Highly accurate biomolecular structure prediction is a key component of developing biomolecular foundation models, and one of the most critical aspects of building foundation models is identifying the recipes for scaling the model. In this work, we present SeedFold, a folding model that successfully scales up the model capacity. Our contributions are threefold: first, we identify an effective width-scaling strategy for the Pairformer to increase representation capacity; second, we introduce a novel linear triangular attention that reduces computational complexity to enable efficient scaling; finally, we construct a large-scale distillation dataset to substantially enlarge the training set. Experiments on FoldBench show that SeedFold outperforms AlphaFold3 on most protein-related tasks.
@article{arxiv.2512.24354,
title = {SeedFold: Scaling Biomolecular Structure Prediction},
author = {Yi Zhou and Chan Lu and Yiming Ma and Wei Qu and Fei Ye and Kexin Zhang and Lan Wang and Minrui Gui and Quanquan Gu},
journal= {arXiv preprint arXiv:2512.24354},
year = {2026}
}