And you can consider a bistochastic kernel - Sinkhorn: arxiv.org/abs/2603.12366 (which is a sinkformer arxiv.org/abs/2110.11773) which leads to an almost perfect translation of the mean.
Who's Who of AI
Gabriel Peyré
Why follow
Researcher with public evidence across AI research.
- AI signals
- 1 past 30d
- Sources
- 1 distinct domains
- Discussions
- 2 past 30d
- Latest signal
- 21d ago
CNRS researcher at ENS
What they're sharing
Sinkhorn-Drifting Generative Models arxiv.org
Sinkformers: Transformers with Doubly Stochastic Attention arxiv.org
Demystifying MMD GANs arxiv.org
Generative Modeling via Drifting arxiv.org
IA for theory speakerdeck.com
L'IA générative face au concours d'entrée à l'École normale supérieure blogs.mediapart.fr
View on Bluesky →
Articles & links
And you can consider a bistochastic kernel - Sinkhorn: arxiv.org/abs/2603.12366 (which is a sinkformer arxiv.org/abs/2110.11773) which leads to an almost perfect translation of the mean.
It is a comparison between - MMD: a kernel (2017) arxiv.org/abs/1801.01401 - Drifting: a stochastic kernel (2026) arxiv.org/abs/2602.04770
It is a comparison between - MMD: a kernel (2017) arxiv.org/abs/1801.01401 - Drifting: a stochastic kernel (2026) arxiv.org/abs/2602.04770
Slides for an introductory talk on IA for maths. speakerdeck.com/gpeyre/ia-fo...
Gabriel Peyré reposted
L'IA générative face au concours d'entrée à l'École normale supérieure blogs.mediapart.fr/david-monnia...
Their own posts
Recent commentary
Thanks to LLMs, I think the exponent for the (refutal) of Erdos unit distance conjecture will be more famous than omega (the exponent for matrix multiplication)!
Their network
In Gabriel Peyré's orbit
Center = Gabriel Peyré. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.