Neural Networks

Researchers introduced Implicit Causal World Models to recover environmental dynamics from offline multi-agent demonstrations without pre-defined causal graphs, addressing the failure of world models under distribution s…

Researchers from Georgia Tech and Apple have shown that applying standard graph algorithms to UMAP's internal k-nearest-neighbor (kNN) graph can enhance data sensemaking, outperforming or complementing purpose-built meth…

A developer's attempt to build a chess engine using ternary weights and a looped transformer failed, as both innovations proved ineffective, and the engine's strength came from a 1958 search algorithm. The loop collapsed…

A double neural bypass (DNB) neuroprosthetic system restored hand movement and sensation in a participant with chronic C4 sensory/C5 motor complete tetraplegia, enabling functional abilities such as self-feeding and mani…

The defense industry is shifting from static threat libraries to cognitive radar and electronic warfare (EW) systems that use artificial neural networks (ANN), deep neural networks (DNN), fuzzy logic, and genetic algorit…

An engineer at Frontend Facile explains the Transformer architecture, which underpins modern AI models like GPT, Gemini, and Claude. The Transformer overcomes two key limitations of previous recurrent architectures: poor…

Researchers have developed NRFormer+, a spatio-temporal Transformer that achieves state-of-the-art accuracy in nationwide nuclear radiation forecasting, reducing sudden-change mean absolute error by up to 19.1% over the …

A new theoretical framework from a paper on arXiv (2607.25507v1) proposes a bounded spectral analysis of rotary phase alignment in Transformer language models, proving that uniformly bounded phase displacement limits deg…

Researchers propose temporal-distance JEPA (TD-JEPA), a plan-aware representation learning method that mines directed temporal cost from reward-free trajectories to improve latent world model predictive control. Under lo…

Researchers propose WHTMix, a Walsh-Hadamard token mixer that replaces global self-attention in stereo depth estimation transformers, reducing model compute by a factor of 2.46 and single-image inference latency by a fac…

A new study from arXiv proposes neuromorphic masked diffusion language models (N-MDLMs) that integrate block diffusion with spike-based neuromorphic computation to improve inference efficiency. The approach achieves subs…

A new paper by Patience Strong proposes building neural networks as semiconductor devices rather than emulating them in software, which could eliminate the massive compute power currently required. The approach uses digi…

A new review article by Salk Institute neuroscientists, published in Neuron on July 21, 2026, concludes that neural traveling waves in the visual cortex function as a computational engine that builds internal representat…

A new study from researchers explores optimizing Transformer neural networks for real-time outlier detection in financial time series using FPGAs. The work demonstrates efficient implementation on a PYNQ-Z2 board to mini…

Researchers introduced EMG-CrossFormer, a hybrid convolutional-transformer model for multimodal surface EMG hand gesture recognition, achieving mean accuracies of up to 92.79% on NinaPro datasets when fusing sEMG with in…

Researchers propose a loss-aware feature-map pruning framework for convolutional neural networks that uses multi-armed bandits (UCB1 and Thompson Sampling) to identify and remove redundant feature maps while preserving a…

A study using EEG signals and a custom convolutional neural network (CNN) predicted the outcome of repetitive transcranial magnetic stimulation (rTMS) therapy for major depressive disorder (MDD) with 93.60% accuracy, acc…

A new preprint on arXiv (2607.22748v1) introduces Accessibility Plasticity, a principle of adaptive computation in which systems adapt by reorganizing which existing computations can interact, rather than only modifying …

A new study from arXiv identifies a fundamental limitation in standard attention mechanisms: when evidence patterns repeat, the numerator and denominator grow at the same rate, causing inputs with different amounts of ac…

A 10th-grade student built Green-AI, a Rust project exploring energy-efficient AI training using only integer arithmetic, and discovered a 'dead zone' problem where fixed-point weight updates stall when errors become sma…