Anna Foix
@afoix.bsky.social
PhD candidate at EMBL-EBI and the University of Cambridge (Uhlmann Group). Turning bioimages into numbers and finding the stories they hide. Loves math, climbing, and anime
Pinned
Anna Foix
@afoix.bsky.social
· Sep 23
Happy to share that ShapeEmbed has been accepted at @neuripsconf.bsky.social 🎉 SE is self-supervised framework to encode 2D contours from microscopy & natural images into a latent representation invariant to translation, scaling, rotation, reflection & point indexing
📄 arxiv.org/pdf/2507.01009 (1/N)
📄 arxiv.org/pdf/2507.01009 (1/N)
Reposted by Anna Foix
📢 Apply now for the first DL@Janelia Bootcamp (June 4–18, 2026)! 2 weeks of hands-on deep learning for microscopy: train models on your own data, Python needed (no ML experience), housing + meals included, no registration fee
📍 Janelia Research Campus, VA
🗓️ Apply by Jan 15, 2026
🔗 shorturl.at/j4sgY
📍 Janelia Research Campus, VA
🗓️ Apply by Jan 15, 2026
🔗 shorturl.at/j4sgY
November 6, 2025 at 6:56 PM
📢 Apply now for the first DL@Janelia Bootcamp (June 4–18, 2026)! 2 weeks of hands-on deep learning for microscopy: train models on your own data, Python needed (no ML experience), housing + meals included, no registration fee
📍 Janelia Research Campus, VA
🗓️ Apply by Jan 15, 2026
🔗 shorturl.at/j4sgY
📍 Janelia Research Campus, VA
🗓️ Apply by Jan 15, 2026
🔗 shorturl.at/j4sgY
📢 Apply now for the first DL@Janelia Bootcamp (June 4–18, 2026)! 2 weeks of hands-on deep learning for microscopy: train models on your own data, Python needed (no ML experience), housing + meals included, no registration fee
📍 Janelia Research Campus, VA
🗓️ Apply by Jan 15, 2026
🔗 shorturl.at/j4sgY
📍 Janelia Research Campus, VA
🗓️ Apply by Jan 15, 2026
🔗 shorturl.at/j4sgY
November 6, 2025 at 6:56 PM
📢 Apply now for the first DL@Janelia Bootcamp (June 4–18, 2026)! 2 weeks of hands-on deep learning for microscopy: train models on your own data, Python needed (no ML experience), housing + meals included, no registration fee
📍 Janelia Research Campus, VA
🗓️ Apply by Jan 15, 2026
🔗 shorturl.at/j4sgY
📍 Janelia Research Campus, VA
🗓️ Apply by Jan 15, 2026
🔗 shorturl.at/j4sgY
Reposted by Anna Foix
Thrilled to be speaking at #CBIAS2025! 🥳
CBIAS has been my scientific home since the beginning of my PhD, providing a welcoming space for early-career researchers. This year feels extra special, as I’ll be presenting my work in the final year of my PhD.
Join us if you get the chance! 😃
CBIAS has been my scientific home since the beginning of my PhD, providing a welcoming space for early-career researchers. This year feels extra special, as I’ll be presenting my work in the final year of my PhD.
Join us if you get the chance! 😃
The provisional program for The 6th Crick Bioimage Analysis Symposium (#CBIAS2025) is live!
Join us at the @wellcomecollection.bsky.social in London in November for incredible talks, posters and insightful discussions.
Space is limited - register now!
www.crick.ac.uk/whats-on/cri...
Join us at the @wellcomecollection.bsky.social in London in November for incredible talks, posters and insightful discussions.
Space is limited - register now!
www.crick.ac.uk/whats-on/cri...
September 23, 2025 at 12:17 PM
Thrilled to be speaking at #CBIAS2025! 🥳
CBIAS has been my scientific home since the beginning of my PhD, providing a welcoming space for early-career researchers. This year feels extra special, as I’ll be presenting my work in the final year of my PhD.
Join us if you get the chance! 😃
CBIAS has been my scientific home since the beginning of my PhD, providing a welcoming space for early-career researchers. This year feels extra special, as I’ll be presenting my work in the final year of my PhD.
Join us if you get the chance! 😃
Reposted by Anna Foix
My take: Engineering *is* important. Ideas are cheap. Novelty is overrated. "Hyperparameter tuning" is a cynically dismissive term for something that is in fact the real, difficult problem.
