Researchers have developed a conditional Generative Adversarial Network (cGAN) framework that generates 3D porous media volumes with controlled porosity from 2D thin section images, eliminating the ne…
Researchers have developed a new approach to 1-WL stable coloring for Graph Neural Networks that breaks traditional scalability bottlenecks by using a probabilistically backed refinement algorithm. A …
Researchers introduced CORA (Coherent Orthogonal Rotation Adaptation), a parameter-efficient fine-tuning method that uses orthogonal rotations and diagonal scaling to outperform existing approaches li…
Researchers have developed a hybrid learning framework that integrates physics-informed constraints into neural networks to improve angle-of-arrival (AoA) estimation for RF signals, reducing errors by…
Researchers have developed a new framework called Dual-Critic Guided Diffusion Alignment (DCDA) that enables autonomous vehicles to navigate adverse weather conditions without explicit weather modelin…
Researchers have advanced Neural Controlled Differential Equations (NCDEs) with Log-NCDEs and Linear NCDEs, reducing training time by up to three orders of magnitude while achieving state-of-the-art r…
Researchers introduced Platonic Projection Structures (PPS), a framework that models observability in representation learning using operator theory, revealing fundamental limits on what can be inferre…
FUSE, a novel dual-track architecture for simulation-based inference, outperforms state-of-the-art baselines on standard benchmarks by preserving multimodal input features and using an FK-steered samp…
Researchers introduced FlatManifold, a continual learning framework that uses a Nyström manifold flattening map to handle non-stationary streams and severe label noise. The method projects data onto a…
Researchers introduced FAST, a framework that accelerates Temporal Graph Neural Network training by integrating sampling, memory I/O, and computation optimizations, achieving up to 4.7x speedup withou…
Researchers have developed a new method for feature selection in reinforcement learning that uses a non-convex projected minimax concave penalty to reduce estimation bias. The approach, integrated wit…
SCALA, a new machine learning framework inspired by cognitive psychology, improves model accuracy and sample efficiency in data-scarce environments by guiding learning from broad categories to fine-gr…
ManifoldFlow, a new approach to neural network weight constraints, introduces flexible spectral control by allowing a bounded positive spectrum instead of fixed singular values, outperforming traditio…
Researchers introduced PGRE (Poisson-Gamma Relational Evolution), a probabilistic model designed to capture temporal and relational dependencies in dynamic knowledge graphs. The model uses Gamma-distr…
Researchers introduced TRIAGE, a novel framework that refines credit assignment in agentic reinforcement learning by classifying actions based on their role, improving success rates and reducing ineff…
New research proposes a method to distinguish AI-generated speech from natural speech by analyzing vowel spectra using the Wasserstein metric and topological mapping. The approach could enhance digita…
Researchers have developed End-Net, a convolutional neural network for multi-class MRI classification of neurological disorders, outperforming existing models in accuracy and generalization. The syste…
New research argues that mathematically verifying the safety of artificial general intelligence (AGI) is fundamentally impossible due to theorems like Rice's, Gödel's, and Trakhtenbrot's, which collec…
Researchers introduced OrthoReg, a method that penalizes overlap between physics-based equations and neural networks in hybrid models, improving symbolic recovery and out-of-distribution performance i…
Researchers have reimagined Transformers as a dynamic dance between fast and slow paths, where weight dynamics and stability play essential roles. The framework divides parameter space into visible an…