1B Model Rivals Evo 2 40B in Genomic Prediction Using 1980x Less Compute
stanfordnlp · x · 2026-08-20
MarinDNA reports that a 1B parameter standard Transformer, optimized via data curation and hyperparameter transfer, rivals the 40B Evo 2 model on variant effect prediction (VEP). It achieves this with 1,980x fewer training FLOPs and 2,330x faster inference. The study also notes that zero-shot VEP performance can regress with scale, even as linear-probe VEP improves.
Related event: MarinDNA's 1B Model Matches Evo 2 40B at 1/1980 the Compute(2 posts)→
More from Research
- GEN-1.5 robot model: one-shot learning of physical skills emerges — ChongZzZhang · 2026-08-20
- AI to accelerate biomedical research, compressing years of work into weeks — coherence · 2026-08-20
- LLMs predict forward reading, but fail to explain eye regressions — tallinzen · 2026-08-20
- CRUX Team Rebuttal: Scaffold Not the Bottleneck in AI Research Agents — random_walker · 2026-08-20
- GeneralistAI demos GEN-1.5 robot capable of one-shot learning — teortaxesTex · 2026-08-20
- FRONT 3.1 Paper: Cognitive architecture with "Digital Somatic Body" and homeostatic drives — Sufficient-War4616 · 2026-08-20