Neural Networks news and analysis on Web Pulse: 1654 curated articles tracking the latest Neural Networks developments, tools, and research, updated continuously from vetted sources.
A new arXiv paper (2609.19934v1) proposes the Depth Control Protocol (DCP), a diagnostic suite that disentangles three factors conflated by depth truncation when evaluating whether depth-recurrent language models genuine…
Researchers posted arXiv:2609.19996v1, a deep architecture that jointly optimizes cost functions and a route-ranking model for customizable route planning. The system runs a multi-objective Dijkstra algorithm offline to …
A new LSTM Universal Transformer (LSTM-UT) with bounded gated memory outperformed both the Block Universal Transformer (BUT) and CoTFormer on Rule 30 cellular automata and a delayed-recall task, according to an arXiv pap…
A non-equilibrium dynamical mean-field theory (DMFT) developed by researchers describes how learning in recurrent neural networks drives a transition from chaotic to stable task-dependent dynamics, according to a paper p…
A new arXiv paper (2609.19384v1) proposes Riemannian–Lorentz Parameter Fusion (RLPF), a geometry-aware method for merging a Vision Transformer and a state-space model into a two-branch hybrid that reaches 82.37% on CIFAR…
Researchers proposed Compressed Active Subspaces (CAS), a method that maps model parameters into a compressed space via a structured isometric embedding before constructing the active subspace, cutting the memory needed …
Researchers introduced JointMatch, a learning-based framework that solves ride-sharing request pairing and vehicle assignment together on a single sparsified graph using a graph neural network. On New York City Yellow Ta…
VIDRAFT AI Research published a paper (arXiv:2609.20269) testing whether Transformer attention mechanisms need to repeat identically at every layer, using a 7×7 Latin square to spread seven sequence mixers evenly across …
A developer released a 14-byte neural network that solves mazes, the result of an experiment across 47 distinct phases aimed at maximizing maze solve rate with the most compact network representation possible. The projec…
Researchers at Johns Hopkins Medicine reported in Nature Neuroscience on December 2, 2024 that axons in mouse neurons form repeating nanoscale swellings called "non-synaptic varicosities" rather than the smooth tubes dep…
A developer's technical explainer outlines four ways deep generative models make complex data distributions learnable: autoregressive models factorize a joint distribution into conditionals, variational autoencoders intr…
Researchers established a transplantation platform called xenocortication, genetically depleting glutamatergic neurons from mouse neocortex and hippocampus to engraft human stem-cell-derived cortical organoids (hCOs) int…
Researchers proposed Sharp Mode Connectivity (SMC), a sharpness-aware reformulation of mode connectivity that enforces low loss across the entire neighborhood of a weight-space interpolation curve rather than only along …
A paper posted to arXiv (2609.17654v1) proposes a regularized least squares approach for training quadratic neural networks that yields a lower bound on the training optimization problem's solution when the regularizatio…
The University of Bozen/Bolzano has released lecture notes from its 2025/2026 PhD course on Physics Informed Neural Networks, published as arXiv:2609.17638v1. The notes cover Physics Informed Deep Neural Networks (PINN) …
A new arXiv paper (2609.17571v1) reports that grokking in Transformers is a spectral recoding of an existing distributed circuit rather than a switch between modules, based on behavior-aligned exact activation games the …
Researchers introduced K$^2$SVD, a method that learns the leading singular functions of the Koopman operator by optimizing a Hilbert-Schmidt objective, producing a low-rank approximation with a latent space using less th…
Cloudflare's Page Shield machine learning model detected all eight malicious JavaScript payloads across four client-side attacks on storefronts, while seven of the eight were entirely absent from VirusTotal and URLScan r…
Researchers developed ASDint, a spiking neural network model, paired with SyNC, an ASIC-based hardware architecture, to analyze glutamatergic neuron synapse dysfunction in Autism Spectrum Disorders and related neurologic…
Scientists have mapped a fruit fly's brain in detailed resolution and are using the data to build computational models of its neural network. The work remains far from any human-brain emulation, with the mapping of biolo…