AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models

Weimin Wu, Xuefeng Song, Yibo Wen, Qinjie Lin, Zhihan Zhou, Jerry Yao-Chieh Hu, Zhong Wang, Han Liu

ICML 2026 · Large language models › Instruction and fine-tuning · approach: Fine-tuning for reasoning data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adapter tuning instead of full fine-tuning (ablation)DNABERT-2 · COVID variant (GUE)peak memory and throughput: 7.30 GB -> 2.09 GB memory; 40.70 -> 124.30 KTok/sImproved
use LoRA instead of full fine-tuning (ablation)DNABERT-2 · COVID variant (GUE)trainable params and throughput: 117.08M -> 1.49M params; 40.70 -> 44.07 KTok/sImproved
scale model from Nucleotide Transformer-500M to 2.5B under LoRA (ablation)LoRA · Efficiency vs full tuningmemory savings and throughput ratio: memory savings 16% -> 32%; throughput 1.20 -> 1.39 timesImproved
scale GenomeOcean from 100M to 500M under LoRA (ablation)LoRA · Efficiency vs full tuningmemory savings and throughput ratio: memory savings 5% -> 21%; throughput 1.01 -> 1.27 timesImproved
use LoRA instead of full fine-tuning (ablation)GenomeOcean-100M · Genomic BenchmarksMCC: 68.26 -> 66.28No clear effect
use LoRA instead of full fine-tuning (ablation)DNABERT-2 · GUEGUE score: 65.25 -> 48.39Hurt
use adapter instead of LoRA (ablation)Caduceus-131k · GUEGUE score: 34.70 -> 38.61Improved
use adapter instead of LoRA (ablation)GenomeOcean-100M · GUEGUE score: 59.35 -> 46.65Hurt
use adapter tuning instead of full fine-tuning (ablation)DNABERT-2, HyenaDNA, Nucleotide Transformer · GUEmemory, throughput, GUE scoreMixed
use foundation model (GenomeOcean-100M full) over classical SVM baselineGUE · GUEGUE score: 57.01 -> 65.52Improved
use larger EVO-1-131k (7B) with LoRA rather than smaller modelsLoRA · GUEGUE score: 44.97 vs 59.35 (GenomeOcean-100M)Hurt
use GenomeOcean-4B instead of EVO 2-7BLoRA on GUE epigenetic marks · GUE epigenetic marks (10 tasks)average MCC: 61.77 -> 60.43No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy