Anshuk Uppal's Avatar

Anshuk Uppal

@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

620 Followers  |  398 Following  |  6 Posts  |  Joined: 17.11.2024  |  1.4318

Latest posts by sigmabayesian.bsky.social on Bluesky

Generative Modeling Summer School (GeMSS)

Excited about

๐ŸŽ“ Generative Modeling Summer School / Statlearn
๐Ÿ—“๏ธ Mar 31 - Apr 4, 2025, France

โ„น๏ธ gemss.ai
๐ŸŽŸ๏ธ Deadline: Jan 27, 2025

๐Ÿง‘โ€๐Ÿซ Yingzhen Li, @stephanmandt.bsky.social, Aude Sportisse, Anna Korba, @glouppe.bsky.social, @jesfrellsen.bsky.social, @pamattei.bsky.social, @jmtomczak.bsky.social, TBA

10.01.2025 10:42 โ€” ๐Ÿ‘ 24    ๐Ÿ” 11    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 1

๐Ÿ”ฅYou enjoyed @arnauddoucet.bsky.social talk but want even more Schrodinger Bridge? Come talk to me at our poster!

๐Ÿ”ทSchrodinger Bridge Flow for Unpaired Data Translation
๐Ÿ”Š East Exhibit Hall A-C #2504

Work done with my amazing collaborators Ira Korshunova
Andriy Mnih and @arnauddoucet.bsky.social

13.12.2024 17:52 โ€” ๐Ÿ‘ 17    ๐Ÿ” 2    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Video thumbnail

Anne Gagneux, Sรฉgolรจne 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

27.11.2024 09:00 โ€” ๐Ÿ‘ 354    ๐Ÿ” 102    ๐Ÿ’ฌ 12    ๐Ÿ“Œ 11

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.

28.11.2024 05:53 โ€” ๐Ÿ‘ 2    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

This year, there are 16 positions at CNRS in computer science (8 in "applied" domains โ†’ ask me - 8 on "fundamental" domains โ†’ ask the other David).

@mathurinmassias.bsky.social has a good list of advice mathurinm.github.io/cnrs_inria_a...

Official ๐Ÿ”— www.ins2i.cnrs.fr/en/cnrsinfo/...

Don't wait!

23.11.2024 19:33 โ€” ๐Ÿ‘ 32    ๐Ÿ” 18    ๐Ÿ’ฌ 2    ๐Ÿ“Œ 1

Highly interested! Dropping you an email.

23.11.2024 05:32 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

Hi Nathan, I am interested in applying but the job link doesn't seem to be working?

23.11.2024 02:05 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Preview
Seminar on Advances in Probabilistic Machine Learning This seminar series aims to provide a platform for young researchers (PhD student or post-doc level) to give invited talks about their research, intending to have a diverse set of talks & speakers on ...

For those who donโ€™t know yet, I am organising an online talk series together with Arno Solin on โ€œAdvances in Probabilistic Machine Learning (APML)โ€.

Itโ€™s free for everyone to join and support early career researchers!

You can register and check out the schedule here: aaltoml.github.io/apml/

20.11.2024 20:33 โ€” ๐Ÿ‘ 93    ๐Ÿ” 30    ๐Ÿ’ฌ 2    ๐Ÿ“Œ 1

โœ‹

20.11.2024 06:52 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 0

For theoreticians there's just more incentive to find that wall, so they can go back to doing what they were before.

19.11.2024 23:40 โ€” ๐Ÿ‘ 2    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

Me as well ๐Ÿ™‹. Thanks

19.11.2024 05:07 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 2    ๐Ÿ“Œ 0

Alright, letโ€™s try out that ๐Ÿฆ‹ thing! Iโ€™ll try to post some little pieces about machine learning, uncertainty, and applied maths in general!

18.11.2024 20:00 โ€” ๐Ÿ‘ 9    ๐Ÿ” 1    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

@sigmabayesian is following 20 prominent accounts