@psteinb.bsky.social
π€ 303
π₯ 335
π 50
Using Machine Learning for Matter Research
@helmholtzai.bsky.social
This is so cool! πππ
add a skeleton here at some point
21 days ago
0
3
0
Looky Looky! ππ₯³π
arxiv.org/abs/2508.12939
Super fun project, I β€οΈed coauthoring w/
@sbi-devs.bsky.social
. Great lead by
@deismic.bsky.social
&
@janboelts.bsky.social
. Contribs by many talented people
@jakhmack.bsky.social
. π to
#BenjaminKurtMiller
for the kickstart!
@helmholtzai.bsky.social
loading . . .
Simulation-Based Inference: A Practical Guide
A central challenge in many areas of science and engineering is to identify model parameters that are consistent with prior knowledge and empirical data. Bayesian inference offers a principled framewo...
https://arxiv.org/abs/2508.12939
3 months ago
0
39
10
The 0th day of
#HAICON25
was a blast! I've had the plsre to participate in a tutorial on
@sbi-devs.bsky.social
by
#AlinaBazarova
and
#JoseRoblero
.
@helmholtzai.bsky.social
@fz-juelich.de
In the afternoon, I ran a birds-of-a-feather on inverse problems in Helmholtz.
@hzdr.bsky.social
5 months ago
1
4
0
reposted by
RAV
5 months ago
Heute vor 6 Jahren wurde Walter
#LΓΌbcke
von einem Rechtsradikalen ermordet. Walter LΓΌbcke steht fΓΌr einen Konservatismus, der heute so sehr fehlt. Ein Konservatismus, der humane Werte, das Menschenrecht auf Asyl, offensiv verteidigt. Und der nicht opportunistisch Positionen der
#NoAfD
ΓΌbernimmt.
15
1247
288
From anecdotal evidence: same holds for the German schools, I have contact with.
add a skeleton here at some point
6 months ago
0
0
0
Cunning idea by the looks of it!
add a skeleton here at some point
6 months ago
0
1
0
π₯³Great news, our JOSS paper "sbi reloaded" has been accepted! π This community lead by the fine folks of
@sbi-devs.bsky.social
is very welcoming and super fun to work with! I learn with every discussion I have. paper:
joss.theoj.org/papers/10.21...
review:
github.com/openjournals...
loading . . .
[REVIEW]: sbi reloaded: a toolkit for simulation-based inference workflows Β· Issue #7754 Β· openjournals/joss-reviews
Submitting author: @janfb (Jan Boelts) Repository: https://github.com/sbi-dev/sbi Branch with paper.md (empty if default branch): joss-submission-2024 Version: v0.24.0 Editor: @boisgera Reviewers: ...
https://github.com/openjournals/joss-reviews/issues/7754#issuecomment-2789593224
7 months ago
0
6
3
Canβt wait to listen in!
add a skeleton here at some point
7 months ago
1
2
0
reposted by
Riccardo Sapienza
7 months ago
I also agree that openness is they key skill for a researcher
www.nature.com/articles/s41...
loading . . .
Openness guides discovery - Nature Biotechnology
Nature Biotechnology - Openness guides discovery
https://www.nature.com/articles/s41587-025-02635-7
0
3
2
reposted by
Serge Belongie
7 months ago
Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? SΓΈren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)
loading . . .
NeurIPS participation in Europe
We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...
https://docs.google.com/forms/d/e/1FAIpQLSezao8Be0d3lP7stopj1u72uWRwumumEkLVcupqdbKqYDeosA/viewform
6
280
173
Great initiative to see if Neurips could be replicated in Europe! πͺπΊ
add a skeleton here at some point
7 months ago
0
0
0
Great to see that many noise2void inspired denoising algorithms have been ported to
@pytorch.org
! Kudos to
@florianjug.bsky.social
and many others ...
github.com/CAREamics/ca...
loading . . .
GitHub - CAREamics/careamics: A deep-learning library for denoising images using Noise2Void and friends (CARE, PN2V, HDN etc.), with a focus on user-experience and documentation.)
A deep-learning library for denoising images using Noise2Void and friends (CARE, PN2V, HDN etc.), with a focus on user-experience and documentation.) - CAREamics/careamics
https://github.com/CAREamics/careamics
7 months ago
0
18
9
It's been a blast, thanks to
@sbi-devs.bsky.social
! This week's hackathon was phenomenal! π π The sbi hackathon welcomed about 25 people in TΓΌbingen with contributions spanning the globe , e.g. πΊπΈπ―π΅π§πͺπ©πͺ. Wanna see, what we did? Check out the PRsπ
github.com/sbi-dev/sbi/...
loading . . .
