!
We are presenting new works on:
✨ Diffusion for LiDAR point-clouds
🌙 Depth estimation with light enhancement
🔄 Multimodal distillation for 3D semantic segmentation
👇 #BMVC2025
to present three papers tackling challenges in 3D vision!
We are presenting new works on:
✨ Diffusion for LiDAR point-clouds
🌙 Depth estimation with light enhancement
🔄 Multimodal distillation for 3D semantic segmentation
👇 #BMVC2025
November 24, 2025 at 9:00 AM
The team is at BMVC'25 @bmvcconf.bsky.social
to present three papers tackling challenges in 3D vision!
We are presenting new works on:
✨ Diffusion for LiDAR point-clouds
🌙 Depth estimation with light enhancement
🔄 Multimodal distillation for 3D semantic segmentation
👇 #BMVC2025
to present three papers tackling challenges in 3D vision!
We are presenting new works on:
✨ Diffusion for LiDAR point-clouds
🌙 Depth estimation with light enhancement
🔄 Multimodal distillation for 3D semantic segmentation
👇 #BMVC2025
Honored to host a very special guest today: Huy V. Vo, PhD alumnus of @valeoai.bsky.social
He presented his work on automatic data-curation strategies for self-supervised representation learning (DINOv2, DINOv3). Find out more about his research here: huyvvo.github.io
He presented his work on automatic data-curation strategies for self-supervised representation learning (DINOv2, DINOv3). Find out more about his research here: huyvvo.github.io
November 20, 2025 at 6:02 PM
Honored to host a very special guest today: Huy V. Vo, PhD alumnus of @valeoai.bsky.social
He presented his work on automatic data-curation strategies for self-supervised representation learning (DINOv2, DINOv3). Find out more about his research here: huyvvo.github.io
He presented his work on automatic data-curation strategies for self-supervised representation learning (DINOv2, DINOv3). Find out more about his research here: huyvvo.github.io
Thrilled to have Jayneel Parekh visiting us over a break in the CVPR sprint to talk about his exciting works in analyzing MLLMs representations. Check out his great work jayneelparekh.github.io
November 20, 2025 at 8:31 AM
Thrilled to have Jayneel Parekh visiting us over a break in the CVPR sprint to talk about his exciting works in analyzing MLLMs representations. Check out his great work jayneelparekh.github.io
Privileged to the diffusion master @nicolasdufour.bsky.social give to our team (full house) a tour of his excellent works in data and compute efficient diffusion models and a sneak preview of his latest MIRO work.
Check it out 👌
Check it out 👌
October 31, 2025 at 7:28 PM
Privileged to the diffusion master @nicolasdufour.bsky.social give to our team (full house) a tour of his excellent works in data and compute efficient diffusion models and a sneak preview of his latest MIRO work.
Check it out 👌
Check it out 👌
Our recent research will be presented at @iccv.bsky.social! #ICCV2025
We’ll present 5 papers about:
💡 self-supervised & representation learning
🌍 3D occupancy & multi-sensor perception
🧩 open-vocabulary segmentation
🧠 multimodal LLMs & explainability
valeoai.github.io/posts/iccv-2...
We’ll present 5 papers about:
💡 self-supervised & representation learning
🌍 3D occupancy & multi-sensor perception
🧩 open-vocabulary segmentation
🧠 multimodal LLMs & explainability
valeoai.github.io/posts/iccv-2...
October 17, 2025 at 10:10 PM
Our recent research will be presented at @iccv.bsky.social! #ICCV2025
We’ll present 5 papers about:
💡 self-supervised & representation learning
🌍 3D occupancy & multi-sensor perception
🧩 open-vocabulary segmentation
🧠 multimodal LLMs & explainability
valeoai.github.io/posts/iccv-2...
We’ll present 5 papers about:
💡 self-supervised & representation learning
🌍 3D occupancy & multi-sensor perception
🧩 open-vocabulary segmentation
🧠 multimodal LLMs & explainability
valeoai.github.io/posts/iccv-2...
The PhD graduation season in the team goes on!
Today, Corentin Sautier is defending his PhD on "Learning Actionable LiDAR Representations without Annotations".
Good luck! 🚀
Today, Corentin Sautier is defending his PhD on "Learning Actionable LiDAR Representations without Annotations".
Good luck! 🚀
Another great event for @valeoai.bsky.social team: a PhD defense of Corentin Sautier.
His thesis «Learning Actionable LiDAR Representations w/o Annotations» covers the papers BEVContrast (learning self-sup LiDAR features), SLidR, ScaLR (distillation), UNIT and Alpine (solving tasks w/o labels).
His thesis «Learning Actionable LiDAR Representations w/o Annotations» covers the papers BEVContrast (learning self-sup LiDAR features), SLidR, ScaLR (distillation), UNIT and Alpine (solving tasks w/o labels).
October 7, 2025 at 1:40 PM
The PhD graduation season in the team goes on!
Today, Corentin Sautier is defending his PhD on "Learning Actionable LiDAR Representations without Annotations".
Good luck! 🚀
Today, Corentin Sautier is defending his PhD on "Learning Actionable LiDAR Representations without Annotations".
Good luck! 🚀
“Has anyone heard about DUSt3R?”
All hands and hearts up in the room.
Honored to welcome @gabrielacsurka.bsky.social today to speak about the amazing work @naverlabseurope.bsky.social towards 3D Foundation Models
All hands and hearts up in the room.
Honored to welcome @gabrielacsurka.bsky.social today to speak about the amazing work @naverlabseurope.bsky.social towards 3D Foundation Models
October 6, 2025 at 12:38 PM
“Has anyone heard about DUSt3R?”
All hands and hearts up in the room.