Sometimes I’ll see a paper that implements an idea I’ve had but implements it poorly for engineering reasons. But then it’s hard to write a follow up paper because it’s not “novel” anymore
October 9, 2025 at 2:13 PM
My take: Engineering *is* important. Ideas are cheap. Novelty is overrated. "Hyperparameter tuning" is a cynically dismissive term for something that is in fact the real, difficult problem.
Reposted by Anna Foix
Don’t miss Elena’s (from @ilastik-team.bsky.social lab) brilliant work @ #ICCV2025 with @anwaiarchit.bsky.social & @cppape.bsky.social poster 292 @ 11:15AM 🔬They tackle segmentation of massive 3D microscopy images & show how BatchRenorm removes tiling artifacts boosting transferability and clarity🌺
October 22, 2025 at 8:23 PM
Don’t miss Elena’s (from @ilastik-team.bsky.social lab) brilliant work @ #ICCV2025 with @anwaiarchit.bsky.social & @cppape.bsky.social poster 292 @ 11:15AM 🔬They tackle segmentation of massive 3D microscopy images & show how BatchRenorm removes tiling artifacts boosting transferability and clarity🌺
Don’t miss Elena’s (from @ilastik-team.bsky.social lab) brilliant work @ #ICCV2025 with @anwaiarchit.bsky.social & @cppape.bsky.social poster 292 @ 11:15AM 🔬They tackle segmentation of massive 3D microscopy images & show how BatchRenorm removes tiling artifacts boosting transferability and clarity🌺
October 22, 2025 at 8:23 PM
Don’t miss Elena’s (from @ilastik-team.bsky.social lab) brilliant work @ #ICCV2025 with @anwaiarchit.bsky.social & @cppape.bsky.social poster 292 @ 11:15AM 🔬They tackle segmentation of massive 3D microscopy images & show how BatchRenorm removes tiling artifacts boosting transferability and clarity🌺
Attending BISCUIT workshop at #ICCV2025 🌺 — the first talk by @mariavak.bsky.social on quantifying biases in foundation models was fantastic! Exciting to see interdisciplinary efforts focused not just on prediction but on understanding why — and ViTs seem to be the trend in biomedical vision 👩💻
October 19, 2025 at 7:56 PM
Attending BISCUIT workshop at #ICCV2025 🌺 — the first talk by @mariavak.bsky.social on quantifying biases in foundation models was fantastic! Exciting to see interdisciplinary efforts focused not just on prediction but on understanding why — and ViTs seem to be the trend in biomedical vision 👩💻
Reposted by Anna Foix
We’ll be presenting at the #BIC workshop at @iccv.bsky.social! This year’s BIC has amazing speakers 🌺 — join us on 19 October at the Honolulu Convention Center to explore cutting-edge methods at the intersection of computer vision and biology 🔬 #ICCV2025 More details: www.bioimagecomputing.com
BioImage Computing
a truly interdisciplinary workshop
www.bioimagecomputing.com
October 17, 2025 at 7:35 AM
We’ll be presenting at the #BIC workshop at @iccv.bsky.social! This year’s BIC has amazing speakers 🌺 — join us on 19 October at the Honolulu Convention Center to explore cutting-edge methods at the intersection of computer vision and biology 🔬 #ICCV2025 More details: www.bioimagecomputing.com
Reposted by Anna Foix
We’ve upgraded ShapeEmbed 🎉 ShapeEmbedLite decodes latent codes via an MLP to guarantee valid EDMs, making it lighter and ideal for small microscopy datasets or limited compute. Hear more at my BIC workshop talk or poster at #ICCV2025! Try it out at github.com/uhlmanngroup...
October 17, 2025 at 7:35 AM
We’ve upgraded ShapeEmbed 🎉 ShapeEmbedLite decodes latent codes via an MLP to guarantee valid EDMs, making it lighter and ideal for small microscopy datasets or limited compute. Hear more at my BIC workshop talk or poster at #ICCV2025! Try it out at github.com/uhlmanngroup...
Reposted by Anna Foix
Thank you, @afoix.bsky.social!
I am really happy I could be part of this one. Everybody, please enjoy the new ShapeEmbeding goodness!
I am really happy I could be part of this one. Everybody, please enjoy the new ShapeEmbeding goodness!
We’ve upgraded ShapeEmbed 🎉 ShapeEmbedLite decodes latent codes via an MLP to guarantee valid EDMs, making it lighter and ideal for small microscopy datasets or limited compute. Hear more at my BIC workshop talk or poster at #ICCV2025! Try it out at github.com/uhlmanngroup...
October 17, 2025 at 11:43 AM
Thank you, @afoix.bsky.social!
I am really happy I could be part of this one. Everybody, please enjoy the new ShapeEmbeding goodness!
