Robert Haase
Biomedical Computer Vision & Language Models, scads.ai / Leipzig University, also NFDI4BIOIMAGE, NEUBIAS/GloBIAS, GPUs, AI, ML 🔬🖥️🚀 views:mine
- Reposted by Robert HaaseImage analysis is often treated as an individual skill—leading to irreproducible pipelines and bias. Sustainable #BioImageAnalysis must be an institutional responsibility: training, automation, standards, and GSP-aligned guidance. Read the full article on LinkedIn: www.linkedin.com/feed/update/...
- Reposted by Robert HaaseWissenschaffende arbeiten intensiv daran, LLMs der Community zur Verfügung zu stellen, die lokal laufen und Code für spezifische Aufgaben produzieren. @haesleinhuepf.bsky.social hat „bia-bob“ gebaut, um Menschen beim Erstellen von Code für Bildanalyse zu helfen. 8/9
- Reposted by Robert HaaseDas Umwandeln von Bildern in Zahlen zur Quantifizierung wird als Bildanalyse bezeichnet. Das ist ein eigenständiges Forschungsgebiet, das von vielen Wissenschaffenden weiterentwickelt wird. (Das Bild ist ein Sticker, gefunden in einer Bahn der LVB) 1/9
- Reposted by Robert HaaseDie Doktorandin Elena Nicolay forscht am mTox Lab des ufz.de in Leipzig; www.ufz.de/index.php?de...
- [Admin] Unweltchemikalien und Darmentzündungen - Bitte begrüßt Elena Katharina Nicolay ganz herzlich auf dem Kanal! realscientistsde.blogspot.com/2026/01/unwe...
- Reposted by Robert HaaseA Comment discusses how commands, data, and metadata currently discarded by scientific instruments could be used to train AI systems to learn to conduct experiments. @henrypinkard.bsky.social @nilsnorlin.bsky.social www.nature.com/articles/s41...
- Reposted by Robert HaaseWir sind Platz 1! 🏆 Unsere #BibliothecaAlbertina ist die schönste Uni-Bib Deutschlands – so das Ergebnis der Instagram-Umfrage von funk. Dem haben wir nichts hinzuzufügen, oder @unileipzig.bsky.social? 🥳
- On my way for my second guest lecture about the Secrets of LLMs @tudresden.bsky.social 🚅 Last week was about Vision Language Models, this week I'll talk about AI-agents. Thanks Michael Färber and Simon Razniewski @scadsai.bsky.social for having me! Slides #openaccess 🧑🏫💻🔓 zenodo.org/records/1829...
- Reposted by Robert HaaseI wrote a post describing a minimal set of principles that I've been using to make my research papers a bit more reproducible. Would love hearing what you think! #OpenScience brunovellutini.com/posts/daft-p...
- For teaching purposes, I vibe-coded an MCP server that querys the meal plan of the canteens at @tudresden.bsky.social 🍲🤖 And yes, I will be giving the related lecture just before lunch 😋 github.com/ScaDS/mensa-...
- The new stackview (0.19.1) comes with a zoom() function. 🔍🚀 Give it a try using pip install stackview==0.19.1 (Example image licensed CC-BY 4.0 by Alexandr Khrapichev, Oxford) pypi.org/project/stac...
- Years ago, I spent endless time to write hundreds of image processing filters so that they run on GPUs; resulting in the #clij library. Today, I asked claude to write the Kuwahara Filter in the CLIJ OpenCL dialect and it worked in the first attempt. Mind-blow-ing. 🤯
- Just adding a link to #clij, from the time when things were written by humans 😊 clij.github.io
- Reposted by Robert HaaseI am looking for two postdocs to join our lab - One (bio)image analyst - One cell biologist interested to work on lymphatics! The positions will open soon, be in touch!
- Reposted by Robert HaaseWe're happy to announce that the IJCAI-ECAI 2026 - the leading academic conference on #ArtificialIntelligence - will take place in #Bremen, Germany from 15th of August 'til 21st of August 2026! More details about Calls for Papers/Proposals and Special Tracks 👉 2026.ijcai.org
- Reposted by Robert Haase[This post could not be retrieved]
- Reposted by Robert HaaseUnder greedy/low-temp decoding, reasoning LLMs get stuck in loops repeating themselves, wasting test-time compute and sometimes never terminating! They find that: - Low temps => more looping - Smaller models => more looping - Harder problems => more looping
- Reposted by Robert Haase🔬 🖥️ Applications are open for the CSHL course Quantitative Imaging: From Acquisition to Analysis (April 6–21, 2026)! An intensive, hands-on course covering advanced fluorescence microscopy and quantitative image analysis using open-source tools. 🗓️ Apply online by Jan 30, 2026
- Reposted by Robert HaaseIf you have time tomorrow, join my online talk about LLS/single molecule/microtubules and 3D data at @bioimagingna.bsky.social user group (18:00 CET for Europe). I hope I manage to fit 25 movies into 20 cohesive slides and connection will be ok.
- #HappyMicroscpyMonday #microscopycommunity - Join us tomorrow, Tue Jan 6 for a talk by Eugene Katrukha on "Single molecule imaging using LLS7", hosted by the BINA Lattice Lightsheet User Group Learn more & register here: buff.ly/US5Xd2q
- Reposted by Robert HaaseApply for a PhD in Singapore at NUS! Deadline Jan 12. I'm recruiting: Here with Mechanobiology Institute: www.mbi.nus.edu.sg/education/gr... and Here with Biomedical Engineering dept: cde.nus.edu.sg/bme/
- How your email from mid December finds me
- Reposted by Robert Haase🚨 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/...
- Reposted by Robert HaaseMerry Christmas one and all, from the Vaders 🎄
- Recommended train-ride-read about socio-technical challenges in the triangle between Data Scientists, Software Engineers and Product Value. 👌 Fantastic summary of common real project issues + practical tips and guidelines 🤩 sws.informatik.uni-leipzig.de/wp-content/u...
- Recommended train-ride-read about socio-technical challenges in the triangle between Data Scientists, Software Engineers and Product Value. 👌 Fantastic summary of common real project issues + practical tips and guidelines 🤩 sws.informatik.uni-leipzig.de/wp-content/u...
- Reposted by Robert Haase🚀📰 End-of-year news for #RxivMaker =). Now it generates both #pdf and #docx from #markdown. Docx makes it easier to collaborate on a document for non-markdown users, making it simple to loop between docx and #RxivMaker to a professional-looking #preprint Preprint updated: arxiv.org/abs/2508.00836
- Reposted by Robert HaaseNew video: more examples showing deep learning segmentation failure modes—and how to detect them with Napari. I show how Napari’s layer system compares images, ground truth, and results, and how Appose enables comparison across incompatible DL packages. www.youtube.com/watch?v=c369...
- Reposted by Robert HaaseGreat to teach a Git version-control session as part of the workshop on reproducible workflows for scientific computing! 💻 👩💻📊 Workshop from the @carpentries.carpentries.org in collaboration with @babeheim.bsky.social hosted by @mpi-eva-leipzig.bsky.social #git #coding #github #AcademicSky
- Teaching Academic life to cats, lesson 301: Funding Opportunities 💸🐈
- Credits for this amazing card game: fortrama.net
- Reposted by Robert HaaseMastodon: the Command Center for Large-Scale Lineage-Tracing Microscopy Datasets biorxiv.org/content/10.64898/20…
- Reposted by Robert Haase#NFD4BIOIMAGEfromAtoZ - K for Knowledge Graph @nfdi4bioimage.bsky.social has its own #knowledgegraph (#N4BIKG) since July. It contains information about the consortium, services, and research artifacts deposited in #Zenodo. 👉 More information: mpievolbio-scicomp.pages.gwdg.de/blog/post/20...
- #paperalert 🚨 Check out AutoEncodix, a framework for multi-omics data integration and analysis using autoencoders developed #opensource by Jan Ewald and his team @scadsai.bsky.social github.com/jan-forest/a...
- 📢Jan Ewald and colleagues from @scadsai.bsky.social introduce an open-source tool called AUTOENCODIX, developed to enable reproducible comparison of vanilla, variational, stacked, ontology-based, and cross-modal autoencoders for biological molecular profiling data. www.nature.com/articles/s43...
- Do you enjoy exploring embeddings interactively as much as I do? Check out _embeddoor_! I recently vibe-coded it while watching too many Harry Potter movies 😃 Feedback welcome as more features will certainly come! github.com/haesleinhuep...
- Reposted by Robert HaaseInterested in Zebrafish brain imaging? We released a 3D printed mold that's is super helpful for us. Check it out Customizable FDM-based zebrafish embryo mold for live imaging www.biorxiv.org/content/10.1... Work by Marcela and Jaakko in the lab
- Reposted by Robert HaaseAs part of the #NFDI4DS conference, @haesleinhuepf.bsky.social from @nfdi4bioimage.bsky.social gave a presentation on 'How LLMs impact BioImage Data Science', which is now available at #Zenodo. 🍁 👉 Learn more about the use of LLMs and code generation for bioimage analysis: doi.org/10.5281/zeno...
- Today announcement in the train: “Ladies and gentlemen, after our train driver once again drove like a young god, we are now 8 minutes early in Bitterfeld.” The whole carriage bursts out laughing. Cudos @deutsche-bahn.bsky.social
- Reposted by Robert HaaseAt the end of September @haesleinhuepf.bsky.social, training coordinator @scadsai.bsky.social held the AI competence training AI4psychology which focused on fundamentals, efficient application, risks, and legal framework of AI models and systems. Find the slides here: 👉 doi.org/10.5281/zeno...
- Reposted by Robert HaaseWe just released a new major version of TrackMate (v8), the cell and organelle tracking plugin of Fiji. It ships many new features, detailed below, but that are articulated around the following:
- Reposted by Robert HaaseCollaboration is key to the success of #NFDI from the very beginning. Here is the next video in our strategy series with York Sure-Vetter – this time it's about working together. 🤝 ➡️ About the NFDI strategy: www.nfdi.de/verein/ ➡️ About the sections: www.nfdi.de/sektionen/ #fdm #rdm #researchdata
- Reposted by Robert HaasePreprint alert! CochleaNet, our framework for analyzing light-sheet data of the cochlea. It consists of three networks to segment spiral ganglion neurons, inner hair cells, and to detect synapses. See rendering of a full cochlea in the image, find the preprint at doi.org/10.1101/2025....
- Reposted by Robert HaaseNow on #Zenodo: "Data literacy, Open Science and Collaborative Coding and CI/CD" slides from the @Sca_DS GA workshop presented by Mike Berger, Pia Voigt and Matthias Täschner. Share, copy, distribute & adapt the work with proper credit to creators! 🔗 zenodo.org/records/17130780
- Reposted by Robert HaaseWhat aspects of human knowledge do vision models like CLIP fail to capture, and how can we improve them? We suggest models miss key global organization; aligning them makes them more robust. Check out LukasMuttenthaler's work, finally out (in Nature!?) www.nature.com/articles/s41... + our blog! 1/3
- Reposted by Robert HaaseJoin our 34th Living Lab Lecture about "Demystifying Data Stream Processing"! 🗣️ Apurv Deepak Kulkarni (@scadsai.bsky.social / @tudresden.bsky.social) 📅 November 20 | 11 AM 📍 Online (tud.link/i8zf) 👉 scads.ai/event/living-lab-le…
- Reposted by Robert HaaseWould you like to learn more about #XAI? Take a look at @haesleinhuepf.bsky.social's presentation on "Explainable Machine Learning" on the @scadsai.bsky.social #Zenodo page. It covers the basics, including SHAP analysis and Grad-CAM as examples. 👉 f.mtr.cool/mzmitnigaa
- Reposted by Robert HaaseSeeing our good old AURA-Net from 2021 (doi.org/10.1109/ISBI...) end up 2nd on a 2025 U-Net variants leaderboard was not on my bingo card for this year, but here we are (source: doi.org/10.48550/arX...)
- Reposted by Robert HaaseJupyterCon!
- Reposted by Robert HaaseThis is the eXplainable AI research channel of the machine learning group of Prof. Klaus-Robert Müller at Technische Universität Berlin @tuberlin.bsky.social & BIFOLD @bifold.berlin. Let's connect! #XAI #ExplainableAI #MechInterp #MachineLearning #Interpretability
- Reposted by Robert Haase#GloBIAS2025 is ongoing with amazing speaker lineups at Kobe city Beautiful location, amazing food and warm bioimage analysis community. What wlse does one need? 😊 Thanks to @globias.bsky.social for this event
- Reposted by Robert HaaseUsing #LLMs for science👨💻💬? We have a fun tool for you: introducing #folder2md4llms. It converts an entire folder of docs/code/pdfs/pptx into a single markdown file that you can upload to your chatbot of choice. We use it to talk with our publications database or code repos github.com/HenriquesLab...
- Reposted by Robert HaaseWe just released "German Commons", the largest openly-licensed German text dataset for LLM training: 154B tokens with clear usage rights for research and commercial use. huggingface.co/datasets/coral-nlp/german-commons
- Reposted by Robert HaaseEpisode 17 - perhaps my favorite yet. How do you write a forum.image.sc post that will get you the answers you need without revealing information you don't want to tell? @erinweisbart.bsky.social and I go through what the experts need to know to help you. Post your sci q's today on forum.image.sc !
