Evo 2 shows emergent generative in-context learning for few-shot regulatory sequence design
anshulkundaje · x · 2026-10-30
Brian Hie's team reports a surprising, unanticipated finding: prompting the genomic foundation model Evo 2 with a handful of functionally related sequences steers it to generate new sequences with similar function—a form of generative in-context learning (ICL)—enabling few-shot design of mammalian regulatory elements. Stanford's Anshul Kundaje praises the ICL capability but notes simpler approaches already work well for promoter/enhancer design of reporter constructs, citing deep learning-guided cell type-specific AAV promoter design (bioRxiv preprint).
More from Research
- WSDM 2027 to host LongSeek, first workshop on long-horizon information seeking — mrdrozdov · 2026-10-30
- Lean 4 formalization of an asymmetric metric-tensor physics paper hits GitHub — SubtleGradient · 2026-10-30
- Is sycophantic AI inflating research publications? Two mechanisms worth questioning — KLdivergence · 2026-10-30
- Tahoe AI's Tara plug-in brings 100M-cell drug datasets to Claude Code, Codex and Cursor — anshulkundaje · 2026-10-30
- Joy dataset: 100,000 hours of unscripted two-person calls to teach voice models real timing — Scobleizer · 2026-10-30
- Exo: Berkeley's self-improving agent architecture cuts costs 31-62% vs Codex — arena · 2026-10-30