@InvertTheWing Don't think adding a stochastic interpreter to this will fix mistakes. How can you automate an interpretative process with a hallucinating system?
El mapa que os traigo hoy muestra la extensión estimada del euskera a finales del siglo XVI.
Se evidencia el retroceso que estaba sufriendo la lengua en las riberas y zonas llanas del valle del Ebro, pero también su extensión más allá de las fronteras modernas de Euskal Herria.
When I was an academic, I first started attending conferences affiliated with a bad, obscure university in (what was then) a country whose universities weren't well known. Obv got snubbed all the time.
Then I moved to a well respected prestigious university. People came up to talk to me at conferences.
I guess for most people this would've felt like "I made it," but for me it made academia feel like a sham. I was the same person, working with the same ideas, with the same potential. But brand name on the badge meant value, so to me these people were spiritually no different from the Kardashians.
How does an embryo reliably "compute" its form - "cell by cell" - using only local interactions and mechanics, yet produce a precise global body plan? I’m excited to share our Nature Methods paper "MultiCell: geometric learning in multicellular development", presenting #AIxBiology research led by @HaiqianYang and the result of a great collaboration with Ming Guo, George Roy, Tomer Stern, Anh Nguyen and Dapeng Bi.
A long-standing challenge in developmental biology is to predict how thousands of cells collectively self-organize as tissues fold, divide, and rearrange. In MultiCell, we represent a developing embryo as a dual graph that unifies two complementary views of tissue mechanics with single-cell resolution: cells as moving points (granular) and cells as a connected foam (junction network). This lets the model learn dynamics from both geometry and cell–cell connectivity.
On whole-embryo 4D light-sheet movies of Drosophila gastrulation (~5,000 cells), our model predicts key cell behaviors and the timing of events, including junction loss, rearrangements, and divisions with high accuracy, at single-cell resolution. Beyond prediction, the same representation supports robust time alignment across embryos and offers interpretable activation maps that highlight the morphogenetic "drivers" of development. The broader goal is a foundation for cell-by-cell forecasting in more complex tissues, and eventually for detecting subtle dynamical signatures of disease.
Kudos to the team for this inspiring collaboration with brilliant researchers to push the boundary of AI for biology!
Citation: Yang, H., Roy, G., Nguyen, A.Q., Buehler, M.J., et al. MultiCell: geometric learning in multicellular development. Nature Methods (2025), DOI: 10.1038/s41592-025-02983-x
Code/data links are in the manuscript.
Assassinated MIT Fusion professor was like, essentially:
`What if we just ignore Einstein and treat plasma as a continuous fluid, instead of particles?`
It's Aetherial mechanics, like what Lorentz and Tesla believed in:
Here's the timestamp:
https://t.co/QK9PXmDHoz