arXiv:2601.10905v1 Announce Type: new Abstract: Numerous offline and model-based reinforcement learning systems incorporate world models to emulate the inherent environments. A world model is particularly important in scenarios where direct interactions with the real environment is costly, dangerous, or impractical.…
arXiv:2601.09926v2 Announce Type: replace Abstract: Most language-based assistants follow a reactive ask-and-respond paradigm, requiring users to explicitly state their needs. As a result, relevant but unexpressed needs often go unmet. Existing proactive agents attempt to address this gap either by…
arXiv:2601.10911v1 Announce Type: new Abstract: Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy…
arXiv:2505.21388v3 Announce Type: replace-cross Abstract: Social recommender systems facilitate social connections by identifying potential friends for users. Each user maintains a local social network centered around themselves, resulting in a naturally distributed social structure. Recent research on distributed modeling for…
arXiv:2601.10914v1 Announce Type: new Abstract: Learning physically meaningful spatiotemporal representations from high-resolution multivariate Earth observation data is challenging due to strong local dynamics, long-range teleconnections, multi-scale interactions, and nonstationarity. While ConvLSTM2D is a commonly used baseline, its dense convolutional gating…
arXiv:2601.05810v2 Announce Type: replace-cross Abstract: The ability to automatically generate large-scale, interactive, and physically realistic 3D environments is crucial for advancing robotic learning and embodied intelligence. However, existing generative approaches often fail to capture the functional complexity of real-world interiors,…
arXiv:2601.10940v1 Announce Type: new Abstract: Split learning (SL) enables collaborative training of large language models (LLMs) between resource-constrained edge devices and compute-rich servers by partitioning model computation across the network boundary. However, existing SL systems predominantly rely on first-order (FO)…
arXiv:2504.12569v4 Announce Type: replace Abstract: Open-set semi-supervised learning (OSSL) leverages unlabeled data containing both in-distribution (ID) and unknown out-of-distribution (OOD) samples, aiming simultaneously to improve closed-set accuracy and detect novel OOD instances. Existing methods either discard valuable information from uncertain…
arXiv:2508.01687v4 Announce Type: replace Abstract: Explaining machine learning (ML) models for time series (TS) classification remains challenging due to the difficulty of interpreting raw time series and the high dimensionality of the input space. We introduce PHAR–Post-hoc Attribution Rules–a unified…
arXiv:2601.11435v1 Announce Type: cross Abstract: This paper studies decentralized stochastic nonconvex optimization problem over row-stochastic networks. We consider the heavy-tailed gradient noise which is empirically observed in many popular real-world applications. Specifically, we propose a decentralized normalized stochastic gradient descent…
