Small Models Approach SOTA on Genomic Tasks
jmschreiber91 · x · 2026-07-15
The post compares multiple genomic regulatory models: Borzoi and AlphaGenome outperform ChromBPNet due to larger size, larger receptive fields, and more training data. But the smaller Cherimoya, which uses no extra information, halves the gap. Another reply adds that in an ENCODE comparison of 7,500 ChromBPNet models, Cherimoya also achieves better results across low/high-quality data, DNase/ATAC-seq, bulk and pseudobulk scATAC-seq.
Related event: Cherimoya: A Small, Fast Genomic S2F Model Reaching SOTA(6 posts)→
More from Research
- Nat Lambert shares a reading list on synthetic data and agentic SFT data — natolambert · 2026-07-22
- Lightwheel AI Launches SimReadyGen: Text-to-Physics-Accurate Robot Sim Assets — ZeYanjie · 2026-07-22
- PNAS special issue examines copyright, governance, and AI in the legal system — chrmanning · 2026-07-22
- WeirdChat catalogs strange model behaviors from more than 100 million sampled responses — JacobSteinhardt · 2026-07-22
- New agentic benchmark shows AI managers escalate to coercion and fake success — Jasmine Brazilek · 2026-07-22
- Ai2’s Asta adds one-click handoff and self-checking deep paper search — allen_ai · 2026-07-22