"Accept (spotlight)" at ICML'26 😎 Our paper brings particle filters back to life: autoregressive diffusion models + posterior sampling yield optimal proposals for Bayesian filtering, scaling up to GenCast-sized systems. arxiv.org/abs/2605.20028 w/ Thomas Savary and @francois-r…
Who's Who of AI
Gilles Louppe
AI for Science, deep generative models, inverse problems. Professor of AI and deep learning @universitedeliege.bsky.social. Previously @CERN, @nyuniversity. https://glouppe.github.io
What they're sharing
[2605.20028] Training-Free Bayesian Filtering with Generative Emulators arxiv.org
Sakana AI sakana.ai
View on Bluesky →
Conditioning Gaussian Processes on Almost Anything arxiv.org
View on Bluesky →
ReViT: Rotational-equivariant Vision Transformers for Neural PDE Solvers tum-pbs.github.io
View on Bluesky →
Articles & links
Gilles Louppe reposted
Sakana Fugu — a multiagent system for general tasks that performs on par with the Mythos Preview It uses a collection of open and closed models, including itself, to handle all angles of a problem — model selection, delegation, verification and synthesis sakana.ai/fugu-release/
Gilles Louppe reposted
Henry and co-authors arxived a really exciting paper today (arxiv.org/abs/2605.21041) on a new paradigm for Gaussian Process regression where you can condition on (almost) ANYTHING, even LLM prompts!
Gilles Louppe reposted
Congratulations to Hao for his ICML Oral on rotationally equivariant transformers: tum-pbs.github.io/revit-web/ 👍 The key idea is to transform physical fields into local canonical coordinate systems, enabling standard self-attention while preserving physical symmetries
Their own posts
Recent commentary
I am just old and grumpy, but I can't help but notice AI-generated slides and speakers reading their AI-generated scripts full of empty buzzwords without any substance, insight, and pedagogy. #ICML2026 #ICML
Their network
In Gilles Louppe's orbit
Center = Gilles Louppe. 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.