Physics foundation model Walrus finetuned to predict living embryo tissue flow
ninamiolane · x · 2026-10-20
An internship project at PolymathicAI asks whether a foundation model trained on simulated physical systems can predict how living embryo tissue flows. The team finetuned Walrus on 12 wild-type Drosophila blastoderm videos and tested it on unseen conditions, using footage from EMBL — an AI-for-Science attempt to transfer a physics foundation model to live biology.
More from Research
- Stanford and Databricks use AI agents to reproduce medical findings and test analytical robustness — ChengleiSi · 2026-10-23
- EMNLP paper: diffusion LMs internally encode latent denoising timestep representations — gsarti_ · 2026-10-23
- KU Leuven and VIB open two Group Leader professorships in AI for Biology, start 2027 — jpillowtime · 2026-10-23
- Subspace Tuning curbs LLM catastrophic forgetting by freezing principal singular directions — scottniekum · 2026-10-23
- Perceptic launches PercepticOS, an AI workspace for 'scientific superintelligence' — nathanbenaich · 2026-10-23
- EPFL's Bosselut to talk long context as test-time learning at ELLIS seminar — andre_t_martins · 2026-10-23