Virtual Cells at ICLR'26 Conference

This month's meetup discusses 3 papers from the ICLR 2026 conference held in April.

This won't be as much of a deep dive into one paper, but I'd like to give an overview / some intuition on latest modeling approaches in cell modeling & AI in biology.

1 - scDFM - a flow matching model predicting cell transitions in the transcriptomics space as a result of applying perturbations

2 - TxFM - a masked autoencoder style foundation model trained on a well-curated transcriptomics dataset. Authors demonstrate: how important data quality is in biological models, outweighing sheer scale.

3 - VCWorld - a world model approach for virtual cell simulation. A white-box, cell simulator approach that combines structured biological knowledge with LLMs

=== ENTRY DETAILS ===

- QR code with entry information will be available soon, in the "Photos" section of this event page.
- Gate closes at 18:15 - no late entries.