Neural Networks

VisionWave Holdings (Nasdaq: VWAV) filed a U.S. provisional patent application for its SDNN (Symbiotic Deep Neural Network) architecture, encompassing a 455-page specification. The early-stage, pre-revenue technology tar…

Russian scientists at the Moscow Institute of Physics and Technology developed an AI algorithm that predicts extreme Arctic weather with five times higher effective resolution than global climate models. The neural netwo…

Researchers argue that the 'lottery ticket' analogy for overparameterized neural networks is misleading, proposing instead that wider networks succeed by expanding optimization dimensions to escape bad minima. The study …

Bright Kwaku Manu et al. introduced LANTERN, a longitudinal attribute-conditioned neural network that estimates multi-state health-transition probabilities from irregular health records. Using Health and Retirement Study…

Researchers led by Yi-Ran Xue introduced phase-gradient estimators for neural-network quantum states in a paper submitted to arXiv on June 11, 2026. The direct estimator reduces variance in phase gradients, and an adapti…

Researchers at the University of Tennessee and the University of Florida developed a hardware neural network backdoor that can be hidden in custom chips used for edge AI, exploiting vulnerabilities in the supply chain of…

Noise Contrastive Estimation (NCE) and InfoNCE are machine learning methods for estimating statistical distributions by distinguishing real data from noise, with applications in language modeling, speech recognition, and…

Researchers introduced Muon$^p$, a new optimizer that uses fractional spectral-power updates to interpolate between Muon and gradient descent, improving finetuning performance on billion-scale models. The method preserve…

Researchers found that repetition loops in Gemma 4 instruction-tuned LLMs can be fixed by editing as few as one neuron, but the fix does not resolve deeper 'doom loops' caused by missing knowledge. The study shows that w…

Researchers at arXiv have causally demonstrated that the weight norm sets the grokking timescale in neural networks, settling a dispute over whether weight norm causes the delayed generalization. By intervening on the no…

Researchers developed a Transformer-based scheduling policy for the open shop scheduling problem (OSSP) using deep reinforcement learning. The model, trained on small Taillard benchmark instances, generalizes to larger p…

Researchers found that introducing structured noise into artificial neural network activations improves robustness against adversarial attacks and naturalistic image modifications, with noise structure from adversarial a…

A new thesis investigates how Bayesian principles can improve understanding of modern deep learning systems, introducing the Deep Variational Implicit Process (DVIP) and post-hoc methods VaLLA and FMGP for uncertainty es…

Researchers developed the LANTERN framework, a neural network that models health-state transition probabilities for long-term care using irregular longitudinal data. The model outperformed logistic regression and gradien…

Researchers propose Spiking Fourier Graph Operators (SpikF-GO), a spiking neural network model for multivariate time series forecasting that uses a hypervariate graph to model inter-variable dependencies. SpikF-GO achiev…

Researchers propose Feature Interaction NEtwork (FINE), a lightweight semantic alignment module that refines low-level features via high-level contextual guidance using cross-level attention prior to fusion in object det…

Researchers introduced neural slack variables, a primal-side approach that converts constraint enforcement into a regression problem by coupling a primary network with an auxiliary network. The method achieved zero measu…

Researchers have demonstrated that convolutional neural networks can achieve higher accuracy by introducing learnable pairwise connections between filters, moving beyond traditional pointwise activation functions. The ne…

A research project using k-sparse autoencoders found interpretable features in a small reasoning model, including features that appear to correspond to the model's reasoning process. The experiment analyzed hidden states…

The Kimi Team published a new attention architecture, Kimi Linear, on arXiv in 2025. The architecture uses Kimi Delta Attention interleaved 3:1 with full attention, becoming the first linear hybrid to outperform softmax …