- Episode 16 - Learn more about the Cell Painting Gallery, a free repository of nearly a petabyte of images and imaging data, curated by the incredibly talented @erinweisbart.bsky.social . Truly a goldmine for big-data lovers everywhere!
- I just finished my @unileipzig.bsky.social #LunchLecture. Thanks everyone for the vivid discussion and Nicole Koburger for hosting us! The slides are online #openaccess 🧑🏫🔓 zenodo.org/records/1742...
- Reposted by Robert HaaseOne more open position at the Data Science Centre here! This one is working on our recently open-sourced ELN/LIMS/all-in-one solution LabID (gitlab.com/lab-integrat...). If you have either full stack or scientific workflows experience, check it out! embl.wd103.myworkdayjobs.com/en-US/EMBL/j...
- Reposted by Robert HaaseMissed our #ScaDSAIMeetup on AI insights into the Model Context Protocol (#MCP)? All talks, workshop materials & repos are now on #Zenodo! 🎤 Talks: doi.org/10.5281/zenodo.17158643 🛠️ Workshop: zenodo.org/records/17158770"
- Reposted by Robert HaaseThe next @unileipzig.bsky.social's #LunchLectures will take place on October 23, this time featuring @haesleinhuepf.bsky.social from @scadsai.bsky.social . He will give a lecture on “How generative AI influences research and teaching.” 👉 f.mtr.cool/srahlhpary
- Reposted by Robert HaaseAs part of our monthly meeting, we do a run-down of all* the new #bioimageanalysis tools that have been published in the last couple of weeks on BioRxiv**, so I thought I'd start sharing here as well. *I will miss some, apologies if I miss your paper
- Reposted by Robert HaaseTogether with the @iom-leipzig.bsky.social, @haesleinhuepf.bsky.social & Matthias Täschner hosted the #AISchool2025 last week in Leipzig. The Materials were provided by @scadsai.bsky.social. 👉 f.mtr.cool/yzmimoxbvz #MachineLearning #DataVisualization #HPCWorkflows
- Data Management Plan: * We will keep all data and literature in open browser tabs sychronized between the computers of all project members using the same Google Chrome profile. * By the end of the project we publish the username and password of that profile under a CC-BY 4.0 license.
- "LLMs are here to stay. [...] The best developers won’t be the ones who write every line by hand." 👍
- Some thoughts on LLMs, Autopilot, and VibeCoding rahulpandita.me/blog/2025-10...
- Reposted by Robert Haase🚀Join Helsinki BioImaging as an Image Analysis Specialist🖥️to support cross-disciplinary image analysis projects. If you love coding and are interested in working at the crossroads of computer science and biology, apply by 🗓️ November 15, 2025⤵️ jobs.helsinki.fi/job/Helsinki... #jobopening
- Reposted by Robert Haase#Forschungsbewertung im Fokus Die Veranstaltung am 10.09.25 bot Raum für Austausch: Warum sind Reformen nötig? Welche Chancen und Herausforderungen ergeben sich daraus? Und welchen Mehrwert bietet eine Mitgliedschaft in der internationalen CoARA – Coalition for Advancing #ResearchAssessment?
- Reposted by Robert HaaseThe next @scadsai.bsky.social Meetup on October 21 will give you the chance to learn more about two highly topical fields of AI application: "Sovereign GenAI & Research Agents in Practice". Register here, join the meetup community and share your ideas: 👉 scads.ai/event/meetup/
- Reposted by Robert Haase🥇Congratulations to Filippo de Bortoli from @scadsai.bsky.social, who attended the #FroCoS2025 in Reykjavík, Iceland. He won the Best Student Paper Award for a paper co-authored with @scadsai.bsky.social PI Prof. Franz Baader. Read more about the paper: 👉 f.mtr.cool/yegcmotvkl
- Reposted by Robert Haase[This post could not be retrieved]
- Reposted by Robert HaaseJob alert! We are looking for a bioimage analysis to work in an image analysis core facility in beautiful Paris. Can I ask you to share this opportunity with your networks? See also on the forum: forum.image.sc/t/research-e...
- Reposted by Robert HaaseSecond, for a Mathematical Modeling Specialist - this person will consult and collaborate in projects, but also engage in training and establishing a community of practice. embl.wd103.myworkdayjobs.com/en-US/EMBL/j...
