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
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
Reposted by Anshuk Uppal
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
🎓 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
Generative Modeling Summer School (GeMSS)
gemss.ai
January 10, 2025 at 10:42 AM
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
🎓 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
Reposted by Anshuk Uppal
🔥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
🔷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
December 13, 2024 at 5:52 PM
🔥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
🔷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
Reposted by Anshuk Uppal
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
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
November 27, 2024 at 9:00 AM
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
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
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.
GANs had huge influence, they challenged the view that has equated generative modelling with maximising likelihood of a probabilistic model, and inspired a lot of debate on representation learning and various goals one might have with generative models.
November 28, 2024 at 5:53 AM
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.
Reposted by Anshuk Uppal
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!
@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!
November 23, 2024 at 7:33 PM
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!
@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!
Reposted by Anshuk Uppal
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/
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/
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 ...
aaltoml.github.io
November 20, 2024 at 8:33 PM
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/
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/
Reposted by Anshuk Uppal
Alright, let’s try out that 🦋 thing! I’ll try to post some little pieces about machine learning, uncertainty, and applied maths in general!
November 18, 2024 at 8:00 PM
Alright, let’s try out that 🦋 thing! I’ll try to post some little pieces about machine learning, uncertainty, and applied maths in general!