Neural Networks

Researchers have introduced KREPE, the first generative representation learning method for hyper-relational knowledge graphs (HKGs) that can generate valid facts from arbitrarily masked queries, including completing part…

Researchers have developed a bifurcation theory that detects when neural networks acquire structured representations during training in real time, without relying on retrospective or label-dependent metrics. The theory i…

Researchers have developed the Iterative Refinement Neural Operator (IRNO), a new AI architecture that improves scientific modeling by iteratively correcting errors through fixed-point iteration, directly addressing the …

A developer built a new programming language, Jda, that compiles 33 times faster than Rust, achieving an average compile time of 42 milliseconds. The single-pass compiler produces 1MB static binaries and includes built-i…

A developer with 17 years of distributed systems and SRE experience built torchdiag, a diagnostic toolkit for PyTorch that provides five commands to measure gradient flow, detect dead neurons, and verify training steps. …

Researchers have developed MileStone, a modular framework that models compiler phase ordering as a multi-objective optimization problem using graph neural networks and reinforcement learning. The system reduces execution…

A developer built a Transformer-based time-series forecaster using PyTorch to predict blood glucose levels 30 minutes in advance from Continuous Glucose Monitoring (CGM) data. The model, which uses self-attention mechani…

Tesla has built an AI system that combines supervised, unsupervised, and reinforcement learning into a single architecture that improves every time a customer drives, according to an analysis of the company's strategy. T…

Astrum Verum, an open-source research project, has released a vector symbolic memory architecture called CognitiveMemory that outperforms standard Retrieval-Augmented Generation (RAG) on structured fact recall. The syste…

OpenAI trained a reward model using a loss function that does not require defining ideal reward values in advance. The loss function, introduced in OpenAI's 2022 paper, guides the model to assign higher rewards to prefer…

Neuroscientist Christof Koch argued at an April 2026 symposium in Porto that consciousness is a fundamental feature of reality, similar to gravity or electric charge, rather than a product of brain activity. Koch's propo…

The University of Toronto's Computational Social Science Lab released and open-sourced Maia-3, a chess engine that predicts human moves rather than optimal ones, on Tuesday. The model achieves a 57.1% prediction accuracy…

NVIDIA's InfiniBand became the dominant networking fabric for AI datacenters because it was purpose-built for lossless, high-throughput GPU-to-GPU communication. The shift to AI training fundamentally changed datacenter …

Yann LeCun, a 2018 Turing Award winner and pioneer of deep learning, discussed the rapid adoption of neural networks in speech recognition, image recognition, and natural language processing over the past fifteen years. …

Researchers have developed PiD, a pixel diffusion decoder that directly transforms latent representations into high-resolution images, bypassing the traditional decode-then-super-resolve pipeline. The system decodes 512×…

MathWorks hosted a webinar demonstrating an end-to-end workflow for designing, training, and deploying AI-based virtual sensor models to embedded processors within a single environment. The session highlighted techniques…

Researchers at the German Cancer Research Center (DKFZ) developed a new "Verified Tracking" paradigm for tumor lesion tracking across serial CT scans, achieving first place in the MICCAI autoPET IV challenge. The method …

A new computational study provides causal evidence that large language models acquire knowledge of unacceptable grammatical constructions through statistical preemption, a mechanism previously theorized in Construction G…

Researchers have developed a reproducible NLP pipeline for Katharevousa Greek, a historical language variant used in Greek parliamentary archives, by creating a Universal Dependencies-style parsing resource from 1,697 se…

Researchers developed a graph neural network that models alignment topology between reference documents and LLM outputs to detect hallucinations, achieving state-of-the-art results on four datasets. The method outperform…