Honored to welcome @gabrielacsurka.bsky.social today to speak about the amazing work @naverlabseurope.bsky.social towards 3D Foundation Models
All hands and hearts up in the room.
Honored to welcome @gabrielacsurka.bsky.social today to speak about the amazing work @naverlabseurope.bsky.social towards 3D Foundation Models
It’s PhD graduation season in the team!
Today, @bjoernmichele.bsky.social is defending his PhD on "Domain Adaptation for 3D Data"
Best of luck! 🚀
Today, @bjoernmichele.bsky.social is defending his PhD on "Domain Adaptation for 3D Data"
Best of luck! 🚀
October 6, 2025 at 12:09 PM
It’s PhD graduation season in the team!
Today, @bjoernmichele.bsky.social is defending his PhD on "Domain Adaptation for 3D Data"
Best of luck! 🚀
Today, @bjoernmichele.bsky.social is defending his PhD on "Domain Adaptation for 3D Data"
Best of luck! 🚀
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/...
CoRL 2025 is just around the corner in Seoul, Korea!
🤖 🚗
We're excited to present our latest research and connect with the community.
#CoRL2025
🤖 🚗
We're excited to present our latest research and connect with the community.
#CoRL2025
September 24, 2025 at 4:47 PM
CoRL 2025 is just around the corner in Seoul, Korea!
🤖 🚗
We're excited to present our latest research and connect with the community.
#CoRL2025
🤖 🚗
We're excited to present our latest research and connect with the community.
#CoRL2025
We're thrilled to join the ambitious ELLIOT project towards European large open-multimodal foundation models.
The project kick-off is today!
The project kick-off is today!
🚀 A new era in European #AIresearch begins!
ELLIOT is a €25M #HorizonEurope project launching July 2025 to build open, trustworthy Multimodal Generalist Foundation Models.
30 partners, 12 countries, EU values.
🔗 Press release: apigateway.agilitypr.com/distribution...
ELLIOT is a €25M #HorizonEurope project launching July 2025 to build open, trustworthy Multimodal Generalist Foundation Models.
30 partners, 12 countries, EU values.
🔗 Press release: apigateway.agilitypr.com/distribution...
July 8, 2025 at 6:40 AM
We're thrilled to join the ambitious ELLIOT project towards European large open-multimodal foundation models.
The project kick-off is today!
The project kick-off is today!
Reposted by valeo.ai
ELSA will be extended!🎉
The European Commission decided to extend the duration of our Lighthouse on Secure and Safe AI. We will now run for an additional 12 months until August 2026.
Find more details in the official press release:
elsa-ai.eu/official-ext...
Congratulations to the network!
The European Commission decided to extend the duration of our Lighthouse on Secure and Safe AI. We will now run for an additional 12 months until August 2026.
Find more details in the official press release:
elsa-ai.eu/official-ext...
Congratulations to the network!
June 17, 2025 at 10:42 AM
ELSA will be extended!🎉
The European Commission decided to extend the duration of our Lighthouse on Secure and Safe AI. We will now run for an additional 12 months until August 2026.
Find more details in the official press release:
elsa-ai.eu/official-ext...
Congratulations to the network!
The European Commission decided to extend the duration of our Lighthouse on Secure and Safe AI. We will now run for an additional 12 months until August 2026.
Find more details in the official press release:
elsa-ai.eu/official-ext...
Congratulations to the network!
Check out our MOCA self-supervised learning approach unifying the learning principles of both discriminative & masked image modelling paradigms.
With a non-linear path, MOCA has been accepted at #TMLR and presented in the TMLR poster session at #iclr2025
With a non-linear path, MOCA has been accepted at #TMLR and presented in the TMLR poster session at #iclr2025
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 8:32 AM
Reposted by valeo.ai
Check out DIP (Dense In-context Post-training) @iccv.bsky.social: an effective post-training strategy to unleash dense awareness of features from your favorite pre-trained encoder (DINOv2, CLIP, MAE)
We leverage meta-learning-like pseudo-tasks w/ pseudo-labels.
Kudos @ssirko.bsky.social 👇
#iccv2025
We leverage meta-learning-like pseudo-tasks w/ pseudo-labels.
Kudos @ssirko.bsky.social 👇
#iccv2025
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 7:24 PM
Check out DIP (Dense In-context Post-training) @iccv.bsky.social: an effective post-training strategy to unleash dense awareness of features from your favorite pre-trained encoder (DINOv2, CLIP, MAE)
We leverage meta-learning-like pseudo-tasks w/ pseudo-labels.
Kudos @ssirko.bsky.social 👇
#iccv2025
We leverage meta-learning-like pseudo-tasks w/ pseudo-labels.
Kudos @ssirko.bsky.social 👇
#iccv2025
How to make your DINOv2 excel at dense in-context scene understanding tasks.
Check out DIP an effective post-training strategy by @ssirko.bsky.social @spyrosgidaris.bsky.social
@vobeckya.bsky.social @abursuc.bsky.social and Nicolas Thome 👇
#iccv2025
Check out DIP an effective post-training strategy by @ssirko.bsky.social @spyrosgidaris.bsky.social
@vobeckya.bsky.social @abursuc.bsky.social and Nicolas Thome 👇
#iccv2025
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 7:35 PM
How to make your DINOv2 excel at dense in-context scene understanding tasks.
Check out DIP an effective post-training strategy by @ssirko.bsky.social @spyrosgidaris.bsky.social
@vobeckya.bsky.social @abursuc.bsky.social and Nicolas Thome 👇
#iccv2025
Check out DIP an effective post-training strategy by @ssirko.bsky.social @spyrosgidaris.bsky.social
@vobeckya.bsky.social @abursuc.bsky.social and Nicolas Thome 👇
#iccv2025