iiinova — where your digital self keeps evolving

Reposted by Anirban Ray

Constantin Pape @cppape.bsky.social · 23/06/2026

How can we use foundation models such as (micro)SAM to improve electron microscopy segmentation? Check out our new preprint where we found substantial improvements for nucleus, mito, and neurite-segmentation based on initialization and semi-supervised learning with foundation models.

1165

Reposted by Anirban Ray

Helen Foster @helenfoster.bsky.social · 11/06/2026

There are lots of exciting opportunities to join the in situ structural biology community at Leeds this Autumn - 2 studentships in the Cheney PhD program (astbury.leeds.ac.uk/cheney-phd/) and I am recruiting a PhD student and research assistant. Please share and send any future tomographers our way!

astbury.leeds.ac.uk

Cheney Scholarship PhD Programme : The Astbury Centre for Structural Molecular Biology - "Understanding Life in Molecular Detail"

Applications are open for 2 PhD student places. Closing date for applications is Thursday 26 June, 5pm. Interviews will be held on 9th July 2026. The Cheney Scholarship is a prestigious 4-year PhD pr...

11414

Anirban Ray @anirbanray.bsky.social · 01/06/2026

Super excited to be in Denver this week, presenting our HazeMatching (github.com/juglab/HazeM...) at #CVPR2026 (Findings) and at the #CV4Science Workshop (sites.google.com/nyu.edu/comp...). Please drop by if you're attending 😀 😇.

040

Reposted by Anirban Ray

Anna Foix @afoix.bsky.social · 26/05/2026

🔬 One more year! BioImage Computing has been accepted to @eccv.bsky.social 🎉 Show us your work at the intersection of computer vision, ML & biology! Check out our speaker lineup: @arratemunoz.bsky.social, @jakobtroidl.bsky.social & Juliette Griffié 👏 ⏳ Deadline: 13 July ℹ️ www.bioimagecomputing.com

bioimagecomputing.com

BioImage Computing

a truly interdisciplinary workshop

0129

Reposted by Anirban Ray

Human Technopole @humantechnopole.bsky.social · 22/05/2026

💡 Introducing the Multimodal #AI Across Scales Research Programme with our @florianjug.bsky.social 🤖 The new HT Programme develops open, uncertainty-aware AI tools to connect biological data from molecules and cells to patients and populations. humantechnopole.it/en/news/intr...

humantechnopole.it

Introducing the Multimodal AI Across Scales Programme with Florian Jug - Human Technopole

The new Multimodal AI Across Scales Research Programme, within Human Technopole's Computational Biology Research Centre, develops AI methods that connect biological data across modalities and scales, ...

072

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 22/05/2026

Am I famous now?!? 😉 Jokes aside… I am stoked to start this new research direction with some of the most amazing scientists I know! What a team we already are… and… it will only get better from here!!! ❤️

1163

Anirban Ray @anirbanray.bsky.social · 14/05/2026

Super excited to share that HazeMatching (arxiv.org/abs/2506.22397) has also been selected for presentation at the 3rd CV4Science Workshop (sites.google.com/nyu.edu/comp...) at #CVPR2026 🎉. It’s great to see growing interest from the community in the role of generative models for inverse problems.

lnkd.in

This link will take you to a page that’s not on LinkedIn

010

Reposted by Anirban Ray

Tony S.F. @tonysf.bsky.social · 13/05/2026

New paper! We analyze proximal preconditioned gradient methods that extend Muon/Scion to handle nonconvex constraints (Stiefel manifold, spectral sphere, norm balls, ...) with convergence guarantees under heavy-tailed noise + variance reduction w/ STORM! arxiv.org/abs/2605.11850

131

Reposted by Anirban Ray

Sander Dieleman @sedielem.bsky.social · 06/05/2026

My first blog post in over a year is a deep dive on flow maps🗺️, or how to learn the integral of a diffusion model to enable faster sampling and several other cool tricks. It's the longest one yet👀 Let me know what you think! sander.ai/2026/05/06/f...

sander.ai

Learning the integral of a diffusion model

A deep dive on flow maps.

