Pinned Tweet
I am thrilled to share SMLMFlow: my first research paper for my PhD! 🥳
📰 Preprint: biorxiv.org/content/10.64898…
🧵👇 1/5
Sebastian Bauer retweeted
Introducing Langevin Flow Maps
TLDR: Neural Network Potentials that learn their own stochastic pathwise solution for faster simulation.
- Transferable across molecular systems.
- Transition dynamics are preserved.
- No trajectory data are required.
Work together with @sgmccallum, supervised by @AlexanderTong7, and @JamesFosterBath.
Arxiv: arxiv.org/abs/2610.05998
Data: huggingface.co/datasets/nikl…
Code: github.com/sammccallum/lfm
Sebastian Bauer retweeted
Yes, echoing @Niklas_TR , we are hiring!
Congrats @AlexanderTong7! Also, if you are a recent CS/Math/Physics graduate: we are hiring PhD students. Deadline is 1st of Nov phd.aithyra.at/
Sebastian Bauer retweeted
Strong Stochastic Flow Maps has been accepted to #NeurIPS2026 as an Oral! 🎉
1/5 New paper 🎉Strong Stochastic Flow Maps!
We learn the stochastic integral, not just the transition kernel of an SDE
Huge shout out to my fellow first author Sam McCallum and the rest of the amazing team: Timothy Herschell, @Niklas_TR, @AlexanderTong7, and @JamesFosterBath
Sebastian Bauer retweeted
🔬🌟 Join us for SMLMS2026 in Stockholm! 🔬🌟
We’re excited to welcome the advanced light microscopy community to Stockholm August 26–28 2026. Check out our fantastic speaker line-up and register here: smlms.org
🚨Only 2 weeks left for abstract submission 🚨
🧵4/5
By combining cutting-edge machine learning methods such as Flow Matching, Erwin Transformer, and GNNs, we can correct noisy SMLM point clouds whilst retaining relevant information over various scales.
🧵5/5
A huge thank you ❤️ to our fantastic collaborators @Ruby_Peters_ and Daniel Sage as well as the rest of the CMCB team: @LucaPanconi, @inesmcunha, @EmmaLatron & @GriffieJuliette 🔬🤖
📰: biorxiv.org/content/10.64898…
Sebastian Bauer retweeted
Together with UC Berkeley we are announcing the laser phase plate - a breakthrough in atomic resolution imaging. This is the brightest continuous wave laser in the world, 100 million times the intensity of the surface of the sun.
Phase contrast plays an important role in microscopy, but it was thought close to impossible for electron microscopy, where it would require interfering with an electron beam. Holger Mueller and Robert Glaeser proposed exactly this using a standing wave laser. It has taken over 15 years to make this a reality. Biohub partnered with UC Berkeley and Mueller to support this work and to engineer and build the technology.
Contrast has been the critical barrier to achieving atomic resolution imaging of the cell. In cryo-electron tomography, a cellular imaging technology that uses electron microscopy, the low contrast makes it impossible to resolve anything but the largest proteins within their cellular context. The laser phase plate removes that barrier.
With advances in AI this breakthrough in contrast will start to open up a new frontier in structural biology, that will allow us to see the molecular machines of the cell, and how they assemble into far more complex and dynamic systems, and understand how they work.
Sebastian Bauer retweeted
Antibody–antigen complexes are still hard for AlphaFold: good candidate structures may be generated, but choosing the correct one remains a challenging.
ABAG-Rank tackle this by learning to rank structural ensembles.
Paper: biorxiv.org/content/10.64898…
Code: github.com/tadteo/ABAG-Rank
🎉 New paper out in Nano Letters!
This study demonstrates how our abberior tetrazine dyes (STAR 635, STAR RED) enable precise bioorthogonal labeling and STED imaging.
By combining noncanonical amino acid (ncAA) incorporation with bioorthogonal click chemistry and expansion microscopy (ExM) the team achieved nanoscale resolution of protein distributions in cells, going beyond the limits imposed by traditional antibody labeling.
pubs.acs.org/doi/10.1021/acs…
Always exciting to see our dyes supporting cutting-edge super-resolution research.
Congratulations to the author team around Hans Blom, Hjalmar Brismar, and Steven Edwards.
@scilifelab
#STED #Superresolution #ExpansionMicroscopy #bringingcolortoscience
Sebastian Bauer retweeted
Our work “AI4CellFate: Interpretable Early Cell Fate Prediction with Generative AI” is finally out in @biorxivpreprint !!! 😍❤️🔬biorxiv.org/content/10.1101/… @scilifelab, @franciscrick. More about it in the thread #AI4CellFate (1/n)⬇️
Sebastian Bauer retweeted
⚠️ Last couple of days to apply for a PhD position at CMCB!! Join us 😀 su.varbi.com/en/what:job/job…
🚨🚨 We are recruiting! If you are interested in developing ML tools (with a focus on interpretable ML & generative AI) for bioinformatics applications @scilifelab, look no more😋 1 PhD position su.varbi.com/en/what:job/job… & 2 post doc positions (online soon, PM me in the meantime).
If you are looking for a cool position in an awesome team! Look no further and apply! 😁
🚨🚨 We are recruiting! If you are interested in developing ML tools (with a focus on interpretable ML & generative AI) for bioinformatics applications @scilifelab, look no more😋 1 PhD position su.varbi.com/en/what:job/job… & 2 post doc positions (online soon, PM me in the meantime).
Sebastian Bauer retweeted
🚨We’re hiring!
Passionate about #microscopy, #biophysics and #interdisciplinaryresearch? There's still time to apply for our EPSRC PhD project on how actin network architecture shapes the mechanical properties of cells at @sheffielduni
Learn more/Apply: findaphd.com/phds/project/fo…
Sebastian Bauer retweeted
It has been a bliss of a 1st year for the lab with these guys 🥰🎂 looking forward to sharing what we have been up in the coming months 😆 and, of course, a merry Christmas 🎄🎁
Sebastian Bauer retweeted
In their Review, @inesmcunha, @GriffieJuliette and colleagues discuss the opportunities and challenges associated with applying ML-based pipelines for microscopy datasets from a user point of view.
#JCSImagingSI
journals.biologists.com/jcs/…

ALT Figure showing ML principles. ML can be divided into two main subdivisions: supervised and unsupervised. (A) In supervised ML, during training (left), an untrained model takes raw training data and target labels as its inputs. The model learns a mathematical mapping from raw data to target labels. The trained model can then infer (right) predictions on unseen raw datasets. (B) In unsupervised ML, during training (left), the model learns intrinsic relationships within the raw input data, without target labels. In inference (right), the trained model can then be used to detect patterns within the unseen raw dataset.
Sebastian Bauer retweeted
🚨 Exciting news – my final Birmingham paper, “Mapping membrane biophysical nano-environments”, is now available online and open access with @NatureComms! (1/4)
doi.org/10.1038/s41467-024-5…
first publication out of the CMCB lab! If you want to know more about how you can use Machine Learning in Microscopy, this review is your guide! 😃🔬🤖
😍⚠️And it’s out in @J_Cell_Sci!! Our review on the opportunities and challenges of using Machine Learning in Microscopy research 🤖🔬! From using ML to curate data to using ML to give us more KNOWLEDGE about our data (i.e. Interpretation 😉) DOI: doi.org/10.1242/jcs.262095 (1/n) ⬇️





















