iiinova — where your digital self keeps evolving

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 22/05/2026

This morning I had the chance to present my research at the Cancéropôle IDF "AI & Cancer" day. Talking single-cell foundation models to cancer researchers and clinicians was a great exercise! 😅 1/2

111

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 20/04/2026

🚨 2026 Lilly x Nucleate Grand Challenge: Aging Reimagined 🔬 $100K non-dilutive 🏛️ Pitch at Lilly HQ 🤝 Lilly's science + venture teams Focus: mobility, cognition, immune resilience, regenerative medicine — the frontiers of healthspan. 📅 May 15 👉 linktr.ee/lillygrand...

000

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 13/04/2026

Instead of attending to every pair of positions, you make two lightweight passes — one along rows, one along columns. I Just wrote up a small blogpost about it: 📖 jkobject.com/criss-c... Would love to hear from anyone exploring efficient attention mechanisms 🙂 #Transformers #Attention 2/2

000

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 05/12/2025

It was a blast hosting our Nucleate Inside AI roundtable at the France Techbio 2025 event.

110

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 25/09/2025

The first 1 million prime numbers vizualized in 2D according to their prime factors (Umap) Source: johnhw.github.io/uma...

031

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 20/06/2025

By using common fine-tuning mechanism we show how one can train from one scale to the next by back-propagating signal to the compressed tokens and lower scale model.

100

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 20/06/2025

Each group of biologist are on their own niche and so too are the models. But These models talk about different steps of the same stair. We present ideas on how we might end up training models from atoms to organs by using transformers to compress 🔺 🔻 data into tokens used by larger scale models

100

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 20/06/2025

Very happy to share that my new paper got accepted at the ICML workshop for Foundation model for Life Sciences!! www.biorxiv.org/cont... Foundation Models are being trained from atoms to molecules ⚛️, molecule chains 🧬, entire cells 🦠, and even groups of cell across tissue slices 🫁

111

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 23/05/2025

As part of my research, I believe that scientific outreach is essential. Last week, I had the pleasure of presenting how AI can help us understand biology and the cell at Pint of Science 2025! I also put together a short video recap (in French) for those curious: youtu.be/fc8L8Dn_7tw... 1/2

100

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 23/05/2025

100

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 09/12/2024

Thanks again team and congrats on the First Place!! 6/6

120

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 09/12/2024

Nothing is publication worthy of course and many important problems were not solved like batch effects, adaptive patch size etc. But still seeing what can be done with drive and elbow grease makes me optimistic about the future! 5/6

110

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 09/12/2024

Secondly we have ran scPRINT on gene panel ST datasets like Xenium to predict cell level cell type, disease, and impute the remaining gene's expression. With surprising ability to predict some cancerous cells in BRCA slides. Many other ideas were unfinished. 4/6

110

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 09/12/2024

Finding similar patients through their slides or slide subsets, To retrieve associated molecular profiles, disease subtypes, and treatment and health journey. Our tool automatically downloads the HEST1K database and generates anndata with patch embeddings. 3/6

110

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 09/12/2024

We manage to introduce a pipeline mixing spatialdata, #scPRINT #HEST1K #CONCH #SPATIALDATA and #NAPARI. Our first POC was STsimilarity: finding similar image patches across a large database of histopatologic slides. 2/6

110

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 19/11/2024

I thus decided to formalize it by creating GRnnData: First it is a tool to import and store many different network format to an AnnData. 💁 But it also contains more bells and whistles to work with gene networks! (like subsetting some genes, extracting targets, plotting 💹. 5/6

100

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 19/11/2024

Interestingly, there is a possible standard for it! 🎉AnnData contains the .varp field which is made to store var to var (e.g. genes to gene) relationships. However not many people use it… 4/6

100

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 19/11/2024

However, working with gene networks, I have seen various ways to store them throughout the different papers and benchmarks. Often as some kind of tsv/csv/… file with some kind of a gene-gene list. This lack of standard makes it quite hard to work with gene networks🙉 3/6

100

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 19/11/2024

Multi-modal AI in Biology will certainly be some kind of multi-scale approach where each modalitity is feeding into the next. Transformer use embeddings of element they look at. each can be produced by the previous scale transformer model. going from molecules to whole tissues!

000

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 19/11/2024

💯 🙏 Also, I would like to acknowledge the important pioneering work from Geneformer, UCE, scFoundation and scGPT. Thanks to FlashAttention, pytorch, lightning, and scanpy for their toolkits. Thanks to Omnipath, Scenic+, Openproblems, Replogle et al. and Mc Calla et al.

000

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 19/11/2024

We propose to use the specificity of scRNAseq data and define a multi task pre-training composed of expression denoising, bottleneck learning and classification. We also propose a new hierarchical classification method to work with the rich hierarchical ontologies used to label cells in cellxgene.

100

Jeremie Kalfon 👨‍💻🧬🤖🚀 @jkobject.com · 19/11/2024

-> it is for now a pre-print and more is to come but here are some of our results: scPRINT is a transformer model trained on 50M cells 🦠 from the cellxgene database, it has novel expression encoding and decoding schemes and new pre-training methodologies 🤖. www.biorxiv.org/content/10.1...

110