Neural Networks news and analysis on Web Pulse: 1652 curated articles tracking the latest Neural Networks developments, tools, and research, updated continuously from vetted sources.
A new arXiv paper (2609.35852v1) analyzes Transformer weights at a mesoscopic level using row and column scale fields — median-centred log-RMS profiles over a matrix's channels — which, with a global scale and a full bal…
A new arXiv paper (2609.35884v1) introduces a minimal representation that encodes a real D-component divergence-free vector field on a D-dimensional domain as a real (D-1)-component field on the same domain, using a Hous…
An independent replication of a recent uncertainty-aware graph neural network for road-level crash prediction found that 7 of 11 design decisions failed to replicate on a second London borough, with 4 of those reversing …
Researchers introduced SABLE (Sparse-view Animal Behavior Latent Embeddings), a self-supervised framework that reconstructs 3D animal behavior from two-view video without ground-truth 3D labels, according to the arXiv pa…
A team of researchers posted arXiv paper 2609.36737v1 describing a differentiable, GPU-accelerated acoustic simulator that reconstructs vocal tract shape solely from speech, solving a notoriously non-convex inverse probl…
OpenZL released v0.3.0, whose new LZ engine uses Marcin Żukowski's PivCo Huffman entropy backend to cut decompression time by 33% over v0.2.0 at compression level 1 with a 64KB window, reaching 3062 MB/s — 144% faster th…
OpenZL v0.3.0 introduces the Compression Transformer, a neural network that builds compression graphs automatically by selecting codecs one decision at a time, requiring no per-source training, no manual tuning, and no c…
Researchers introduced NEMSim (Neural Event-Mechanism Simulator), a method that compiles predefined event-attribute descriptions into an executable transition structure to simulate control-conditioned multi-event physica…
A new audit of sliding-window time-series classifiers finds that 75% overlap between test windows produces 16.9% Type-I error under IID observed-record inference, versus 7.2% for session-centered Bartlett-HAC, according …
A two-stage training framework for provably stable neural network observers decouples optimization into a point-guided Lyapunov pre-training phase followed by an LMI fine-tuning phase, according to the arXiv paper 2609.3…
Researchers introduced Newmark-β-DGN, a graph neural network framework that combines a semi-implicit Newmark-β-inspired update with an operator-weighted virtual hub to predict coarse-step physical dynamics and infer unob…
A new arXiv paper (2609.30279v1) proposes an algebraic framework, built on neural ideals, for classifying and interpreting the features captured by hidden-layer neurons in neural networks. The authors establish a corresp…
A controlled synthetic study of distributed solar ramp forecasting found that an explicit advection-aware graph does not beat a plain static or learned-adjacency spatiotemporal GNN when the cloud-motion vector (CMV) is e…
Researchers introduced SheafDEQ, a subhomogeneous deep-equilibrium architecture with adaptive neural-sheaf propagation, in arXiv paper 2609.30277v1, and proved it admits a unique equilibrium reached globally by fixed-poi…
Researchers at UBC-NLP introduced GyroNovo, a de novo peptide sequencing framework that uses decoder errors observed during training to guide fragment imputation and rotary embeddings to encode pairwise mass differences …
Researchers introduced MatFAE, a functional neural network that learns trajectories on the Riemannian manifold of symmetric positive definite (SPD) matrices, according to a new arXiv paper (arXiv:2609.30487v1). MatFAE us…
A mechanism-aware conditioning framework that injects ensemble-covariance statistics into an otherwise unchanged backbone improves rare-event emulation in data-limited chaotic systems, according to arXiv paper 2609.30746…
A developer wired a 130,000-neuron, roughly 5-million-synapse fruit fly connectome into a tic-tac-toe player running in Python on 8 GB of RAM, after an initial build crashed at tick 47 under garbage-collection pressure. …
Independent researcher Pratyaksh Raj published the Pratyaksh Framework, a self-limiting TVD explicit Runge-Kutta family that stays 100% explicit and matrix-free while avoiding the NaN explosions that strike classical RK4…
Developer dy released gpu-font, an open-source browser tool that identifies the closest font families to any line of text using WebGPU, published on Hacker News as a Show HN. The tool splits a crop into up to three grays…