All Competitors

Rigidity-aware geometric pretraining framework that front-loads SE(3) geometry learning to improve protein backbone generation, motif scaffolding, and conformational ensemble modeling.

A hybrid-diffusion protein language model that adds a continuous-token diffusion head to a discrete pLM for joint sequence-structure modeling.

Atom-level generative diffusion model for de novo enzyme design. Scaffolds arbitrary functional group geometries, solving all 41 benchmark active sites vs. 16/41 for prior methods.

Retrieval-augmented encoder-decoder that conditions pretrained ESM-2 on homologous sequences via cross-attention for improved masked prediction and conditional protein sequence generation.

Sequence-first protein generation framework using discrete diffusion over evolutionary alignments, enabling controllable de novo design without structure.

Diffusion model for de novo protein design that generates novel backbone structures conditioned on binding targets, symmetry constraints, and functional motifs.