36417

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 05/05/2026

It is finally out there in published form. 🎉 #MicroSplit (with an 𝕊) #Microscopy 🔬 #AI 🤖 www.nature.com/articles/s41... And no paywall... so... enjoy the read! 💸 👋 This is where the post could end... but I will have to go on for a bit below... 😉 🧵

36118

Reposted by Anirban Ray

lebellig @lebellig.bsky.social · 28/04/2026

My PhD thesis manuscript will be available in the coming months, but I’ve written two blog posts based on the related work chapter: 1. Generative modeling with flow-based models 🪚 2. Data-translation with flow and diffusion bridges 🔨 Open to feedback and discussions! lebellig.github.io/blog/

1357

Reposted by Anirban Ray

Wolfram Pönisch @wolframponisch.bsky.social · 16/04/2026

Interested in stochastic tissue morphodynamics in development and disease? Join us at HT @humantechnopole.bsky.social We are recruiting a postdoc for a project combining image analysis, morphometrics, and modelling in collaboration with experimentalists. More information: tinyurl.com/3kc7s4rz

careers.humantechnopole.it

Postdoc Pönisch Lab

055

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 07/04/2026

Look mum, I made it!!! 🎉 😉 @ellis.eu @humantechnopole.bsky.social

0462

Reposted by Anirban Ray

Jan Funke @janfunkey.bsky.social · 07/04/2026

We are hiring a Software Engineer who can help us turn our methods into easily usable tools for: * Explainable AI * Cell Tracking * Interactive Learning ...and some more: careers.humantechnopole.it/job/Research... Feel free to reach out directly if you are interested and/or have questions!

careers.humantechnopole.it

Research Software Engineer

1118

Reposted by Anirban Ray

Damian Dalle Nogare @damiandn.bsky.social · 07/04/2026

🚨🚨🚨JOB ALERT🚨🚨🚨 The Image Analysis Unit at Human Technopole in Milan is recruiting for two positions to join our growing team: 1) Bioimage Analyst 2) Research Software Engineer (RSE) Read on to learn why one of these two people should be you!

11523

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 02/04/2026

We've spent the last year building something at @humantechnopole.bsky.social that we think is genuinely needed: #AI that works across biological scales and data modalities, not just within them. A thread on what we're doing, why, and who we're looking for. A 🧵... 1/9

25826

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 30/03/2026

🚨Job Alert -- again!🚨 You are into disease risk prediction based on images or other data modalities? This is for you! 🫵 careers.humantechnopole.it/job/Postdoc-... Part of our Scientific AI Flagship @humantechnopole.bsky.social and part of our mission to benefit society via biomedical #AI solutions.

careers.humantechnopole.it

Postdoc on Multimodal AI for Disease Risk Prediction

0128

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 25/03/2026

🚨 We are hiring! Personally, I think this is a fantastic job, good salary, and fun work place with exceptional colleagues. ⚠️ Warning, I’m quite biased… but still right! 😜 Join us! Apply!!! 🎉 careers.humantechnopole.it/job/AI-Exper...

02421

Anirban Ray @anirbanray.bsky.social · 09/03/2026

Super excited to present our poster (rayanirban.github.io/files/EMBL_p...) on HazeMatching and ResMatching at the EMBL AI and Biology Symposium 2026 in Heidelberg, Germany, this week. 🎉 If you’re around, please drop by our poster (#148 on Thursday, 12/3)! 😊 @embl.org #EESAIBio #AI4Science

082

Anirban Ray @anirbanray.bsky.social · 07/03/2026

Update: ResMatching has been selected for an Oral Presentation at IEEE ISBI 2026! #ISBI2026! 🚀 😱 🎉 Being chosen for the oral track is a fantastic validation of the potential impact of this research. Thanks to the reviewers and organizers.

190

Anirban Ray @anirbanray.bsky.social · 06/03/2026

HazeMatching has been accepted to #CVPR2026 (Findings)! @cvprconference.bsky.social 🎉🎉 What if widefield microscopes could produce confocal-quality images? We introduce a Guided Conditional Flow Matching (CFM) framework that does exactly that. Learn more here: www.linkedin.com/feed/update/...

linkedin.com

#cvpr2026 #cvpr2026 #microscopy #imagerestoration #generativeai #ai4science | Anirban Ray

🎉Excited to share that HazeMatching (https://lnkd.in/dP5kWAHS) has been accepted to IEEE/CVF #CVPR2026 (Findings)🎉. 🔬What if widefield microscopes produced confocal-quality images? We introduce Haze...

