Running Boltz-2 100 Million Times: Toward a Bottom-Up Path to Virtual Cells
HannesStaerk · x · 2026-09-04
dombeaini shares results from running the co-folding model Boltz-2 100 million times to simulate interactions among proteins, RNA, DNA and small molecules at scale. He asks whether this data could open a bottom-up path to Virtual Cells, and how to understand the limits of co-folding models and when their predictions actually translate to biology. He will present the work at the Starkly Speaking reading group.
More from Research
- Self-explanation training generalizes beyond narrow hint formats to held-out evals — a_karvonen · 2026-09-05
- Two training targets from behavior investigations: counterfactual predictions and open-ended self-explanations — a_karvonen · 2026-09-05
- Anthropic Fellows train models to explain their own wild behaviors with generalization to held-out evals — a_karvonen · 2026-09-05
- Video DeltaNet open-sources hybrid-attention VDN-H3, 14.4s video in 11.2s on 8 B200s — BigWideBaker · 2026-09-05
- Deep Learning Weekly #471: Claude Fable 5.1 launch, production-parity LLM evals, alignment paper — dl_weekly · 2026-09-05
- CoRL 2026 paper decisions out on OpenReview; conference heads to Austin this November — yukez · 2026-09-05