Is the war entering a new phase? Three black naval drones resembling oversized plastic toys struck a freighter sluggishly navigating the Black Sea off the coast of Bulgaria on October 28. Aerial drones joined the attack, and explosions rocked the Liberian-flagged Contship Jet Monrovia, loaded with more than 400 terracotta-coloured containers. The vessel, travelling from the Israeli port of Haifa to Romania, listed and sank, but all 18 crew members were rescued, Bulgarian authorities said. The drones were Russian, Kyiv claimed, adding that the attack was designed to make the Black Sea unsafe for civilian ships, paralyse Ukraine's exports of grain and further hobble its war-ravaged economy.

Neural processes (NPs) are a class of models that learn stochastic processes directly from data and can be used for inference, sampling and conditional sampling. We introduce a new NP model based on flow matching, a generative modeling paradigm that has demonstrated strong performance on various data modalities. Following the NP training framework, the model provides amortized predictions of conditional distributions over any arbitrary points in the data. Compared to previous NP models, our model is simple to implement and can be used to sample from conditional distributions using an ODE solver, without requiring auxiliary conditioning methods. In addition, the model provides a controllable tradeoff between accuracy and running time via the number of steps in the ODE solver. We show that our model outperforms previous state-of-the-art neural process methods on various benchmarks including synthetic 1DGaussian processes data, 2D images, and real-world weather data.

Furthermore, weprovethat, under mild assumptions, a slight variation of WQL enjoys desirable theoretical properties in the tabular setting.

When n is independent ofδ our approach yields an algorithm whose sample complexityconvergesto 2n2 log 1δ asngrows.

Combined, these features provide both theoretical and practical simplicity.

That is, we propose to formulate continual learning as a sequence modeling problem, allowing advanced sequence models to be utilized for continual learning.