051

Reposted by Anirban Ray

Jan Funke @janfunkey.bsky.social · 05/03/2026

We opened 4 PhD positions at @humantechnopole.bsky.social together with Polimi (see 👇). My lab offers a PhD project on "Computational Morphogenesis": use state-of-the-art machine learning methods together with realistic simulations to build digital twins of developing tissue. Apply by March 26.

12112

Reposted by Anirban Ray

India BioImaging @indiabioimaging.bsky.social · 04/03/2026

Exciting news! An article on India BioImaging (IBI) has been published in "Microscopy and Analysis" (@wileylifesci.bsky.social )(Issue 2/2026) Featured under "Building the India Bioimaging Community," it highlights IBI's vision, activities & growing impact in strengthening bioimaging across India.

122

Reposted by Anirban Ray

Martin Weigert @maweigert.bsky.social · 02/03/2026

Excited to share our new paper (CVPR 2026 🚀): "MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy" which enables local predictions to use global context. Great work led by @albertdm.bsky.social & another fun collab w @gioelelamanno.bsky.social! @scadsai.bsky.social

17030

Anirban Ray @anirbanray.bsky.social · 11/02/2026

It was super cool to hear @alex-krull.bsky.social talking about his research at @humantechnopole.bsky.social. Alex never fails to inspire his audience 🫠🤩

0101

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 05/02/2026

Excellent talk by Matteo Hessel from Google DeepMind at @humantechnopole.bsky.social earlier today! Thanks for dropping by and infecting us with the Meta-RL bug!

031

Anirban Ray @anirbanray.bsky.social · 15/01/2026

ResMatching accepted to IEEE ISBI 2025🎉. We extend Guided CFM to Computational Super-Resolution under extreme noise, achieving SOTA performance and calibrated posterior sampling that reflects uncertainty in real data. Learn more here: www.linkedin.com/posts/anirba...

linkedin.com

#isbi2026 #generativeai #flowmatching #computationalsuperresolution #bioimageanalysis | Anirban Ray

Excited to share that ResMatching (https://lnkd.in/dn_6VB9Q) has been accepted to IEEE International Symposium on Biomedical Imaging (ISBI) 2026! 🎉🎉 This work represents a significant step forward in...

050

Reposted by Anirban Ray

Jia-Bin Huang @jbhuang0604.bsky.social · 12/01/2026

Residual connections are adopted in virtually every deep learning model. BUT, can we further improve it? Hyper-connections is an exciting recent exploration to generalize residual connections. Check out the video explaining manifold constraints hyper-connections! youtu.be/jYn_1PpRzxI

youtu.be

How Residual Connections Are Getting an Upgrade [mHC]

YouTube video by Jia-Bin Huang

1171

Reposted by Anirban Ray

Julian Tachella @tachellajulian.bsky.social · 08/01/2026

📖 We put together with Mike Davies a review of self-supervised learning for inverse problems, covering the main approaches in the literature with a unified notation and analysis. arxiv.org/abs/2601.03244

arxiv.org

Self-Supervised Learning from Noisy and Incomplete Data

Many important problems in science and engineering involve inferring a signal from noisy and/or incomplete observations, where the observation process is known. Historically, this problem has been tac...

184

Reposted by Anirban Ray

Wolfram Pönisch @wolframponisch.bsky.social · 05/01/2026

I'm super excited to announce that I will join the Human Technopole @humantechnopole.bsky.social in Milan in April 2026 as a Research Group Leader.

Image of the Human Technopole

https://it.wikipedia.org/wiki/Human_Technopole#/media/File:Human_Technopole_Milano.jpg

6706

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 28/12/2025

🚨 Alarm!!! 🚨 AI/ML course for microscopy image analysis!!! 🧐 In 2026 at Janelia (@hhmijanelia.bsky.social), no tuition, housing and meals provided! Isn’t that borderline unbelievable?!? 20 students, ~14 TAs and lecturers 🗓️ June 4-18 2026 ✍️ Jan 15 2026 ✍️ 🔁 pls!! www.janelia.org/you-janelia/...

janelia.org

Deep Learning for Microscopy Image Analysis

Topics The following will be covered extensively during lectures, exercises, and project work: Image denoising and restoration (fully supervised and self-supervised) Image translation (e.g.,

07962

Anirban Ray @anirbanray.bsky.social · 04/12/2025

Okay, maybe I didn't pay much attention to this before but there are some elegant works that truly amaze me. This is one of them. A task-agnostic setup built on flow matching that just works across problems. I really like this work. 😀😃

030

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 03/12/2025

Invited talk by Rich Sutton at @neuripsconf.bsky.social was presenting the OaK architecture. A “scaffold” for superintelligent agents in which human inputs (at design time) are depreciated. 🧵

141

Reposted by Anirban Ray

lebellig @lebellig.bsky.social · 18/11/2025

"Back to Basics: Let Denoising Generative Models Denoise" by Tianhong Li & Kaiming He arxiv.org/abs/2511.13720 Diffusion models in pixel-space, without VAE, with clean image prediction = nice generation results. Not a new framework but a nice exploration of the design space of the diffusion models.

