iiinova — where your digital self keeps evolving

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 06/07/2026

New state of the art in one-step image generation 🏆 One forward pass. The method is so simple it's almost unsettling: no teacher, no discriminator, no denoising trajectory 🧵

151

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 01/06/2026

NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering tl;dr: a universal, zero-shot ViT feature upsampler by: L. Chambon, P. Couairon, E. Zablocki, A. Boulch, N. Thome, M. Cord 📄: arxiv.org/abs/2511.18452 bsky.app/profile/vale...

141

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 01/06/2026

Our recent research will be presented at #CVPR2026 @cvprconference.bsky.social! We’ll present nine papers in the main conference and we’ll be speaking in two workshops & one tutorial Here is a quick overview on the works we’ll be presenting in Denver: valeoai.github.io/posts/cvpr-2...

1134

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 21/04/2026

This week, at #ICLR2026, we are presenting: RAP: 3D Rasterization Augmented End-to-End Planning 👉 Project page w/ code: alan-lanfeng.github.io/RAP/ Collab with VITA lab from EPFL @iclr-conf.bsky.social #Bench2Drive #navsim

062

Reposted by Éloi Zablocki

Sophia Sirko-Galouchenko 🇺🇦 @ssirko.bsky.social · 17/04/2026

1/n New paper - V-GIFT 🎁 Self-supervised tasks like rotation prediction or colorization were big in 2018. Do they still matter? Yes. We turn them into visual instruction tuning data for MLLMs. Result: models rely more on the image and perform better on vision tasks 👀

1238

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 19/03/2026

Congratulations to our researchers Renaud Marlet and @abursuc.bsky.social on their repeated recognition as outstanding reviewers at #CVPR, #ICCV, and #ECCV👏👏👏 Thank you for your sharp insights, kindness, and dedication. It's key for the field to count on reviewers like you!

1154

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 09/01/2026

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 👇

1104

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 03/12/2025

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...

151

Reposted by Éloi Zablocki

Yuan Yin @yuanyinnn.bsky.social · 02/12/2025

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 🧵

1122

Éloi Zablocki @eloizablocki.bsky.social · 25/11/2025

Off-the-shelf feature upscaling from any vision model without retraining, with NAF: 🥇 SoTA results ⚡️ High throughput 🧠 Zero-shot generalization 😍 Code available --> NAF brings *pixel-level* features to your frozen vision backbones 🔎 👇 Check out the details!

140

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 24/09/2025

CoRL 2025 is just around the corner in Seoul, Korea! 🤖 🚗 We're excited to present our latest research and connect with the community. #CoRL2025

152

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 09/04/2025

LLM-wrapper: Black-Box Semantic-Aware Adaptation of VLMs for Referring Expression Comprehension (REC), by A. Cardiel, @eloizablocki.bsky.social, E. Ramzi, O. Simeoni, @matthieucord.bsky.social Boost VLM perf by tuning an LLM to reason on its outputs! It's black-box🔒 & efficient⚡ (< 7h on 1 GPU)

121

Reposted by Éloi Zablocki

David Picard @davidpicard.eurosky.social · 21/03/2025

🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷 Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa... Big 🧵👇 with details!

713652

Reposted by Éloi Zablocki

valeo.ai @valeoai.bsky.social · 24/02/2025

🚗 Ever wondered if an AI model could learn to drive just by watching YouTube? 🎥👀 We trained a 1.2B parameter model on 1,800+ hours of raw driving videos. No labels. No maps. Just pure observation. And it works! 🤯 🧵👇 [1/10]

1257

Reposted by Éloi Zablocki

Daphne Cornelisse @daphne-cornelisse.bsky.social · 20/02/2025

GPUDrive got accepted to ICLR 2025! With that, we release GPUDrive v0.4.0! 🚨 You can now install the repo and run your first fast PPO experiment in under 10 minutes. I’m honestly so excited about the new opportunities and research the sim makes possible. 🚀 1/2

2454

Reposted by Éloi Zablocki

Thomas Wolf @thomwolf.bsky.social · 19/02/2025

After 6+ months in the making and over a year of GPU compute, we're excited to release the "Ultra-Scale Playbook": hf.co/spaces/nanot... A book to learn all about 5D parallelism, ZeRO, CUDA kernels, how/why overlap compute & coms with theory, motivation, interactive plots and 4000+ experiments!

hf.co

The Ultra-Scale Playbook - a Hugging Face Space by nanotron

The ultimate guide to training LLM on large GPU Clusters

217952

Reposted by Éloi Zablocki

David Picard @davidpicard.eurosky.social · 12/12/2024

We @imagineenpc.bsky.social are slowly but surely entering our proposals for master's degree internships here: docs.google.com/document/d/1... These are 6 months projects that typically correspond to the end-of-study project in the French curriculum. Probably more offers to come, check it regularly.

docs.google.com

2025 IMAGINE Internships

2025 Internship proposals at IMAGINE IMAGINE is a top research group on computer vision and machine learning. It is part of the LIGM lab and hosted at École des Ponts ParisTech (ENPC), about 25 min f...

23211

Éloi Zablocki @eloizablocki.bsky.social · 29/11/2024

🥐 Building a Computer Vision FR Starter Pack! 👉 Who else should be included? Comment below or DM me to be added go.bsky.app/dfvcLZ

4254

Reposted by Éloi Zablocki

Chris Offner @chrisoffner3d.bsky.social · 28/11/2024

Welcome to all the newcomers! Here's a starter pack for the 3D Computer Vision community: go.bsky.app/Cfm9XFe

74612

Éloi Zablocki @eloizablocki.bsky.social · 28/11/2024

@csprofkgd.bsky.social Hello, thanks for maintaining the computer vision starter packs. Is it possible to be included? Thanks 🙏

110