Institute of Automation, Chinese Academy of Sciences

Single-cell foundation model that predicts latent representations of graph-connected gene blocks instead of reconstructing individual gene counts.

Latent diffusion model that backmaps coarse-grained protein structures to all-atom detail, with bond geometry learned into the latent space.

Compact 1.1M-parameter DNA language model distilled from Nucleotide Transformer v2, outperforming its 500M teacher on 11 of 18 benchmark tasks.

Single-cell multi-omics foundation model with a Mamba backbone, pretrained on 2.7 million paired scRNA-seq and scATAC-seq profiles.

Phosphorylation site prediction from protein sequence. A LoRA-adapted ESM-2 encoder feeds a conformer, reaching 79.5% AUC at serine sites.

Reprograms a frozen single-target diffusion model for dual-target drug design by composing SE(3)-equivariant messages across two aligned pockets.

EEG foundation model that makes each electrode its own token stream, pretrained by causal next-signal prediction over 138 electrode positions.

Self-supervised 3D molecular pretraining that corrupts and rebuilds tetrahedral local structures, then transfers to toxicity and affinity prediction.