Fine-tuning

Sep 25, 2026

Antibody-specific fine-tuning improves framework preservation and hotspot targeting in RFdiffusion

Sep 07, 2026

Fine-tuning PLMs on rank is more effective than fine-tuning on property (regression)

Aug 25, 2026

Ab-Ag inverse folding methods benefit from pretraining

Aug 25, 2026

Fine-tuning almost always improves property prediction

Aug 25, 2026

Fine-tuning leads to small changes in parameter values in L2 space

training/fine-tuning

Aug 25, 2026

Low-rank adaptation causes models to learn less and forget less

training/fine-tuning

Aug 25, 2026

Masked LMs can be fine-tuned starting from autoregressive LMs, but not vice-versa

Aug 25, 2026

Pretraining performance does not capture effectiveness on downstream tasks

Aug 19, 2026

Fine-tuned protein language models can struggle to generalize to positions absent from fine-tuning data

Aug 19, 2026

Pretraining contributes nearly nothing to performance when fine-tuning protein language models in data-rich situations

Apr 21, 2026

Ab finetuning improves naturalness of inverse folding designs

Apr 21, 2026

Adding structural adaptors to language models leads to improvements in thermostability prediction compared to structure-based NNs alone

Apr 21, 2026

AlphaMissense

Apr 21, 2026

Base PLMs must usually be fine-tuned to generate functionally active sequences

Apr 21, 2026

Contrastive learning improves segregation of functional clusters

Apr 21, 2026

Fine-tuning AlphaFold for MHC prediction by adding Evoformer layers improves RMSD and pLDDT

Apr 21, 2026

Fine-tuning base models on test cases can improve the performance of variant effect and structure prediction

Apr 21, 2026

Language models can be infused with structure via low-rank adapter layers

Apr 21, 2026

MSA-based structure prediction models can be retrained as pathogenicity prediction models by upweighting BERT losses

Apr 21, 2026

PLM embeddings fine-tuned using contrastive learning outperform other representations in drug-target interaction prediction

Apr 21, 2026

Reinforcement learning outperforms fine-tuning in property-guided inverse folding

Apr 21, 2026

Sequence homology composition can affect performance of fine-tuned protein language models for variant effect prediction

Apr 21, 2026

Sequences with lower log-likelihoods are worse for zero-shot variant effect prediction using PLMs

Apr 21, 2026

Unfreezing PLM during structure training improves prediction quality

Apr 21, 2026

Contrastive fine-tuning PLMs on inverse folding embeddings of experimental structures but not computational models improves downstream tasks

Apr 21, 2026

Different versions of low-rank adaptation have equivalent performance after controlling for learning rate

training/fine-tuning

Apr 21, 2026

Grokking

Apr 21, 2026

Low-rank Adaptation

training/fine-tuning

Apr 21, 2026

Low-rank adaptation changes the magnitude, but not directionality, of matrix operations relative to fine-tuning

training/fine-tuning

Apr 21, 2026

Low-rank adaptation with even fewer parameters can operate on truncated SVD matrices, but only with reinforcement learning

training/fine-tuning

Apr 21, 2026

Overtrained language models are more difficult to fine-tune

Apr 21, 2026

Weight-decomposed low-rank adaptation

training/fine-tuning

Apr 20, 2026

Contrastive learning

Apr 20, 2026

Model merging

training/fine-tuning

Apr 17, 2026

Catastrophic forgetting

training/fine-tuning

Quartz 4

Explorer

Fine-tuning

Antibody-specific fine-tuning improves framework preservation and hotspot targeting in RFdiffusion

Fine-tuning PLMs on rank is more effective than fine-tuning on property (regression)

Ab-Ag inverse folding methods benefit from pretraining

Fine-tuning almost always improves property prediction

Fine-tuning leads to small changes in parameter values in L2 space

Low-rank adaptation causes models to learn less and forget less

Masked LMs can be fine-tuned starting from autoregressive LMs, but not vice-versa

Pretraining performance does not capture effectiveness on downstream tasks

Fine-tuned protein language models can struggle to generalize to positions absent from fine-tuning data

Pretraining contributes nearly nothing to performance when fine-tuning protein language models in data-rich situations

Ab finetuning improves naturalness of inverse folding designs

Adding structural adaptors to language models leads to improvements in thermostability prediction compared to structure-based NNs alone

AlphaMissense

Base PLMs must usually be fine-tuned to generate functionally active sequences

Contrastive learning improves segregation of functional clusters

Fine-tuning AlphaFold for MHC prediction by adding Evoformer layers improves RMSD and pLDDT

Fine-tuning base models on test cases can improve the performance of variant effect and structure prediction

Language models can be infused with structure via low-rank adapter layers

MSA-based structure prediction models can be retrained as pathogenicity prediction models by upweighting BERT losses

PLM embeddings fine-tuned using contrastive learning outperform other representations in drug-target interaction prediction

Reinforcement learning outperforms fine-tuning in property-guided inverse folding

Sequence homology composition can affect performance of fine-tuned protein language models for variant effect prediction

Sequences with lower log-likelihoods are worse for zero-shot variant effect prediction using PLMs

Unfreezing PLM during structure training improves prediction quality

Contrastive fine-tuning PLMs on inverse folding embeddings of experimental structures but not computational models improves downstream tasks

Different versions of low-rank adaptation have equivalent performance after controlling for learning rate

Grokking

Low-rank Adaptation

Low-rank adaptation changes the magnitude, but not directionality, of matrix operations relative to fine-tuning

Low-rank adaptation with even fewer parameters can operate on truncated SVD matrices, but only with reinforcement learning

Overtrained language models are more difficult to fine-tune

Weight-decomposed low-rank adaptation

Contrastive learning

Model merging

Catastrophic forgetting