I am really happy I could be part of this one. Everybody, please enjoy the new ShapeEmbeding goodness!
We’ve upgraded ShapeEmbed 🎉 ShapeEmbedLite decodes latent codes via an MLP to guarantee valid EDMs, making it lighter and ideal for small microscopy datasets or limited compute. Hear more at my BIC workshop talk or poster at #ICCV2025! Try it out at github.com/uhlmanngroup...
October 17, 2025 at 7:35 AM
We’ve upgraded ShapeEmbed 🎉 ShapeEmbedLite decodes latent codes via an MLP to guarantee valid EDMs, making it lighter and ideal for small microscopy datasets or limited compute. Hear more at my BIC workshop talk or poster at #ICCV2025! Try it out at github.com/uhlmanngroup...
Reposted by Anna Foix
Also don’t miss:
🧬👯 @epetsalaki.bsky.social’s talk “From Data to Digital Twins” (Wed, Digital Twin Models)
📊🧬 My poster P03.14 – Towards Data-Driven Executable Models (Wed)
🧩🤖 @alussana.bsky.social’s poster P18.13 – Data-Driven Inference of Functionally Coherent Gene Modules (Mon)
🧬👯 @epetsalaki.bsky.social’s talk “From Data to Digital Twins” (Wed, Digital Twin Models)
📊🧬 My poster P03.14 – Towards Data-Driven Executable Models (Wed)
🧩🤖 @alussana.bsky.social’s poster P18.13 – Data-Driven Inference of Functionally Coherent Gene Modules (Mon)
October 5, 2025 at 5:59 PM
Also don’t miss:
🧬👯 @epetsalaki.bsky.social’s talk “From Data to Digital Twins” (Wed, Digital Twin Models)
📊🧬 My poster P03.14 – Towards Data-Driven Executable Models (Wed)
🧩🤖 @alussana.bsky.social’s poster P18.13 – Data-Driven Inference of Functionally Coherent Gene Modules (Mon)
🧬👯 @epetsalaki.bsky.social’s talk “From Data to Digital Twins” (Wed, Digital Twin Models)
📊🧬 My poster P03.14 – Towards Data-Driven Executable Models (Wed)
🧩🤖 @alussana.bsky.social’s poster P18.13 – Data-Driven Inference of Functionally Coherent Gene Modules (Mon)
Reposted by Anna Foix
Happy to share that ShapeEmbed has been accepted at @neuripsconf.bsky.social 🎉 SE is self-supervised framework to encode 2D contours from microscopy & natural images into a latent representation invariant to translation, scaling, rotation, reflection & point indexing
📄 arxiv.org/pdf/2507.01009 (1/N)
📄 arxiv.org/pdf/2507.01009 (1/N)
September 23, 2025 at 8:32 AM
Happy to share that ShapeEmbed has been accepted at @neuripsconf.bsky.social 🎉 SE is self-supervised framework to encode 2D contours from microscopy & natural images into a latent representation invariant to translation, scaling, rotation, reflection & point indexing
📄 arxiv.org/pdf/2507.01009 (1/N)
📄 arxiv.org/pdf/2507.01009 (1/N)
Thrilled to be speaking at #CBIAS2025! 🥳
CBIAS has been my scientific home since the beginning of my PhD, providing a welcoming space for early-career researchers. This year feels extra special, as I’ll be presenting my work in the final year of my PhD.
Join us if you get the chance! 😃
CBIAS has been my scientific home since the beginning of my PhD, providing a welcoming space for early-career researchers. This year feels extra special, as I’ll be presenting my work in the final year of my PhD.
Join us if you get the chance! 😃
The provisional program for The 6th Crick Bioimage Analysis Symposium (#CBIAS2025) is live!
Join us at the @wellcomecollection.bsky.social in London in November for incredible talks, posters and insightful discussions.
Space is limited - register now!
www.crick.ac.uk/whats-on/cri...
Join us at the @wellcomecollection.bsky.social in London in November for incredible talks, posters and insightful discussions.
Space is limited - register now!
www.crick.ac.uk/whats-on/cri...
September 23, 2025 at 12:17 PM
Thrilled to be speaking at #CBIAS2025! 🥳
CBIAS has been my scientific home since the beginning of my PhD, providing a welcoming space for early-career researchers. This year feels extra special, as I’ll be presenting my work in the final year of my PhD.
Join us if you get the chance! 😃
CBIAS has been my scientific home since the beginning of my PhD, providing a welcoming space for early-career researchers. This year feels extra special, as I’ll be presenting my work in the final year of my PhD.
