Category
arXiv:2602.18801v1 Announce Type: new Abstract: Neural operators provide fast PDE surrogates and often generalize across parameters and resolutions. However, in the short train long test …
arXiv:2602.18825v1 Announce Type: new Abstract: Bayesian neural networks (BNNs) are a useful tool for uncertainty quantification, but require substantially more computational resources than conventional neural …
arXiv:2602.18837v1 Announce Type: new Abstract: Despite their theoretical advantages, spectral methods based on the graph Fourier transform (GFT) are seldom used in graph neural networks …
arXiv:2602.18849v1 Announce Type: new Abstract: Despite powering modern AI, transformers remain mysteriously brittle to train. We develop a stability theory that explains why pre-LayerNorm works, …
arXiv:2602.18851v1 Announce Type: new Abstract: Attention scores in transformers are bilinear forms $S_{ij} = x_i^\top M x_j / \sqrt{d_h}$ whose maximum magnitude governs overflow risk …
arXiv:2602.18856v1 Announce Type: new Abstract: Reinforcement learning (RL) has enabled major advances in fields such as robotics and natural language processing. A key challenge in …
arXiv:2602.18857v1 Announce Type: new Abstract: Optimally trading-off exploration and exploitation is the holy grail of reinforcement learning as it promises maximal data-efficiency for solving any …
arXiv:2602.18858v1 Announce Type: new Abstract: Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage …
arXiv:2602.18866v1 Announce Type: new Abstract: Despite the widespread use of boosting in structured prediction, a general theoretical understanding of aggregation beyond scalar losses remains incomplete. …
arXiv:2602.18897v1 Announce Type: new Abstract: Knowledge Graph(KG) has gained traction as a machine-readable organization of real-world knowledge for analytics using artificial intelligence systems. Graph Neural …
arXiv:2602.18904v1 Announce Type: new Abstract: Vector-quantized autoencoders deliver high-fidelity latents but suffer inherent flaws: the quantizer is non-differentiable, requires straight-through hacks, and is prone to …
arXiv:2602.17784v1 Announce Type: cross Abstract: Mineral prospectivity mapping requires synthesizing heterogeneous geological knowledge, including textual deposit models and geospatial datasets, to identify regions likely to …
