MarinDNA 1B Model Matches Evo 2 40B Performance with 1980x Less Compute
anshulkundaje · x · 2026-08-19
MarinDNA shows a 1B parameter standard Transformer rivals Evo 2 40B on variant effect prediction (VEP) using curated data and scaling laws. It uses 1,980x fewer training FLOPs and scores variants 2,330x faster. The study notes zero-shot VEP may regress with scale while linear-probe VEP improves.
More from Research
- ACL 2026 Paper: LLMs Stick to Old Knowledge Despite New Information — mdredze · 2026-08-19
- NeurIPS 2026 Workshop Focus: AI Writing, AI Review, and Academic Governance — ManlingLi_ · 2026-08-19
- OpenAI Reply: RLHF and World Models Accelerate Design Iteration — TinfoilTricorn · 2026-08-19
- A self-devised 'freeze a service first' method let Codex pass a Terminal-Bench task with zero public solves — Present-Quantity-813 · 2026-08-19
- Stanford, Yale Win First Live AI Agent Competition at Data + AI Summit — CShorten30 · 2026-08-19
- Tuesday index combines 8 Surge benchmarks, more coming — echen · 2026-08-19