Carbon-A DNA Model Proposes 500M+ Gene Candidates Across 22,000 Species
lvwerra · x · 2026-10-12
lvwerra (Hugging Face) announced Carbon-A, a DNA foundation model that has proposed over 500 million gene candidate annotations across 22,000 species. A comparison chart shows existing database annotations (blue) versus Carbon-A's new annotations (green), which substantially expand coverage — a notable AI-for-Science application at scale in genome annotation.
Related event: Hugging Face Open-Sources Carbon-A DNA Model Proposing 500M Gene Candidates(2 posts)→
More from Research
- Microsoft's Fork-and-Flush helps agents escape "idea basins," improving results 66% — DimitrisPapail · 2026-10-12
- Award-winning Nikon microscopy video disqualified over AI use, sparking debate — AnnaCiaunica · 2026-10-12
- Sim-to-real lessons: RL-trained robots vastly outperform behavior cloning, UW work shows — chris_j_paxton · 2026-10-12
- New Study Quantifies What Diffusion Models Generate First: Only RAE Space Shows Abstract-to-Concrete Order — sedielem · 2026-10-12
- Pedro Domingos on harness learning paper: the model swallows the harness — DanielKhashabi · 2026-10-12
- Data-space iteration: a new few-step generation paradigm removes flow discretization, arXiv paper shows — bdsqlsz · 2026-10-12