Pull requests Β· sbi-dev/sbi
sbi is a Python package for simulation-based inference, designed to meet the needs of both researchers and practitioners. Whether you need fine-grained control or an easy-to-use interface, sbi has ...
https://github.com/sbi-dev/sbi/pulls?q=sort%3Aupdated-desc+is%3Apr+is%3Aopen
8 months ago
0
14
6
This week will be an upskill from dusk till dawn: I'll be at the hackathon of
@sbi-devs.bsky.social
! I am so much looking forward to meet and work with collaborators. Learn a lot and push
#sbi
forward. Can't wait to arriveπ!
@helmholtzai.bsky.social
@tuebingen-ai.bsky.social
#appliedAI
8 months ago
0
1
0
What a gem! Lovely article on our blind focus on accuracy in ML. Can't wait to get my hands on the references therein.
add a skeleton here at some point
8 months ago
1
3
1
Working with
#julia
sometimes feels like playing minesweeper. Found a helpful library on the web π£, punched in `add AwesomeLib` and boom π₯ I have to wait for 15min π₯± to get all dependencies compiled and installed.
#21century
#oldhardware
8 months ago
0
0
0
Congrats! π
add a skeleton here at some point
8 months ago
0
1
0
I think, this is a great opportunity for anyone interested!
add a skeleton here at some point
8 months ago
0
0
0
ποΈ No plans for Wednesday in Dresden, March 12, 5:30pm yet? Then please join us for a fun event on Computer Vision π» and Image analysis π¬ π ... there will be food for thought π€― , drinks π₯ and pizza π . For the agenda and registration see the link below π
events.hifis.net/event/2248/
loading . . .
https://events.hifis.net/event/2248/
8 months ago
0
2
0
Jaw dropping results! Congrats
@maxxxzdn.bsky.social
for this wonderful treat. Happy to put this into play.
add a skeleton here at some point
8 months ago
0
1
0
The
@turingpost.bsky.social
send out a survey to its readers. Starting the thing, I already felt excluded a bit πππ But hey, being at
#Neurips24
already gave be impression that being in academia and working on
#AI
is a niche profession these days. π€·
9 months ago
0
1
0
Is it time to buy a new laptop, if
#julia
crashes with an OOM error during project build if it can only use 6GB of RAM?
#PrematureOptimisation
#InvertedReality
9 months ago
0
0
0
πWe started with some colleagues of
@esciencecenter.bsky.social
and π΄σ §σ ’σ ·σ ¬σ ³σ Ώ to devise a
@carpentries.carpentries.org
lesson on
#DeepLearning
. Based on the incredible commitment of many individuals, the lesson is now adopted into the carpentries lab! Congrats to all involed! π₯³
github.com/carpentries-...
loading . . .
[Review]: Introduction to deep learning Β· Issue #25 Β· carpentries-lab/reviews
Lesson Title Introduction to deep learning Lesson Repository URL https://github.com/carpentries-incubator/deep-learning-intro Lesson Website URL https://carpentries-incubator.github.io/deep-learnin...
https://github.com/carpentries-lab/reviews/issues/25#issuecomment-2647178962
9 months ago
1
12
3
**Dresden Image Analysis Regulars** We're excited to invite you to a casual get-together where you'll dive into the latest news and advancements in
#CV
in
#Dresden
. β When? Mar 12, 2025, 5:30pm π§ Where? Oncoray in Dresden βοΈ How? Just register on the page below
events.hifis.net/event/2248/
loading . . .
https://events.hifis.net/event/2248/
9 months ago
0
0
0
Didnβt know that
#ML
in
#rust
is so rich today:
github.com/huggingface/...
loading . . .
GitHub - huggingface/candle: Minimalist ML framework for Rust
Minimalist ML framework for Rust. Contribute to huggingface/candle development by creating an account on GitHub.
https://github.com/huggingface/candle
9 months ago
0
0
0
reposted by
Harry Thasarathan
9 months ago
ππ°οΈπWanna know which features are universal vs unique in your models and how to find them? Excited to share our preprint: "Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment"!
arxiv.org/abs/2502.03714
(1/9)
1
56
22
Welcome! π€
add a skeleton here at some point
10 months ago
0
1
0
Great to see flow matching more and more in the wild!
add a skeleton here at some point
10 months ago
0
1
0
reposted by
Paul Hagemann
10 months ago
Our paper "PnP-Flow: Plug-and-Play Image Restoration with Flow Matching" has been accepted to ICLR 2025. Here a short explainer: We want to restore images (i.e., solve inverse problems) using pretrained velocity fields from flow matching. However, using change of variables is super costly.
