AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Low rank adaptation of chemical foundation models generate effective odorant representations

Grant D. McConachie, Emily Duniec, Florence V. Guerina, Meg Younger, Brian DePasquale

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis

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
add LoRA fine-tuning of the chemical model (LORAX vs frozen ProSmith)ProSmith with ChemBERTa-77M-MTR · Carey (random 5-fold)R2: 0.703 -> 0.712No clear effect
add LoRA fine-tuning of the chemical modelProSmith · Carey (unseen odorants)R2: -0.402 -> 0.045Improved
add LoRA fine-tuning of the chemical modelProSmith · Carey (unseen receptors)R2: 0.088 -> 0.060No clear effect
add LoRA fine-tuning of the chemical modelProSmith · M2OR (full, weighted)MCC: 0.641 -> 0.651Improved
add LoRA fine-tuning of the chemical modelProSmith · M2OR (full, weighted)AUROC: 90.47 -> 83.24Hurt
add LoRA fine-tuning of the protein model on top of chemical LoRA (ablation)LORAX (C) · M2OR (full, weighted)MCC: 0.651 -> 0.650Hurt
add receptor (protein) representation to the odorant-only modelridge model with ChemBERTa-77M-MTR · Carey (feature-based, 5-fold)R2: 0.218 -> 0.290Improved
add transformer and XGBoost ensemble (ProSmith) over ridge MPChemBERTa-77M-MTR features · Carey (feature-based, 5-fold)R2: 0.290 -> 0.704Improved
replace random odorant vectors with a pretrained chemical foundation modelProSmith · Carey (feature-based, 5-fold)R2: 0.586 -> 0.704Improved
replace physicochemical descriptors (RDKit) with ChemBERTa foundation featuresProSmith · Carey (feature-based, 5-fold)R2: 0.720 -> 0.704No clear effect
replace random vectors with ChemBERTa features in the ridge MP modelMP · Carey (feature-based, 5-fold)R2: 0.294 -> 0.290No 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