Neural Networks news and analysis on Web Pulse: 1660 curated articles tracking the latest Neural Networks developments, tools, and research, updated continuously from vetted sources.
A study posted to arXiv (2609.10657v1) mapped the memorization-to-generalization boundary across 384 configurations of two-hidden-layer MLPs on modular arithmetic, fitting a power-law scaling relation for grokking onset …
A multi-stage rule-chaining framework solved 230 of 240 ARC-AGI-2 test tasks and exceeded 95 percent overall accuracy, according to an arXiv paper (2609.10654v1) presenting the system. The framework combines a determinis…
Researchers introduced RAMamba-Net, a reliability-aware Mamba-based multimodal fusion network for auditory attention decoding (AAD) that combines electroencephalography (EEG) and electrooculography (EOG) signals, accordi…
Researchers proposed CoMA-DiT, a bidirectional cross-modal Diffusion Transformer for latent augmentation that treats paired modalities as mutual generative supervision, according to an arXiv paper (2609.11341v1). In expe…
A software engineer at Coinbase, Alex Wormuth, is training a digital reconstruction of an adult male fruit fly's brain to play the original Doom, with the fly reaching round 6385 as of the time of writing. Google announc…
Coinbase software engineer Alex Wormuth reported that a simulated fruit-fly brain wired to trade Bitcoin turned a $1 profit on a $100 stake one day after the experiment launched on September 11, 2026. The project, called…
A working example project called GraphSAGE-GraphRAG demonstrates that structure-aware retrieval using a Neo4j knowledge graph and an offline-trained GraphSAGE GNN can solve multi-hop reasoning that flat vector RAG fails …
Researchers from HHMI Janelia, Google Research, and other collaborators used AI to produce a complete brain map of a male fruit fly, a years-long project announced in a Google Research blog post. Software engineers then …
A developer tool called GPU-time parses plain-English date and time phrases into real dates and RFC 5545 recurrence rules using a small neural model with 24,761 parameters that runs locally in the browser. The tool accep…
Researchers introduced FreeFlow, a bias-free hierarchical transformer for optical flow estimation that avoids task-specific inductive biases such as correlation volumes, feature warping, and iterative refinement. The wor…
Moonlake founders Chris Manning and Fan-yun Sun are proposing causal, action-conditioned world models that fuse game engine abstractions, symbolic reasoning, and learned neural priors, positioning the approach against Ya…
Researchers at the Indian Institute of Technology (IIT) Bombay demonstrated an ultra-low-power neuromorphic neuron fabricated in standard GlobalFoundries 45-nm CMOS technology that consumed about 1,000× less power and sh…
Researchers proposed the Adaptive Margin Ordinal Loss (AMOL), a multiplicative per-class weighting scheme that suppresses "center-class hedging" in ordinal classification, according to an arXiv paper (arXiv:2609.10752v1)…
Researchers introduced HiPerViT, a compact vision-only architecture that injects an explicit second-order statistical prior into a transformer-based recognition pipeline via a bilinear descriptor encoded as a statistical…
A new arXiv paper (2609.11227v1) shows that time-to-first-spike spiking neural networks can generate richer partitions of the input space than conventional feedforward ReLU networks. The authors derive upper and lower bo…
Researchers introduced CoRA-NAS, a two-stage neural architecture search framework that combines a static ranking prior with low-cost learning-curve refinement, according to a new arXiv paper (arXiv:2609.11884v1). CoRA-Re…
Researchers introduced Graph-Guided Quasimetric Dense Reward (G2QDR), a framework that predicts pairwise state connectivity strength in asymmetric environments and converts those strengths into scalar auxiliary dense rew…
A paper posted to arXiv (2609.10589v1) introduces Halo, a modification that reuses an existing deep forecaster's architecture to add a second output estimating the scale of its implied distribution and trains it under th…
A new arXiv paper (2609.09589v1) develops a statistical-mechanical description of deep neural network learning directly in function space, treating parameter configurations as microscopic realizations and functions with …
A paper posted to arXiv (2609.09306v1) introduces "Gradland," an idealized world of neural networks whose physics are known and functions mostly differentiable, to test whether the first-order structure of physical inter…