Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design

Antibodies play a key role in immune recognition by binding specific antigens. Although recent protein language models have enabled progress in single-chain protein modeling and generation, they often fall short in antigen-specific antibody design, where effective modeling requires explicit pairing between antibody and antigen, particularly at the epitope level. To address these limitations, we introduce AAMFM, an $\textbf{A}$ntigen-specific $\textbf{A}$ntibody $\textbf{M}$ultimodal $\textbf{F}$oundation $\textbf{M}$odel that learns unified representations of antibody sequences and structures conditioned on antigen context. AAMFM incorporates rich antigen information including geometric interfaces and epitope annotations via a cross-modal adapter, enabling joint modeling of antibody-antigen interactions in a shared latent space. To further guide the model toward functional relevance, we fine-tune AAMFM using Calibrated Direct Preference Optimization (Cal-DPO), leveraging preference signals extracted from a strong structural prior (AlphaFold3) to align learning with binding-specific objectives. Extensive experiments demonstrate that AAMFM achieves state-of-the-art performance in functional antibody design, revealing its potential for antigen-specific antibody engineering. Our code is available at https://anonymous.4open.science/r/AAMFM.