A single autoregressive foundation model unifies protein, molecule, and crystal structures into a shared token vocabulary and generates inspectable reasoning traces, achieving SOTA on 67 of 86 scientific tasks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
scpFormer is a panel-agnostic transformer model that creates unified cell representations from variable single-cell proteomic panels via continuous embeddings and ESM integration, supporting batch integration, clustering, in silico expansion, and transfer to bulk tasks.
citing papers explorer
-
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
A single autoregressive foundation model unifies protein, molecule, and crystal structures into a shared token vocabulary and generates inspectable reasoning traces, achieving SOTA on 67 of 86 scientific tasks.
-
scpFormer: A Foundation Model for Unified Representation and Integration of the Single-Cell Proteomics
scpFormer is a panel-agnostic transformer model that creates unified cell representations from variable single-cell proteomic panels via continuous embeddings and ESM integration, supporting batch integration, clustering, in silico expansion, and transfer to bulk tasks.