Karlsruhe Institute of Technology

RNA language model pretrained on 30M non-coding RNA sequences that predicts secondary structure, contacts, and splice sites without alignments.

De novo protein backbone design conditioned on a target per-residue flexibility profile, with SE(3)-equivariant flow matching and MD validation.

EEG foundation model with cross-scale spatiotemporal tokenization and sparse structured attention, evaluated on 11 decoding tasks across 16 datasets.

Protein conformational ensemble generator conditioned on backbone geometry alone, sampling MD-like dynamics without MSAs or a folding model.

De novo protein backbone design with geometric-algebra attention, sampling designable structures whose secondary structure matches natural proteins.