Neural Networks

Clark Labs Inc. released Clark Hash, a Rust package that compresses 384-dimensional neural embeddings into 48-byte searchable sketches, achieving a 32x reduction in vector memory. The stateless codec uses sparse Johnson-…

Python's performance in the benchmarks game is roughly 40 times slower than C or C++, yet it remains the dominant language for data analysis and machine learning because core libraries like NumPy, TensorFlow, and PyTorch…

Researchers have developed CHEEM, a continual learning framework that adapts model structure during task streams using four primitive operations—reuse, new, adapt, and skip—to reduce catastrophic forgetting without stori…

A new arXiv preprint proposes an end-to-end deep learning framework that directly learns portfolio weights by combining Long Short-Term Memory networks, Graph Attention Networks, and financial news sentiment analysis. Th…

A team of Bayesian statisticians has developed a method to fit million-parameter models using serverless GPU computing for pennies, dramatically reducing the cost and complexity of Markov chain Monte Carlo (MCMC) inferen…

Researchers have developed a new emotion representation method called Dimensional Distribution Emotion State (DDES) to help museum curators predict the emotional responses artworks will evoke in visitors. The approach us…

AirCast-SR, a new foundation model for atmospheric super-resolution, downscales global AI weather forecasts from 28-kilometer to 1-kilometer horizontal resolution at hourly intervals, producing 67-hour forecasts of eight…

Researchers have developed DuoGesture, a neuro-inspired dual-stream system that separately generates semantic and beat gestures for co-speech animation. The model uses a stochastic gate to coordinate when semantic gestur…

Researchers have developed Geometry-Aware Representation Denoising (GARD), a framework that uses diffusion-based restoration within a feed-forward 3D reconstruction model's feature space to improve multi-view 3D reconstr…

Researchers have developed a neural rule evaluator that detects anomalies by identifying violations of logical constraints, even when such violations are absent from training data. The system compiles rules into directed…

A new study benchmarked twelve deep learning architectures across four model families—convolutional neural networks, vision transformers, hybrid CNN-transformer backbones, and vision-language models—for multi-disease ret…

Researchers have introduced Neural Bayesian Sequential Routing (NBSR), a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph using a Dirichlet-Categorical con…

Researchers have developed InfoQuant, a training-free method that reshapes activation distributions in large language models to improve low-bit quantization efficiency. The approach, which uses Peak Suppression Orthogona…

Researchers at OpenPangu identified two failure modes in HiF8 W8A8 quantization-aware training for the OpenPangu-Embedded-1B model: amax saturation, which corrupts knowledge-sensitive representations through forward-pass…

Researchers have developed CoAD, a new framework that unifies classification and reconstruction approaches to improve time series anomaly detection. The framework uses a classification module to generate probability-info…

Researchers at arXiv introduced PathoFM, an encoder-centric transformer for clinical time-series learning that uses three complementary pretraining objectives—Local Completion, Temporal Continuity, and Unsupervised In-Co…

A unified evaluation of twelve deep learning models for binary skin cancer detection on the PAD-UFES-20 dataset found that well-tuned CNNs provide strong baselines, but transformer-based families consistently improve dis…

Researchers have proven a finite-sample bound on the approximate max-information of differentially private stochastic gradient descent (DP-SGD) that scales at most linearly with dataset size, matching classic results for…

Researchers developed HRVConformer, a deep learning architecture that classifies neonatal hypoxic-ischemic encephalopathy (HIE) by directly processing raw heart rate signals, achieving an AUC of 83.23% and accuracy of 74…

Researchers have developed VesselSim, a two-stage framework for 3D blood vessel segmentation that eliminates the need for expert annotations during training by generating 16,500 synthetic angiographic volumes. The system…