Neural Networks

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…

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 RadarSim, a unified differentiable renderer that uses multimodal neural fields to generate high-resolution Doppler radar range images by leveraging camera data. The system addresses the low spa…

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 developed Lie group embedded dynamical neural networks (LieEDNN) that enable stable, learnable dynamics on smooth manifolds by treating Lie groups as intrinsic representations of continuous symmetry. The…

Researchers have developed CE-FedGNN, a federated graph neural network framework that enables organizations to collaboratively learn from distributed graph data without sharing raw data or frequent embedding exchanges. T…

Researchers have developed PaGeR, a framework that adapts existing 3D foundation models designed for perspective images to reconstruct full 360-degree scenes from single panoramic images. The model predicts scale-invaria…

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 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…

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 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…

Two engineers in Dubai built an AI memory engine inspired by the hippocampus that reduced retrieval-augmented generation (RAG) costs by 10x. The system uses sparse binary codes—40 active bits out of 8,192 slots—to achiev…

A team of researchers from Yale's Building AI Infrastructure class achieved a new speed record of 81.2 seconds on the modded-nanoGPT benchmark by introducing a learnable per-(layer, head) tanh(α) gate on Exclusive Self-A…

Hussein Mahdi published a breakdown of the mathematics underlying neural networks, aiming to clarify concepts he felt were poorly explained elsewhere. The guide walks through the core calculations that power deep learnin…

Machine learning teams are adopting visual debugging tools to gain real-time visibility into model internals during training, addressing the common problem of silent failures like vanishing gradients and overfitting that…

KlongPy now supports a PyTorch backend that enables GPU acceleration and automatic differentiation for gradient-based computations. The torch backend outperforms NumPy by up to 8x on large arrays and provides exact gradi…

Researchers at arXiv (arXiv:2605.23035) used sparse autoencoders to decompose GPT-2 XL and Llama-3.1-8B into 16K-32K interpretable features per layer, finding that semantic features alone recovered 94% of peak neural enc…

DeepSeek researchers introduced manifold-constrained hyper-connections to restore the identity mapping property in transformer architectures, addressing training instability and scalability issues caused by standard hype…

A developer explains that understanding seven core AI metrics—parameters, tokens, FLOPS, TOPS, and FLOPs—is essential for avoiding costly deployment mistakes, such as choosing a 70B-parameter model that runs on a laptop …