0132

Reposted by Anirban Ray

Jan Funke @janfunkey.bsky.social · 17/11/2025

We moved the AI@MBL course "Deep Learning for Microscopy Image Analysis" to HHMI Janelia (@hhmijanelia.bsky.social). Join us for two weeks of intense lectures, exercise, and hands-on project work! Course dates: June 4-18 2026 Application by: January 15 2026 www.janelia.org/you-janelia/...

janelia.org

Deep Learning for Microscopy Image Analysis

Topics The following will be covered extensively during lectures, exercises, and project work: Image denoising and restoration (fully supervised and self-supervised) Image translation (e.g.,

1189

Reposted by Anirban Ray

Julian Tachella @tachellajulian.bsky.social · 05/11/2025

💥 DeepInverse is now part of the official PyTorch Landscape💥 We are excited to join an ecosystem of great open-source AI libraries, including @hf.co diffusers, MONAI, einops, etc. pytorch.org/blog/deepinv...

pytorch.org

DeepInverse Joins the PyTorch Ecosystem: the library for solving imaging inverse problems with deep learning – PyTorch

1105

Reposted by Anirban Ray

Florian Jug @florianjug.bsky.social · 03/11/2025

I’m at #AIS25 today and tomorrow… Where scientists, industry leaders, investors, and policymakers meet to explore the transformative impact of artificial intelligence on scientific discovery. I think this is a very important conversation we must have NOW! 👍

4181

Reposted by Anirban Ray

arxiv cs.CV @arxiv-cs-cv.bsky.social · 31/10/2025

Anirban Ray, Vera Galinova, Florian Jug ResMatching: Noise-Resilient Computational Super-Resolution via Guided Conditional Flow Matching arxiv.org/abs/2510.26601

001

Anirban Ray @anirbanray.bsky.social · 19/10/2025

“We may not win every battle, but we will win the war.” --- Such an appropriate characterization for posterior samplers. Each posterior sample fights its own battle against noise and degradation; some win, some lose. But the MMSE estimate wins the war 😉. #iykuk #ImageRestoration

000

Reposted by Anirban Ray

lebellig @lebellig.bsky.social · 14/10/2025

Diffusion Transformers with Representation Autoencoders by Boyang Zheng, et al (arxiv.org/abs/2510.116...) Unexpected result: swapping the SD-VAE for a pretrained visual encoder improves FID, challenging the idea that encoders' information compression is not suited for generative modeling!

0151

Reposted by Anirban Ray

OMIBS @ MBL @omibs-mbl.bsky.social · 26/08/2025

We had an awesome #OMIBS2025 Thanks to all the lecturers, staff members, vendor faculty, sponsors, and participants for making this an amazing course year!

011

Reposted by Anirban Ray

Simon Kohl @saakohl.bsky.social · 22/07/2025

Introducing Latent-X — our all-atom frontier AI model for protein binder design. State-of-the-art lab performance, widely accessible via the Latent Labs Platform. Free tier: platform.latentlabs.com Blog: latentlabs.com/latent-x/ Technical report: tinyurl.com/latent-X

2124

Reposted by Anirban Ray

lebellig @lebellig.bsky.social · 07/07/2025

New episode in this line of work from @giannisdaras.bsky.social et al. on training diffusion models with mostly bad/low-quality/corrupted data (+few high-quality samples). This time for proteins! 📄 Ambient diffusion Omni: arxiv.org/pdf/2506.10038 📄 Ambient Proteins: www.biorxiv.org/content/10.1...

132

Reposted by Anirban Ray

Mathurin Massias @mathurinmassias.bsky.social · 18/06/2025

New paper on the generalization of Flow Matching www.arxiv.org/abs/2506.03719 🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*? w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇

25617