Heteroscedastic Diffusion for Multi-Agent Trajectory Modeling

ArXi:2605.10717v1 Announce Type: new Multi-agent trajectory modeling traditionally focuses on forecasting, often neglecting general tasks like trajectory completion, which is essential for real-world applications such as correcting tracking data. Existing methods also generally predict agents' states without offering any state-wise measure of heteroscedastic uncertainty. Moreover, popular multi-modal sampling methods lack error probability estimates for each generated scene under the same prior observations, which makes it difficult to rank the predictions at inference time. We