ND
Nicolas Dufour
cs.CVcs.LGcs.AI
On Valency
published · living versionsW_4tf2r79f·v1 · currentpublished
Rethinking Neural Thickets Without Weight Perturbations
with Elouan Gardès, Amil Dravid, Patrick Pérez, Loic Landrieu
1 version
W_ssnhu7t7·v1published
Preprints & journals
17 papers in the corpus · 2022–2026Diffusable Latents from Structure-Agnostic Distillation2609.39657v1 · Adrien Ramanana Rahary, Nicolas Dufour, Patrick P'erez et al.2026 · 0 citationsarXiv
The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation2606.20536v1 · Nicolas Dufour, Alexei A. Efros, Patrick P'erez2026 · 0 citationsarXiv
Surflo: Consistent 3D Surface Flow Model with Global State2606.13644v1 · Antoine Gu'edon, Shu Nakamura, Nicolas Dufour et al.2026 · 0 citationsarXiv
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer2604.06129v1 · David Picard, Nicolas Dufour, Lucas Degeorge et al.2026 · 0 citationsarXiv
One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation2603.23488v3 · Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez et al.2026 · 0 citationsarXiv
Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective2603.09936v2 · Erkan Turan, Nicolas Dufour, Maks Ovsjanikov2026 · 0 citationsarXiv
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency2510.25897v2 · Nicolas Dufour, Lucas Degeorge, Arijit Ghosh et al.2025 · 0 citationsarXiv
Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance2509.22635v1 · Luc Boudier, Loris Manganelli, Eleftherios Tsonis et al.2025 · 0 citationsarXiv
How far can we go with ImageNet for Text-to-Image generation?2502.21318v4 · L. Degeorge, A. Ghosh, N. Dufour et al.2025 · 0 citationsarXiv
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation2412.06781v1 · Nicolas Dufour, David Picard, Vicky Kalogeiton et al.2024 · 6 citationsarXiv
PoM: Efficient Image and Video Generation with the Polynomial Mixer2411.12663v1 · David Picard, Nicolas Dufour2024 · 0 citationsarXiv
E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness2407.01516v1 · Robin Courant, Nicolas Dufour, Xi Wang et al.2024 · 4 citationsarXiv
Don't drop your samples! Coherence-aware training benefits Conditional diffusion2405.20324v2 · Nicolas Dufour, Victor Besnier, Vicky Kalogeiton et al.2024 · 4 citationsarXiv
OpenStreetView-5M: The Many Roads to Global Visual Geolocation2404.18873v1 · Guillaume Astruc, Nicolas Dufour, Ioannis Siglidis et al.2024 · 18 citationsarXiv
Analysis of Classifier-Free Guidance Weight Schedulers2404.13040v2 · Xi Wang, Nicolas Dufour, Nefeli Andreou et al.2024 · 0 citationsTransactions on Machine Learning Research, 2835-8856, 2024
Machine Learning for Brain Disorders: Transformers and Visual Transformers2303.12068v1 · Robin Courant, Maika Edberg, Nicolas Dufour et al.2023 · 0 citationsarXiv
SCAM! Transferring humans between images with Semantic Cross Attention Modulation2210.04883v1 · Nicolas Dufour, David Picard, Vicky Kalogeiton2022 · 13 citationsarXiv
Career total: 21 works. 17 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.