SITE-AIT: SITE-BOUND LATENT TOKENIZATION AND JOINT OPTICAL INFERENCE FOR DENSE QUBIT READOUT

Dense fluorescence images of large qubit registers violate the independence assumption behind per-site thresholding: neighboring point-spread functions overlap, emitter coordinates drift, and local observations depend on unknown neighboring states. Moreover, pixel-based representations and generic object queries fail to maintain a persistent one-to-one correspondence with dense physical sites, hindering high-fidelity readout. We propose Site-AIT, a representation that binds one latent token to each dense site and resolves coupled decisions via register-wide self-attention. Tokens are constructed via offset-corrected, point-spread-function-weighted Top-16 selection from a $13\times 13$ candidate field, reducing local features from 2,704 to 256 dimensions. When labeled data are scarce, a detector-aware noise prior initializes the image backbone, while a differentiable optical reconstruction objective guides training without adding inference overhead. Evaluated on a 2,000-frame benchmark from a 300-site trapped-ion register, Site-AIT achieves per-ion accuracy of $0.9978\pm 0.0004$, with $0.0152\pm 0.0004$ pixel localization error and $0.31\pm 0.01$ ms FPGA latency. Extensive ablations and physical perturbation experiments confirm that aligning the inference unit with the physical measurement unit provides an effective design principle for calibrated, densely overlapping emitter arrays.