CVPR@Paris 2026 🇫🇷 — June 1st, co-organised by ELLIS Unit Paris. A one-day local event ahead of CVPR, open to all. Oral & poster sessions for CVPR 2026, CVPR workshops & ICLR 2026 papers.
🔗 https://cvprinparis.github.io/CVPR2026InParis/
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 📉
Familiar names among #ICCV2025 Outstanding Reviewers from our team 😇
Antoine Guédon @antoine-guedon.bsky.social
Sinisa Stekovic
Renaud Marlet
👏
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
Thrilled to share that MIRO is accepted to ICML 2026 @icmlconf.bsky.social ! 🎉
By training on the reward scores, we can simply condition the model on high rewards at inference time to guarantee top-tier, aligned outputs.
We’ve updated our paper with some additional results!
The default paradigm of post-training text-to-image generators includes post-hoc selection of generated images, and subsequent training with one reward model to align the generator to the reward, typi...
11/11 📚 Resources:
📄 Paper: arxiv.org/abs/2506.24096
💻 Code: github.com/Anttwo/MILo
🌐 Project Page: anttwo.github.io/milo/
Huge thanks to my amazing co-authors and the supporting institutions! 🙏
Surflo: Consistent 3D Surface Flow Model with Global State
@antoine-guedon.bsky.social, Shu Nakamura, @nicolasdufour.bsky.social, Jiahui Lei, Ko Nishino, @akanazawa.bsky.social
arxiv.org/abs/2606.13644
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 📉
CVPR@Paris is starting!
🚨 arxiv.org/abs/2604.06129
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
This paper is the result of doing a lab-wide hackathon on an idea I've had for some time. Probably the paper with the highest number of authors I've ever done.
It's a CVPR Findings 26.
Thread 🧵👇
Project page for MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction
This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention. PoM aggregates input tokens into a comp...
🔴FROM BLOBS TO SPOKES🚲
We released paper and code for GaussianWrapping, our latest work on RGB-to-mesh!
We introduce explicit geometric field formulas for Gaussians (occupancy&normals), allowing for fast and sharp surface reco (see bicycle spokes).
So happy about this work!🤩
CVPR@Paris 2026 🇫🇷 — June 1st, co-organised by ELLIS Unit Paris. A one-day local event ahead of CVPR, open to all. Oral & poster sessions for CVPR 2026, CVPR workshops & ICLR 2026 papers.
🔗 https://cvprinparis.github.io/CVPR2026InParis/
Antoine Guédon
Antoine Guédon
ELLIS
1/n 🧵 Introducing Gaussian Wrapping — a principled framework for extracting high-quality meshes from 3DGS! 🚲
We recover thin structures, like bicycle spokes, where all prior methods fail.
Follow the thread for a brief overview and links!
Video
1/n🚀Gaussians > Differentiable function > Mesh?
Check out our new work: MILo: Mesh-In-the-Loop Gaussian Splatting!
🎉Accepted to SIGGRAPH Asia 2025 (TOG)
MILo is a novel differentiable framework that extracts meshes directly from Gaussian parameters during training.
🧵👇
