Profile avatar
sigmabayesian.bsky.social
Visiting Researcher @NYU Courant, CILVR. PhD student @TU Denmark, MLLS(https://mlls.dk). Probabilistic ML/DL. Nth order Markovian. Support Manifolds and latents. Previously intern @SonyAI in deep generative modelling. web: http://uppalanshuk.github.io
6 posts 604 followers 396 following
Getting Started
Posts 7 Comments 5

Excited about 🎓 Generative Modeling Summer School / Statlearn 🗓️ Mar 31 - Apr 4, 2025, France ℹ️ gemss.ai 🎟️ Deadline: Jan 27, 2025 🧑‍🏫 Yingzhen Li, @stephanmandt.bsky.social, Aude Sportisse, Anna Korba, @glouppe.bsky.social, @jesfrellsen.bsky.social, @pamattei.bsky.social, @jmtomczak.bsky.social, TBA

submitted 59 days ago • 0 comments

🔥You enjoyed @arnauddoucet.bsky.social talk but want even more Schrodinger Bridge? Come talk to me at our poster! 🔷Schrodinger Bridge Flow for Unpaired Data Translation 🔊 East Exhibit Hall A-C #2504 Work done with my amazing collaborators Ira Korshunova Andriy Mnih and @arnauddoucet.bsky.social

submitted 87 days ago • 0 comments

Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition! We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423

submitted 103 days ago • 12 comments

This. Training a high dimensional discriminator as a proxy to the log likelihood and doing it so successfully had a ripple effect. Also people forget styleGAN, progressiveGAN and text to image GAN models.

submitted 102 days ago • 0 comments

This year, there are 16 positions at CNRS in computer science (8 in "applied" domains → ask me - 8 on "fundamental" domains → ask the other David). @mathurinmassias.bsky.social has a good list of advice mathurinm.github.io/cnrs_inria_a... Official 🔗 www.ins2i.cnrs.fr/en/cnrsinfo/... Don't wait!

submitted 107 days ago • 2 comments

For those who don’t know yet, I am organising an online talk series together with Arno Solin on “Advances in Probabilistic Machine Learning (APML)”. It’s free for everyone to join and support early career researchers! You can register and check out the schedule here: aaltoml.github.io/apml/

submitted 110 days ago • 2 comments

Alright, let’s try out that 🦋 thing! I’ll try to post some little pieces about machine learning, uncertainty, and applied maths in general!

submitted 112 days ago • 0 comments