How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks
Theoretical analysis of generalization scaling laws in quadratic neural networks as functions of model width and sample count.
Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Theoretical analysis of generalization scaling laws in quadratic neural networks as functions of model width and sample count.
Physics-informed neural networks with transfer learning applied to lithium-ion battery state estimation.
Physics-informed neural networks with wavelet encoding for inverse conductivity problems; applied math, not AI systems frontier.
ADC-GNN: diffusion-guided graph neural network for fraud detection with sparse, imbalanced labels on transaction graphs.
Higher-order Fourier Neural Operator: mode mixing for nonlinear PDE surrogate models beyond linear constant-coefficient regimes.
Physics-constrained neural networks projecting onto Stiefel manifold for energy-conserving surrogate modeling of optical structures.
OperatorSHAP efficiently computes Shapley values for neural operators on irregular grids for safety-critical physical applications.
MLVC: cross-platform neural video codec with deterministic hardware-robust entropy coding for practical deployment.
Analysis of geopolitical security implications of US Fable/Mythos suspension limiting domestic cybersecurity patching capability.
Error-Conditioned Neural Solvers use learned correction instead of gradient descent to improve PDE solutions and extrapolation.
Modular open-source NLP pipeline extracts political-elite networks from multilingual text using joint entity-relation extraction.
PEEU method trains open-source MLLMs for GUI task planning via autonomous environment exploration and hindsight experience replay.
Taxonomy of indirect linguistic encoding (algospeak, euphemisms) mechanisms enables LLM detection of camouflaged social media expressions.
Survey connects GNN expressiveness to Weisfeiler-Leman hierarchy, clarifying when graph structure justifies computational overhead.
Feature-induced information flow method explains Event-based Temporal GNNs by tracing contributions from embeddings and event-induced variables.
VLM-PBRS uses vision-language model guidance to learn potential-shaping heuristics for sparse-reward RL, avoiding naive reward hacking.
fTNN tensor neural network for fractional PDEs using geometry-adapted integration split on bounded domains.
As ASML CEO Christophe Fouquet told TechCrunch in May, what China can currently buy are older-generation deep ultraviolet tools — gear first shipped about a decade ago — the same machines the MATCH Act would now put off limits.
The laser welding full-penetration is of critical importance, as it constitutes one of the fundamental factors in achieving defect-free welded joints. Accurate prediction of the penetration state is therefore essential for ensuring weld quality. To this end, this paper…
Variational Monte Carlo (VMC) is a central algorithm in electronic structure theory and has gained renewed importance through modern neural-network ansätze such as FermiNet. At its core, VMC seeks ground states by minimizing the Rayleigh quotient by stochastic optimization. In…
We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks. The framework decomposes the compression search across two levels of abstraction: low-level agents (LLAs) operate…
We study whether a scaling-law-style inference-compute frontier appears in limit order book prediction. Using FI-2010 and a suite of models ranging from small decision trees to neural LOB architectures, we find that the realized empirical frontier of predictive loss versus…
Modern neural network training relies on optimizers such as Adam and Muon which act on each weight matrix as a single object. Yet every weight matrix carries two distinct quantities -- a \emph{magnitude} and a \emph{direction} -- and all optimizers stepping in the matrix as a…
Variational Autoencoders (VAEs) belong to a family of autoencoders with probabilistic properties, making them well suited for generating data by producing a smooth and continuous latent space. Despite being introduced over a decade ago, the method continues to be widely adopted…
Fourier Neural Operators (FNO) learn solution operators of partial differential equations by parameterizing global convolutions in the complex Fourier domain. For real-valued PDE solutions, the complex FFT carries representational redundancy through conjugate symmetry. We…
Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information storage, retrieval, update, consolidation, and dynamic lifecycle governance throughout agent execution…
Even when Dirac-Frenkel dynamics determine a well-defined evolution in function space, the corresponding parameter dynamics can be non-unique or ill-conditioned for redundant nonlinear parametrizations such as neural networks or mixture models. We propose to add inertia to the…
The loss of plasticity - the ability of a network to learn new information after having already learned older information - is a fundamental challenge in creating artificial neural networks capable of continual learning. Although this phenomenon has been known for decades, it…
In many decision-making scenarios, acquiring information incurs different costs. We consider the problem of constructing a deterministic evaluation strategy that minimizes the expected cost of evaluating a propositional formula under variable costs and a probability…
Phase-field models play a central role in the continuum description of phase separation, in which the bulk free-energy density and the interfacial thickness parameter determine pattern formation and microstructural evolution. In practice, these constitutive quantities are…