Join us if you get the chance! 😃
Happy to share that ShapeEmbed has been accepted at @neuripsconf.bsky.social 🎉 SE is self-supervised framework to encode 2D contours from microscopy & natural images into a latent representation invariant to translation, scaling, rotation, reflection & point indexing
📄 arxiv.org/pdf/2507.01009 (1/N)
📄 arxiv.org/pdf/2507.01009 (1/N)
September 23, 2025 at 8:32 AM
Happy to share that ShapeEmbed has been accepted at @neuripsconf.bsky.social 🎉 SE is self-supervised framework to encode 2D contours from microscopy & natural images into a latent representation invariant to translation, scaling, rotation, reflection & point indexing
📄 arxiv.org/pdf/2507.01009 (1/N)
📄 arxiv.org/pdf/2507.01009 (1/N)
Reposted by Anna Foix
Thanks for all the trainers and attendees on this course, which was a lot of fun to run, and hopefully filled a gap in genomics/modelling training
And especially co-organisers @leonielorenz.bsky.social @sonjalehtinen.bsky.social Joel Hellewell
And especially co-organisers @leonielorenz.bsky.social @sonjalehtinen.bsky.social Joel Hellewell
Thank you to everyone who joined us this week for the @embo.org Practical Course 'Methods for infectious disease modelling using genomics'.
Join us for 2026's EMBO Practical Course. Sign up for 'Causality in biomedicine' alerts and hear as this new course develops: www.ebi.ac.uk/training/eve...
🧬🧫
Join us for 2026's EMBO Practical Course. Sign up for 'Causality in biomedicine' alerts and hear as this new course develops: www.ebi.ac.uk/training/eve...
🧬🧫
September 22, 2025 at 9:43 AM
Thanks for all the trainers and attendees on this course, which was a lot of fun to run, and hopefully filled a gap in genomics/modelling training
And especially co-organisers @leonielorenz.bsky.social @sonjalehtinen.bsky.social Joel Hellewell
And especially co-organisers @leonielorenz.bsky.social @sonjalehtinen.bsky.social Joel Hellewell
It’s crucial that the bioimage community joins spaces long dominated by computer vision/CS to highlight challenges in microscopy data and how we tackle them. Brilliant talk from @aafkegros.bsky.social showing how biology is both exciting and challenging👩🏻💻🔬🧬🦠 #bioimage #microscopy #interdisciplinary
I gave a talk at Blender Conference yesterday, showing how biological volumes work, and how to visualize them in Blender 😋 youtu.be/WPajSWX730o?... #bcon25
Microscopy Nodes: handling large biological volumes — Blender Conference 2025
YouTube video by Blender
youtu.be
September 19, 2025 at 8:00 AM
It’s crucial that the bioimage community joins spaces long dominated by computer vision/CS to highlight challenges in microscopy data and how we tackle them. Brilliant talk from @aafkegros.bsky.social showing how biology is both exciting and challenging👩🏻💻🔬🧬🦠 #bioimage #microscopy #interdisciplinary
Reposted by Anna Foix
The abstract submission deadline for #CBIAS2025 has just closed and, for the first time, we have a near perfect gender-balance in our abstract submissions.
In fact, we have slightly more submissions from women than men.
In fact, we have slightly more submissions from women than men.
a man with his arms crossed is smiling and saying noice !
ALT: a man with his arms crossed is smiling and saying noice !
media.tenor.com
September 1, 2025 at 9:44 AM
The abstract submission deadline for #CBIAS2025 has just closed and, for the first time, we have a near perfect gender-balance in our abstract submissions.
In fact, we have slightly more submissions from women than men.
In fact, we have slightly more submissions from women than men.
Reposted by Anna Foix
![Comic. A snake slithers around a hypercube. No two non-consecutive parts of its coils can be on adjacent corners. [Three small 4-dimensional hypercubes showing disallowed options with one large cube with snake wrapped around it. Dimensions = 4. Max Length - 7.] Snake(N) = Longest snake that can fit in an n-dimensional hypercube. Snake(N=1, 2, 3…8) = 1, 2, 4, 7, 13, 26, 50, 98. Snake(N>8) = UNSOLVED. [caption] It turns out every scientific field has a key thought experiment that involves putting a cute animal in a weird box for no reason. So far, quantum mechanics and graph theory have found theirs, but most other fields are still working on it.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:cz73r7iyiqn26upot4jtjdhk/bafkreicjbjwxfe3ef6styvrvsjtt63znh24tfuqxlceewi3b6t7zfu756i@jpeg)
August 8, 2025 at 4:22 AM
Reposted by Anna Foix
"i asked grok" "i asked chatgpt" yeah well i asked carl sagan and he said the greatest enemy of knowledge is not ignorance but the illusion of knowledge 🧪
July 18, 2025 at 4:12 AM
"i asked grok" "i asked chatgpt" yeah well i asked carl sagan and he said the greatest enemy of knowledge is not ignorance but the illusion of knowledge 🧪
Reposted by Anna Foix
Can robots in a swarm act like the cells of an organism? Thanks to Sedeer El-Showk for the new article in @nature.com, which highlights the work of a number of research groups, including our own, on how “Robots demonstrate principles of collective intelligence”. www.nature.com/articles/d41...
