Diffusers merges RFD4-Proteína, a protein design flow-matching model from Baker Lab and NVIDIA
RisingSayak · x · 2026-10-21
The first protein sequence design model, RFD4-Proteína from Baker Lab and NVIDIA, has been merged into Hugging Face Diffusers, pushing open BioML forward.
- A flow-matching model that generates protein sequences and all-atom structures together, conditioned on binding targets, enzyme motifs, ligands, hotspots or secondary structure
- Uses a paired transformer and autoencoder with two schedulers (backbone + local latents)
- Demo tasks include PD-L1 binder design, antibody CDR H3 redesign, enzyme scaffold generation, small-molecule pocket generation, unconditional generation and inverse folding
- Domain-specific CIF preprocessing lives in a separate rfd4-proteina-prep package
Related event: NVIDIA and Baker Lab Open-Source RFD4-Proteina Protein Design Model(35 posts)→
More from Research
- Paper asks 'How long is the coast of a neuron?' — resolution shapes neural computation — neurovium · 2026-10-21
- Yoav Goldberg on ICLR reviewing: question-title papers must actually answer the question — yoavgo · 2026-10-21
- Surge AI's Chartography and GDP.pdf top Papers with Code trending benchmarks — NielsRogge · 2026-10-21
- OpenAI scales thousands of AI agents to find new leads in biological data — truecakesnake · 2026-10-21
- EAU: Co-evolving user simulator, environment, and RL setup for training LLM agents — UAlberta · 2026-10-21
- Meta's Self-Credit: Dense Rewards from Sparse RLVR via Intra-group Rescaling — meta · 2026-10-21