Michael Albergo
@msalbergo.bsky.social
junior fellow at @Harvard.edu, incoming prof at @HSEAS and @Kempnerinstitute.bsky.social studying machine learning and its applications to nature and the sciences
Reposted by Michael Albergo
DO NOT GIVE UP!
Our advocacy is working.
A key Senate committee has indicated that it will reject Trump’s proposed cuts to science agencies including NASA and the NSF.
Keep speaking up and calling your electeds 🗣️🗣️🗣️
Our advocacy is working.
A key Senate committee has indicated that it will reject Trump’s proposed cuts to science agencies including NASA and the NSF.
Keep speaking up and calling your electeds 🗣️🗣️🗣️
July 11, 2025 at 7:03 PM
DO NOT GIVE UP!
Our advocacy is working.
A key Senate committee has indicated that it will reject Trump’s proposed cuts to science agencies including NASA and the NSF.
Keep speaking up and calling your electeds 🗣️🗣️🗣️
Our advocacy is working.
A key Senate committee has indicated that it will reject Trump’s proposed cuts to science agencies including NASA and the NSF.
Keep speaking up and calling your electeds 🗣️🗣️🗣️
Reposted by Michael Albergo
Congratulations to Peter Holderrieth @msalbergo.bsky.social and Tommi Jaakkola for winning the best paper award for their work entitled "LEAPS: A discrete neural sampler via locally equivariant networks" at this year's Frontiers in Probabilistic Inference workshop #ICLR2025!
April 28, 2025 at 4:53 AM
Congratulations to Peter Holderrieth @msalbergo.bsky.social and Tommi Jaakkola for winning the best paper award for their work entitled "LEAPS: A discrete neural sampler via locally equivariant networks" at this year's Frontiers in Probabilistic Inference workshop #ICLR2025!
Excited to be at @iclrconf for #ICLR2025! I’ll give a talk at the Frontiers on Probabilistic Inference workshop to discuss work with @evdende2, @peholderrieth, @brianlee_lck, @jeha_paul, and Francisco Vargas! Let me know about your work, I will come by :)
April 24, 2025 at 1:34 AM
Excited to be at @iclrconf for #ICLR2025! I’ll give a talk at the Frontiers on Probabilistic Inference workshop to discuss work with @evdende2, @peholderrieth, @brianlee_lck, @jeha_paul, and Francisco Vargas! Let me know about your work, I will come by :)
Reposted by Michael Albergo
We are thrilled to share the appointment of @sueyeonchung.bsky.social as an #KempnerInstitute Investigator, bringing her expertise in using #AI to understand #brain structure and function to @harvard.edu. Read the announcement: bit.ly/3PL3SEn
Leading Computational Neuroscientist SueYeon Chung to join Harvard’s Kempner Institute and FAS’ Center for Brain Science - Kempner Institute
CAMBRIDGE, MA —The Kempner Institute announced today the appointment of SueYeon Chung (PhD ‘17), who returns to Harvard as a Kempner Institute Investigator and faculty member in the Faculty of […]
bit.ly
January 22, 2025 at 3:28 PM
We are thrilled to share the appointment of @sueyeonchung.bsky.social as an #KempnerInstitute Investigator, bringing her expertise in using #AI to understand #brain structure and function to @harvard.edu. Read the announcement: bit.ly/3PL3SEn
Reposted by Michael Albergo
I am hiring a postdoctoral scholar with a start date summer or fall 2025. Projects will be focused on thermodynamically consistent generative models, broadly defined. If you’re interested, please send a CV and one paragraph about why you think you’d be a good fit to rotskoff@stanford.edu
December 23, 2024 at 5:31 PM
I am hiring a postdoctoral scholar with a start date summer or fall 2025. Projects will be focused on thermodynamically consistent generative models, broadly defined. If you’re interested, please send a CV and one paragraph about why you think you’d be a good fit to rotskoff@stanford.edu
We got a preview of this stuff just a few days ago at the CECAM workshop. This is really cool stuff from @franknoe.bsky.social and co. Congrats!
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science.
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
December 6, 2024 at 7:53 PM
We got a preview of this stuff just a few days ago at the CECAM workshop. This is really cool stuff from @franknoe.bsky.social and co. Congrats!
Reposted by Michael Albergo
Hellinger and Wasserstein are the two main geodesic distances on probability distributions. While both minimize the same energy, they differ in their interpolation methods: Hellinger focuses on density, whereas Wasserstein emphasizes position displacements.
December 3, 2024 at 5:16 PM
Hellinger and Wasserstein are the two main geodesic distances on probability distributions. While both minimize the same energy, they differ in their interpolation methods: Hellinger focuses on density, whereas Wasserstein emphasizes position displacements.
Reposted by Michael Albergo
If you're at NeurIPS next week come see our spotlight poster led by Yinuo Ren and Haoxuan Chen! We use the parallel sampling technique to rigorously establish a big acceleration for diffusion model inference! neurips.cc/virtual/2024...
NeurIPS Poster Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time ComplexityNeurIPS 2024
neurips.cc
December 3, 2024 at 9:55 PM
If you're at NeurIPS next week come see our spotlight poster led by Yinuo Ren and Haoxuan Chen! We use the parallel sampling technique to rigorously establish a big acceleration for diffusion model inference! neurips.cc/virtual/2024...
Come to Cambridge -- lots of exciting things going on! There is a tenure-track position at Kempner and Harvard CS. Please share around:
academicpositions.harvard.edu/postings/14362
academicpositions.harvard.edu/postings/14362
December 3, 2024 at 2:58 PM
Come to Cambridge -- lots of exciting things going on! There is a tenure-track position at Kempner and Harvard CS. Please share around:
academicpositions.harvard.edu/postings/14362
academicpositions.harvard.edu/postings/14362
Reposted by Michael Albergo
A common question nowadays: Which is better, diffusion or flow matching? 🤔
Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
December 2, 2024 at 6:45 PM
A common question nowadays: Which is better, diffusion or flow matching? 🤔
Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
Thanks, Kyle!
My former student @msalbergo.bsky.social has beautiful papers describing the approach on the right. “Flow matching” and “stochastic interpolants” were concurrent developments of the same core idea.
arxiv.org/abs/2209.15571
arxiv.org/abs/2303.08797
arxiv.org/abs/2209.15571
arxiv.org/abs/2303.08797
Optimal transport computes an interpolation between two distributions using an optimal coupling. Flow matching, on the other hand, uses a simpler “independent” coupling, which is the product of the marginals.
December 2, 2024 at 4:13 PM
Thanks, Kyle!
Hello BlueSky! If and when I'm posting online, I'll be sure to do it here too.
November 21, 2024 at 2:14 AM
Hello BlueSky! If and when I'm posting online, I'll be sure to do it here too.