July 21, 2025 at 10:28 AM
Can robots in a swarm act like the cells of an organism? Thanks to Sedeer El-Showk for the new article in @nature.com, which highlights the work of a number of research groups, including our own, on how “Robots demonstrate principles of collective intelligence”. www.nature.com/articles/d41...
Reposted by Anna Foix
🔬API-first feature extraction for image-based profiling workflows
If you need to obtain interpretable features from your segmented microscopy images, but want to do it in a fully automated way, we know the struggle.
1/6
If you need to obtain interpretable features from your segmented microscopy images, but want to do it in a fully automated way, we know the struggle.
1/6
July 8, 2025 at 7:22 PM
🔬API-first feature extraction for image-based profiling workflows
If you need to obtain interpretable features from your segmented microscopy images, but want to do it in a fully automated way, we know the struggle.
1/6
If you need to obtain interpretable features from your segmented microscopy images, but want to do it in a fully automated way, we know the struggle.
1/6
Reposted by Anna Foix
And just like that @katharinaweins.bsky.social and Elvira Isenring managed to make us look cooler than we'll ever be:
www.youtube.com/watch?v=8t8R...
www.youtube.com/watch?v=8t8R...
Bioimaging | UZH Research Spotlight
YouTube video by Universität Zürich
www.youtube.com
June 24, 2025 at 5:39 PM
And just like that @katharinaweins.bsky.social and Elvira Isenring managed to make us look cooler than we'll ever be:
www.youtube.com/watch?v=8t8R...
www.youtube.com/watch?v=8t8R...
Reposted by Anna Foix
Spotiflow, our deep learning based spot detection method for microscopy, is now published in @natmethods.nature.com!
Since the pre-print, we have added many features, notably native 3D detection!
@maweigert.bsky.social @gioelelamanno.bsky.social @epfl-brainmind.bsky.social
Paper: rdcu.be/epIB7
(1/N)
Since the pre-print, we have added many features, notably native 3D detection!
@maweigert.bsky.social @gioelelamanno.bsky.social @epfl-brainmind.bsky.social
Paper: rdcu.be/epIB7
(1/N)
Spotiflow: accurate and efficient spot detection for fluorescence microscopy with deep stereographic flow regression
Nature Methods - Spotiflow uses deep learning for subpixel-accurate spot detection in diverse 2D and 3D images. The improved accuracy offered by Spotiflow enables improved biological insights in...
rdcu.be
June 6, 2025 at 6:58 PM
Spotiflow, our deep learning based spot detection method for microscopy, is now published in @natmethods.nature.com!
Since the pre-print, we have added many features, notably native 3D detection!
@maweigert.bsky.social @gioelelamanno.bsky.social @epfl-brainmind.bsky.social
Paper: rdcu.be/epIB7
(1/N)
Since the pre-print, we have added many features, notably native 3D detection!
@maweigert.bsky.social @gioelelamanno.bsky.social @epfl-brainmind.bsky.social
Paper: rdcu.be/epIB7
(1/N)
Reposted by Anna Foix
Out today in @natmethods.nature.com : Spotiflow, our transcript localization method for imaging-based spatial transcriptomics. Led by amazing PhD student @albertdm.bsky.social, joint work w @gioelelamanno.bsky.social at EPFL / @scadsai.bsky.social
www.nature.com/articles/s41...
rdcu.be/epIB7
www.nature.com/articles/s41...
rdcu.be/epIB7
June 6, 2025 at 7:06 PM
Out today in @natmethods.nature.com : Spotiflow, our transcript localization method for imaging-based spatial transcriptomics. Led by amazing PhD student @albertdm.bsky.social, joint work w @gioelelamanno.bsky.social at EPFL / @scadsai.bsky.social
www.nature.com/articles/s41...
rdcu.be/epIB7
www.nature.com/articles/s41...
rdcu.be/epIB7