We introduce LatentTrack (LT), a sequential neural architecture for online probabilistic prediction under nonstationary dynamics. LT performs causal Bayesian filtering in a low-dimensional latent space and uses a lightweight hypernetwork to generate predictive model parameters at each time step, enabling constant-time online adaptation without per-step gradient updates. At each time step, a learned latent model predicts the next latent distribution, which is updated via amortized inference using new observations, yielding a predict--generate--update filtering framework in function space. The formulation supports both structured (Markovian) and unstructured latent dynamics within a unified objective, while Monte Carlo inference over latent trajectories produces calibrated predictive mixtures with fixed per-step cost. Evaluated on long-horizon online regression using the Jena Climate benchmark, LT consistently achieves lower negative log-likelihood and mean squared error than stateful sequential and static uncertainty-aware baselines, with competitive calibration, demonstrating that latent-conditioned function evolution is an effective alternative to traditional latent-state modeling under distribution shift.

翻译：本文提出LatentTrack（LT），一种用于非平稳动态下在线概率预测的序列化神经架构。LT在低维潜在空间中执行因果贝叶斯滤波，并利用轻量级超网络在每个时间步生成预测模型参数，从而实现无需逐步梯度更新的恒定时间在线适应。在每个时间步，学习得到的潜在模型预测下一时刻的潜在分布，该分布通过基于新观测值的摊销推理进行更新，形成函数空间中的"预测-生成-更新"滤波框架。该公式在统一目标函数下同时支持结构化（马尔可夫）与非结构化潜在动态，而对潜在轨迹的蒙特卡洛推理能以固定单步成本产生校准的预测混合分布。在耶拿气候基准数据集上进行长时域在线回归评估时，LT始终比有状态序列化基线及静态不确定性感知基线获得更低的负对数似然与均方误差，且具有竞争力的校准性能，证明在分布偏移条件下，潜在条件函数演化是传统潜在状态建模的有效替代方案。