arXiv:2605.24071v1 Announce Type: new Abstract: Training a reinforcement learning agent on-policy means collecting fresh experience at every update, and that experience comes with a hidden problem. Each state in a rollout is the direct output of the previous one, causally…
arXiv:2602.04120v3 Announce Type: replace Abstract: Though Explainable AI (XAI) has made significant advancements, its inclusion in edge and IoT systems is typically ad-hoc and inefficient. Most current methods are “coupled” in such a way that they generate explanations simultaneously with…
arXiv:2605.24084v1 Announce Type: new Abstract: Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search space over the input features. In this work, we take a first step towards scaling exact…
arXiv:2603.17198v2 Announce Type: replace Abstract: A foundational principle in cognitive science holds that intelligent agents do not learn by storing experiences as isolated instances, but by forming abstract schemas that capture relational structure shared across situations. Even though this claim…
arXiv:2605.24106v1 Announce Type: new Abstract: Rapid and accurate flood extent mapping from Remote Sensing data, such as Synthetic Aperture Radar (SAR), is critical for operational disaster response, but standard Deep Learning models often produce physically impossible predictions due to a…
arXiv:2605.07733v2 Announce Type: replace Abstract: Accurate truck-to-shipment matching using GPS data is foundational for full truckload supply chain visibility, enabling real-time tracking and accurate estimated time of arrival (ETA) predictions. However, missing or corrupted vehicle identifiers prevent traditional matching approaches,…
arXiv:2605.24113v1 Announce Type: new Abstract: Classical archetypal analysis is appealing for its interpretability, but its linear geometry can limit performance on data with strongly non-linear structure; at the same time, existing neural extensions improve flexibility while often weakening the geometric…
arXiv:2605.20670v2 Announce Type: replace Abstract: Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally expensive and slow.…
arXiv:2605.24162v1 Announce Type: new Abstract: Biological systems are governed by structured molecular interactions, where pathways, regulatory circuits, and functional gene relationships shape cellular behavior and disease progression. Much of this knowledge is naturally represented as graphs. However, most biomedical AI…
arXiv:2506.19037v5 Announce Type: replace-cross Abstract: Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and effectively reduce to slow,…