1
15
7
reposted by
Dr Charles Smith
10 months ago
My letter in today's Guardian. Just asking, like. But I think we know the answer.
366
17208
3242
Especially "1." seems super useful! Keep going strong
@johanneskoester.bsky.social
and
@snakemake.bsky.social
!
add a skeleton here at some point
10 months ago
0
1
0
What a great episode! Especially proud and happy to discover yet another alumni of
@mpicbg.bsky.social
! π π€ Thanks so much for all these insights
@hugobowne.bsky.social
add a skeleton here at some point
10 months ago
2
4
1
reposted by
sbi - Simulation-based inference
10 months ago
π Just in time for the end of the year, weβve released a new version of sbi! π¦ v0.23.3 comes packed with exciting features, bug fixes, and docs updates to make sbi smoother and more robust. Check it out! π π Full changelog:
github.com/sbi-dev/sbi/...
1
27
8
Great plot! π A bit of clarification for the top entries: cs.CV = computer science->Computer Vision & Pattern Recognition cs.LG = CS->Machine Learning cs.CL = CS->Computation & Language quant-ph = Quantum Physics cs.RO = CS->Robotics cs.AI = CS->Artificial Intelligence
add a skeleton here at some point
10 months ago
1
3
0
This was a great episode that I loved very much.
@khinsen.net
I'd be great to know the repositories behind the MOOCs! I'd love to have a closer look.
#reproducibility
add a skeleton here at some point
10 months ago
1
1
1
Subsequent to
#neurips24
, we had the chance to give a seminar at
#LBNL
.
@lbnlcs.bsky.social
It was great seeing old friends
@axccl.bsky.social
. To complete the swirl, we visited
@loicaroyer.bsky.social
at
@cziscience.bsky.social
in downtown SF. What an inspiring day!
@helmholtzai.bsky.social
11 months ago
1
6
1
thanks to
@smsharma.bsky.social
@marielpettee.bsky.social
and many others for this inspiring
#ML4PS
workshop
@neuripsconf.bsky.social
today. It was extremely fun and I learned a lot. Got new toys to play around with ...
github.com/Ciela-Instit...
loading . . .
GitHub - Ciela-Institute/PQM: Implemenation of PQMass from Lemos et al. 2024
Implemenation of PQMass from Lemos et al. 2024. Contribute to Ciela-Institute/PQM development by creating an account on GitHub.
https://github.com/Ciela-Institute/PQM
11 months ago
0
4
0
So proud of my team member! We won the reproducibility award at the
#ML4PS
workshop of
@neuripsconf.bsky.social
!!
@helmholtzai.bsky.social
11 months ago
0
5
0
One aspect of science today β¦
add a skeleton here at some point
11 months ago
0
0
0
This will be fun the next coming days!
#neurips24
11 months ago
0
4
0
reposted by
Mathurin Massias
12 months ago
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
loading . . .
12
354
113
Totally on my reading list! ππππ€©πππ
add a skeleton here at some point
11 months ago
0
0
0
reposted by
sbi - Simulation-based inference
12 months ago
The sbi package is growing into a community project π To reflect this and the many algorithms, neural nets, and diagnostics that have been added since its initial release, we have written a new software paper π Check it out, and reach out if you want to get involved:
arxiv.org/abs/2411.17337
loading . . .
sbi reloaded: a toolkit for simulation-based inference workflows
Scientists and engineers use simulators to model empirically observed phenomena. However, tuning the parameters of a simulator to ensure its outputs match observed data presents a significant challeng...
http://arxiv.org/abs/2411.17337
1
60
26
At out intro to
#ML
with
@scikit-learn.bsky.social
at
#HIJena
this week with
@tillkorten.bsky.social
, we had a bring-your-own-data session for the last half day. Students presented their work and we guided them in the use of
#ML
. π2/5π projects were amendable to
@sbi-devs.bsky.social
! π€―
11 months ago
0
1
0
Right timing as we finish our introduction to sklearn in Jena for
@helmholtzai.bsky.social
!
add a skeleton here at some point
12 months ago
0
1
1
you reached the end!!
feeds!
log in