AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

MMCP-GEN: A Modality-Extensible Diffusion Language Model for Conditional Protein Sequence Generation

Zeyu An, Wanyu Lin, Feng Tan, Shujun Wang

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Diffusion for protein and antibody design

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
provide all conditions instead of only GO (ablation)MMCP-GEN · GO-conditioned generationMRR: 0.641 -> 0.873Improved
provide all conditions instead of only IPR (ablation)MMCP-GEN · IPR-conditioned generationmacro F1: 0.861 -> 0.977Improved
provide all conditions instead of only EC (ablation)MMCP-GEN · EC-conditioned generationMRR: 0.789 -> 0.927Improved
add structure input with supervised fine-tuning of adapters and fusion (ablation)MMCP-GEN · Inverse foldingAAR (%): 73.88 -> 77.49Improved
add all modalities beyond structure (ablation)MMCP-GEN (SFT) · Inverse foldingAAR (%): 77.49 -> 78.17Improved
add joint generation-and-scoring (GS) loss (ablation)MMCP-GEN (SFT, all conditions) · Inverse foldingAAR (%): 78.17 -> 78.66Improved
add GS loss on scTM and pLDDT (ablation)MMCP-GEN (SFT, all conditions) · Inverse foldingscTM: 0.906 -> 0.912Improved
zero-shot use without fine-tuning adapters (ablation)MMCP-GEN · Inverse foldingAAR (%): 73.88 vs CFP-GEN 77.01Mixed
MMCP-GEN versus CFP-GEN on GO-term MRR with only GO conditionMMCP-GEN (w/ GO) · GO-conditioned generationMRR: 0.824 -> 0.641Hurt
MMCP-GEN versus CFP-GEN on IPR micro F1 with only IPR conditionMMCP-GEN (w/ IPR) · IPR-conditioned generationmicro F1: 0.961 -> 0.913Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy