GaussianCollab: Communication-Efficient Latent Query Fusion via Tokenized Semantic Gaussians for Collaborative Occupancy Prediction

Collaborative perception requires agents to exchange spatially grounded semantic evidence under constrained communication budgets. Existing approaches predominantly communicate dense bird's-eye-view or voxel features, which either collapse vertical geometry or incur the cost of dense 3D grids. We propose $\text{GaussianCollab}$, a collaborative perception framework that uses tokenized semantic Gaussians as the inter-agent communication medium. GaussianCollab communicates and fuses latent semantic queries anchored to explicit Gaussian geometry. This shifts Gaussian-based collaboration from attribute-only exchange to latent-query fusion, preserving explicit 3D structure for rigid transformation and geometric matching while retaining richer learned semantics. GaussianCollab performs geometry-guided matching and latent-query fusion over matched tokens, and decodes and stacks unmatched collaborator evidence. To control the resulting payload, we introduce $\text{Semantic InConsistency (SIC)-guided selective packing}$ together with $\text{Partially Embedded Query Compression (PEQC)}$. Experiments on Semantic-OPV2V and Co3SOP demonstrate state-of-the-art performance on collaborative semantic occupancy prediction task. Under matched Gaussian capacity, the lowest-communication-volume operating points improve mIoU over the reproduced VOGS-L baseline by $\text{2.95 and 3.47 points}$ while reducing communication volume by $\text{7.5}$% and $\text{6.9}$% on Semantic-OPV2V and Co3SOP, respectively. GaussianCollab also maintains favorable accuracy under the tested token-erasure and localization-perturbation settings. These results establish geometry-anchored latent Gaussian queries as an effective and communication-efficient fusion medium for vision-based collaborative occupancy prediction. Code will be made publicly available.