Nicolas DUFOUR profile picture

Nicolas DUFOUR

PostDoc at Kyutai and UC Berkeley

About me

I’m a postdoc at Kyutai and UC Berkeley, working with Patrick Pérez and Alyosha Efros. I’m currently exploring the representation capacities of generative models.

I did my PhD at the IMAGINE (ENPC) and VISTA (École Polytechnique) labs, under the supervision of David Picard and Vicky Kalogeiton. My thesis focused on efficient conditional generative models, and I worked on GANs and diffusion models.

Full CV (PDF)
Research themes
Training with less
Image generation is a great place to make progress, but other fields rarely have unlimited data. I look for methods that need less data and compute, so that this progress carries over to those fields and stays within reach of academic labs.
Generative geolocation
I like how much one photo can reveal about where it was taken: the plants, the road markings, the light. Reading these clues takes broad knowledge of places and cultures, and since they are often ambiguous, generative models are a natural fit.
Generation beyond images
I like taking generative models past still images, to 3D scenes, camera motion and video you can interact with. Each new setting tests what these models really understand about the world.
How generative models work
Beyond any single application, I'm curious about generative models themselves: why they work so well, and what they really learn about the data.

News

2026
2025
2024
2023
  • Organized the first edition of the IMAGINE Hackathon.
2022
2021

Publications

Recent Preprints

Rethinking Neural Thickets Without Weight Perturbations
Arxiv Preprint
Rethinking Video Autoencoders for Interactive World Models
Arxiv Preprint
Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective
Arxiv Preprint

2026

Diffusable Latents from Structure-Agnostic Distillation
NeurIPS 2026 Workshop on Principles of Generative Modeling
Surflo: Consistent 3D Surface Flow Model with Global State
NeurIPS 2026 (Oral)
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation
NeurIPS 2026
The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation
ECCV 2026 Workshop on Empirical Theory in Representation Learning (E.T.) (Oral)
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency
ICML 2026
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
CVPR Findings 2026

2025

DIPSY: Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance
Luc Boudier, Loris Manganelli, Eleftherios Tsonis, Nicolas Dufour, Vicky Kalogeiton
BMVC 2025
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
CVPR 2025
How far can we go with ImageNet for Text-to-Image generation?
Arxiv Preprint

2024

Analysis of Classifier-Free Guidance Weight Schedulers
TMLR
E.T. the Exceptional Trajectories: Text-to-Camera-Trajectory Generation with Character Awareness.
ECCV 2024
Don't drop your samples! Coherence-aware training benefits Conditional diffusion
CVPR 2024 (Highlight)
OpenStreetView-5M: The Many Roads to Global Visual Geolocation
CVPR 2024

2023

Machine Learning for Brain Disorders: Transformers and Visual Transformers
Springer, Machine Learning for Brain Disorders

2022

SCAM! Transferring humans between images with Semantic Cross Attention Modulation
ECCV 2022

Teaching

INF473V
Deep Learning in Computer Vision
Teaching Assistant · Ecole Polytechnique
Apr – Jun 2024
  • Helped supervise the practical sessions of the course.
  • Created a Kaggle competition for the students end of the course project. The goal was to create a classifier but we only provided them with the val and test data. They needed to create their own training data with pretrained diffusion models. The goal was to classify among 37 different cheeses.
INF473V
Deep Learning in Computer Vision
Teaching Assistant · Ecole Polytechnique
Feb – Jun 2023
  • Helped supervise the practical sessions of the course.
  • Built a new practical session on Transformers.
  • Created a Kaggle competition for the students end of the course project. The goal was to classify synthetic images in a weakly supervised setting.
INF573
Image Analysis and Computer Vision
Teaching Assistant · Ecole Polytechnique
Nov 2022
  • Helped supervise students projects.

Open Source

Contributions

Projects

kyutai-labs
structure-agnostic-distillation
Diffusable Latents from Structure-Agnostic Distillation
NeurIPS 2026 Workshop on Principles of Generative Modeling
Anttwo
Surflo
Surflo: Consistent 3D Surface Flow Model with Global State
NeurIPS 2026
kyutai-labs
ovie
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation
NeurIPS 2026
kyutai-labs
logit-psv
Rethinking Neural Thickets Without Weight Perturbations
Arxiv Preprint
kyutai-labs
cadre-autoencoders-and-world-models
Rethinking Video Autoencoders for Interactive World Models
Arxiv Preprint
nicolas-dufour
miro
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency
ICML 2026
davidpicard
pom
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
CVPR Findings 2026
eleftsonis
DIPSY
DIPSY: Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance
BMVC 2025
nicolas-dufour
plonk
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
CVPR 2025
lucasdegeorge
T2I-ImageNet
How far can we go with ImageNet for Text-to-Image generation?
Arxiv Preprint
robincourant
DIRECTOR
E.T. the Exceptional Trajectories: Text-to-Camera-Trajectory Generation with Character Awareness.
ECCV 2024
nicolas-dufour
CAD
Don't drop your samples! Coherence-aware training benefits Conditional diffusion
CVPR 2024
gastruc
osv5m
OpenStreetView-5M: The Many Roads to Global Visual Geolocation
CVPR 2024
nicolas-dufour
SCAM
SCAM! Transferring humans between images with Semantic Cross Attention Modulation
ECCV 2022

Miscellaneous

Talks

2026
2025
  • Dec 18
    Talk at MIT in Philip Isola's group
    Controllable and Efficient Generative Models
  • Dec 17
    Talk at Cornell Tech in Andrew Owens's group
    Controllable and Efficient Generative Models
  • Dec 16
    Talk at NYU in Saining Xie's group
    Controllable and Efficient Generative Models
  • Dec 10
    Talk at BAIR in Alyosha Efros's group
    Controllable and Efficient Generative Models
  • Oct 30
    Talk at ValeoAI
    Controllable and Efficient Generative Models
  • Oct 23
    Talk at Kyutai
    Controllable and Efficient Generative Models
  • Jun 25
    Podcast Underscore_
    Around the World in 80 Timesteps
2024
2023
  • Apr 12
    IMAGINE Seminar
    LLM advances in 2023
  • Apr 12
    IMAGINE Seminar
    Recent advances in diffusion models
2022
  • Apr 20
    IMAGINE Seminar
    Presentation of the Perceiver papers
  • Feb 10
    GeoVic Seminar
    SCAM! Transferring humans between images with Semantic Cross Attention Modulation
  • Jan 5
    IMAGINE Seminar
    Tutorial on GANs
2021
  • Oct 6
    IMAGINE Seminar
    SCAM! Transferring humans between images with Semantic Cross Attention Modulation

Reviewing

2024
2023
2022

Awards

Others

  • I have co-organized the first edition of IMAGINE Hackaton. The topic was geolocation
    Jul 2023
  • I'm co-organizing the IMAGINE reading group for 2023-2024
    Jun 2023