
Paul Jeha @ICLR 2025
@jeha_paul
PhD student in Copenhagen / Generative Models - Diffusion & exploring. pablo2909.github.io/pauljeha/ the work is mysterious and important
ID: 1521767908904517633
04-05-2022 08:25:49
66 Tweet
132 Takipçi
226 Takip Edilen





Excited to share that our paper on reducing variance in diffusion models with control variates is published at the SPIGM ICML Conference workshop. Come check it out! Thanks a lot to will grathwohl Jes Frellsen @carlhenrikek Michael Riis for the collaboration! openreview.net/pdf?id=YqFIzHA…





Heading to Vancouver for NeurIPS to present our paper “On Conditional Diffusion Models for PDE Simulation”. I'll be together with Sasha and Cristiana Diaconu at poster 2500 during Thursday’s late afternoon session. Looking forward exciting discussions and meeting new people!





Tweeting again about sampling, my favourite 2024 Monte Carlo paper is arxiv.org/abs/2307.01050 by F. Vargas, Shreyas Padhy, D. Blessing & N. Nüsken: . Propose a "simple" loss to learn the drift you need to add to Langevin to follow a fixed probability path.

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



Francisco Vargas and Michael Albergo with a combined talk on sampling inference and transport at #FPIworkshop.



Heading to Microsoft Research over the summer to intern and work on some cool diffusion stuff 🫶🏽 hit me up if you want to grab a coffee

[1/9]🚀Excited to share our new work, RNE! A plug-and-play framework for everything about diffusion model density and control: density estimation, inference-time control & scaling, energy regularisation. More details👇 Joint work with Jose Miguel Hernández-Lobato Yuanqi Du, Francisco Vargas
![Jiajun He (@jiajunhe614) on Twitter photo [1/9]🚀Excited to share our new work, RNE! A plug-and-play framework for everything about diffusion model density and control: density estimation, inference-time control & scaling, energy regularisation. More details👇
Joint work with <a href="/jmhernandez233/">Jose Miguel Hernández-Lobato</a> <a href="/YuanqiD/">Yuanqi Du</a>, Francisco Vargas [1/9]🚀Excited to share our new work, RNE! A plug-and-play framework for everything about diffusion model density and control: density estimation, inference-time control & scaling, energy regularisation. More details👇
Joint work with <a href="/jmhernandez233/">Jose Miguel Hernández-Lobato</a> <a href="/YuanqiD/">Yuanqi Du</a>, Francisco Vargas](https://pbs.twimg.com/media/GtQ_FbnWMAA2KAt.png)