arXiv:2510.15174v1 Announce Type: new Abstract: Feature learning (FL), where neural networks adapt their internal representations during training, remains poorly understood. Using methods from statistical physics, we derive a tractable, self-consistent mean-field (MF) theory for the Bayesian posterior of two-layer non-linear…
arXiv:2509.16606v2 Announce Type: replace-cross Abstract: In networked multi-agent reinforcement learning (Networked-MARL), decentralized agents must act under local observability and constrained communication over fixed physical graphs. Existing methods often assume static neighborhoods, limiting adaptability to dynamic or heterogeneous environments. While centralized…
arXiv:2510.15177v1 Announce Type: new Abstract: Geodesic problems involve computing trajectories between prescribed initial and final states to minimize a user-defined measure of distance, cost, or energy. They arise throughout physics and engineering — for instance, in determining optimal paths through…
arXiv:2503.21473v2 Announce Type: replace-cross Abstract: Gaussian Processes (GPs) provide a flexible and statistically principled foundation for modelling spatiotemporal phenomena, but their $O(N^3)$ scaling makes them intractable for large datasets. Approximate methods such as variational inference (VI), inducing points (sparse GPs),…
arXiv:2510.12328v3 Announce Type: replace Abstract: Accurate rainfall forecasting, particularly for extreme events, remains a significant challenge in climatology and the Earth system. This paper presents novel physics-informed Graph Neural Networks (GNNs) combined with extreme-value analysis techniques to improve gauge-station rainfall…
arXiv:2504.00010v3 Announce Type: replace Abstract: Text-to-image (T2I) generation has made remarkable progress, yet existing systems still lack intuitive control over spatial composition, object consistency, and multi-step editing. We present $textbf{LayerCraft}$, a modular framework that uses large language models (LLMs) as…
arXiv:2507.02998v2 Announce Type: replace Abstract: Rare diseases affect an estimated 300-400 million people worldwide, yet individual conditions remain underdiagnosed and poorly characterized due to their low prevalence and limited clinician familiarity. Computational phenotyping offers a scalable approach to improving rare…
arXiv:2510.15669v1 Announce Type: cross Abstract: Variational autoencoders (VAEs) are a leading approach to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought in its continuous latent space. Here we explore a…
arXiv:2411.08590v4 Announce Type: replace Abstract: Associative memory models, such as Hopfield networks and their modern variants, have garnered renewed interest due to advancements in memory capacity and connections with self-attention in transformers. In this work, we introduce a unified framework-Hopfield-Fenchel-Young…
arXiv:2510.15056v1 Announce Type: new Abstract: Reinforcement learning usually assumes a given or sometimes even fixed environment in which an agent seeks an optimal policy to maximize its long-term discounted reward. In contrast, we consider agents that are not limited to…
