Is this the year we finally break up @neuripsconf.bsky.social?
19.09.2025 08:09 β π 47 π 7 π¬ 4 π 1
Three weeks ago I had the pleasure of mentoring a project at @logml.bsky.social. We looked into cortical surface parcellation from a geometric angle and had a lot of fun! Thanks to my project group (including @mustas.bsky.social and @zhengdiyu.bsky.social) for the trust...
04.08.2025 11:50 β π 4 π 1 π¬ 1 π 0
EurIPS is coming! π£ Mark your calendar for Dec. 2-7, 2025 in Copenhagen π
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu
eurips.cc
16.07.2025 22:00 β π 141 π 70 π¬ 2 π 19
Identifiable latent metric space: geometry as a solution to the identifiability problem
6/
π Learn more:
π Blog: syrota.me/posts/2025/0...
π Paper: syrota.me/files/identi...
π With Eugene Zainchkovskyy, Quanhan Xi, Benjamin Bloem-Reddy, and SΓΈren Hauberg.
14.07.2025 05:47 β π 2 π 0 π¬ 0 π 0
5/
π Presenting at ICML:
ποΈ Tuesday, 11:00 AMβ1:30 PM
π West Exhibition Hall B2βB3
π¨ Poster: syrota.me/files/imsdlv...
14.07.2025 05:46 β π 1 π 0 π¬ 1 π 0
4/
Iβm especially curious about the implications for disentanglement and causality. Would love to chat with anyone working on these topics! π
14.07.2025 05:46 β π 1 π 0 π¬ 1 π 0
3/
Why does this matter?
Because it allows trustworthy computations of relations between latent variables β which is essential in scientific applications where latent variables are of interest.
It also strengthens reliability and explainability in generative models in general.
14.07.2025 05:46 β π 1 π 0 π¬ 1 π 0
2/
The core idea:
We prove that the pullback metric is identifiable.
This means geodesic distances, volumes, and optimal transport in latent space are now meaningful & model-invariant. β
14.07.2025 05:46 β π 1 π 0 π¬ 1 π 0
1/
π¨ New paper at #ICML2025!
Identifying Latent Metric Structures in Deep Latent Variable Models π
We solve part of the identifiability puzzle in generative models β using geometry. π§΅
14.07.2025 05:45 β π 6 π 2 π¬ 1 π 0
π©οΈ On my way to #NeurIPS2024 and excited to chat about (ML applications of) linear algebra, differentiable programming, and probabilistic numerics!
Feel free to DM if youβd like to meet up, hang out, and/or discuss any of these topics π
(Where to find me & paper info? -> Thread)
09.12.2024 07:46 β π 11 π 3 π¬ 1 π 1
Postdoc @ Technical University of Munich | Intern @ Qualcomm AI Research | PhD @ University of Twente | Neural operators for cardiovascular flow
PhD student in machine learning at DTU, Copenhagen.
Especially interested in model representations.
LOGML (London Geometry and Machine Learning) aims to bring together mathematicians and computer scientists to collaborate on a variety of problems at the intersection of geometry and machine learning.
For more AI&Tech content, check here www.luok.ai
πApple Die Hard Fanο½ θΉζιͺ¨η°η²
π€GenAI Observer ο½ GenAIθ§ε―θ
π¨π»βπ€Cutting Edge Tech Enthusiast ο½ η§ζη±ε₯½θ
Research director | @McGillU @Mila_Quebec @IVADO_Qc | My team designs machine learning frameworks to understand biological systems from new angles of attack
Asst. Prof. University of Amsterdam, rock climber, husband, father. Model-based (Mathematical) Cognitive Neuroscientist. I study decision-making, EEG, π§ , statistical methods, etc.
πΊπ¦πͺπΊ
Full Professor at @deptmathgothenburg.bsky.social | simulation-based inference | Bayes | stochastic dynamical systems | https://umbertopicchini.github.io/
Machine learner & physicist. At CuspAI, I teach machines to discover materials for carbon capture. Previously Qualcomm AI Research, NYU, Heidelberg U.
Using deep learning to study neural dynamics
@mackelab.bsky.social
Posting about the One World Approximate Bayesian Inference (ABI) Seminar, details at https://warwick.ac.uk/fac/sci/statistics/news/upcoming-seminars/abcworldseminar/
Amortized Bayesian Workflows in Python.
π² Post author sampled from a multinomial distribution, choices
β
@marvin-schmitt.com
β
@paulbuerkner.com
β
@stefanradev.bsky.social
π GitHub github.com/bayesflow-org/bayesflow
π¬ Forum discuss.bayesflow.org
PhD Student at MPI-IS working on ML for Gravitational Waves | #MLforPhysics #SBI
https://www.annalenakofler.com
Assistant Professor at Rensselaer Polytechnic Institute (RPI)
Bayesian | Computational guy | Name dropper | Deep learner | Book lover
Opinions are my own.
Postdoctoral Researcher at University of Basel
Interested in Cognitive Modeling | Decision Making | Dynamics in Cognition | Amortized Bayesian Inference | Superstatistics
Doctoral researcher at Aalto University
Simulation-based Inference
yugahikida.github.io
Black holes, gravitational waves, and AI.
UKRI Future Leaders Fellow @ University of Nottingham.
https://www.stephenrgreen.com/
High Energy Physics/Machine Learning/Data Science Prof @tum.de www.lukasheinrich.com
AI x neuroscience.
π www.rdgao.com
Physics + Machine Learning
Scientist at SLAC National Laboratory at Stanford
CEO of KI macht Schule gGmbH
Previously @mackelab.bsky.social - machine learning in (neuro)science.
