Pleased to announce our new work "Sequential Controlled Langevin Diffusions": arxiv.org/abs/2412.07081 We study the classical problem of sampling from unnormalized densities by bridging diffusion-based sampling with Sequential Monte Carlo methods. Our SCLD method allows SDE

📢 Super excited to announce the first ever Frontiers of Probabilistic Inference: Learning meets Sampling workshop at #ICLR2025 ICLR 2026! 🔗 website: sites.google.com/view/fpiworksh… We invite submissions on sampling, Bayesian inference, accelerating sampling in AI4Science,

I'm happy to say that SCLD has been accepted at ICLR25!

We have a new cool preprint with Cheuk Kit Lee. We developed a sweet Sequential Monte Carlo algorithm for unbiased samples from a tempered distribution p(x0)p(y|x0)^α and applied it to discrete diffusion for text arxiv.org/abs/2502.06079. Huge thanks to Francisco Vargas Michael Albergo