# Triangle Multiplication Is All You Need For Biomolecular Structure Representations

arXiv: https://arxiv.org/abs/2510.18870 · HTML: https://mlsanity.com/paper/2510.18870/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 54 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Hyena Hierarchy: Towards Larger Convolutional Language Models](https://mlsanity.com/paper/2302.10866/) (2023)
- [Axial Attention in Multidimensional Transformers](https://mlsanity.com/paper/1912.12180/) (2019)
- [FNet: Mixing Tokens with Fourier Transforms](https://mlsanity.com/paper/2105.03824/) (2021)
- [Representational Strengths and Limitations of Transformers](https://mlsanity.com/paper/2306.02896/) (2023)
- [An Attention Free Transformer](https://mlsanity.com/paper/2105.14103/) (2021)
- [Proteina: Scaling Flow-based Protein Structure Generative Models](https://mlsanity.com/paper/2503.00710/) (2025)
- [Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2](https://mlsanity.com/paper/2405.15489/) (2024)
- [SimpleFold: Folding Proteins is Simpler than You Think](https://mlsanity.com/paper/2509.18480/) (2025)
- [Fast and Simplex: 2-Simplicial Attention in Triton](https://mlsanity.com/paper/2507.02754/) (2025)

## Built on by (most cited first, 4 of 4)

- [Pearl: A Foundation Model for Placing Every Atom in the Right Location](https://mlsanity.com/paper/2510.24670/) (2025)
- [Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards](https://mlsanity.com/paper/2603.26378/) (2026)
- [Accurate structural modeling of chemically diverse molecular interfaces with Vilya-2](https://mlsanity.com/paper/2607.25156/) (2026)
- [Packora: Systematic Design for Generative Molecular Crystal Structure Prediction](https://mlsanity.com/paper/2608.26962/) (2026)

## Abstract (arXiv)

AlphaFold has transformed protein structure prediction, but emerging applications such as virtual ligand screening, proteome-wide folding, and de novo binder design demand predictions at a massive scale, where runtime and memory costs become prohibitive. A major bottleneck lies in the Pairformer backbone of AlphaFold3-style models, which relies on computationally expensive triangular primitives-especially triangle attention-for pairwise reasoning. We introduce Pairmixer, a streamlined alternative that eliminates triangle attention while preserving higher-order geometric reasoning capabilities that are critical for structure prediction. Pairmixer substantially improves computational efficiency, matching state-of-the-art structure predictors across folding and docking benchmarks, delivering up to 4x faster inference on long sequences while reducing training cost by 34%. Its efficiency alleviates the computational burden of downstream applications such as modeling large protein complexes, high-throughput ligand and binder screening, and hallucination-based design. Within BoltzDesign, for example, Pairmixer delivers over 2x faster sampling and scales to sequences ~30% longer than the memory limits of Pairformer. Code is available at https://github.com/genesistherapeutics/pairmixer.