Machine Learning News

A new integrated deep learning and statistical framework enables whole-network gene-environment association studies of leaf vascular architecture, overcoming limitations of low-dimensional summary traits. The framework f…

Researchers propose DraftExpert, an expansion-aware self-speculative decoding framework for expert-offloaded Mixture-of-Experts (MoE) inference on end devices, achieving 1.45x average decode throughput improvement, 84-87…

A study using EEG signals and a custom convolutional neural network (CNN) predicted the outcome of repetitive transcranial magnetic stimulation (rTMS) therapy for major depressive disorder (MDD) with 93.60% accuracy, acc…

Researchers propose a reference feature atlas for auditing language models, trained once on a reference panel and reused for new targets by fitting only a linear decoder. In tests on five 7-9B instruction-tuned models an…

Researchers propose FMOPF, a framework using latent flow matching and constraint-aware interaction priors to generate diverse near-optimal solutions for AC optimal power flow, addressing the limitations of existing diffu…

A 2025 paper published at ICAIF 2025 and uploaded to arXiv on July 25, 2026, describes a compact neural architecture for portfolio optimization that reduces learnable parameters from 39,586 to 2,175. The authors report l…

A new hybrid model called MTSF-ANO, integrating variational quantum circuits with adaptive non-local observables, ranks first or second in mean squared error in 17 of 20 settings on the four ETT datasets, improving over …

Researchers propose Progress-conditioned Group Policy Optimization (ProGPO), a method that uses first-visit observation coverage to assign higher advantages to trajectories visiting new states when all group samples rece…

A new federated learning framework called QFedPolyp, proposed by researchers, combines quantization-aware training with low-precision model communication to reduce transmission costs by approximately 4 times while preser…

Researchers introduced CausalGate, an intervention-guided framework for transformer module pruning that measures semantic damage via Kullback-Leibler divergence, outperforming dynamic routing baselines on TinyLlama-1.1B,…

A new study from researchers explores optimizing Transformer neural networks for real-time outlier detection in financial time series using FPGAs. The work demonstrates efficient implementation on a PYNQ-Z2 board to mini…

Researchers have developed MEGA-CL, a foundation graph neural network framework for universal molecular ADMET prediction that integrates self-supervised contrastive learning with multi-head external attention and enhance…

A new multi-agent lane change decision model using the QMIX framework with a convolutional neural network (CNN-QMIX) can increase cooperative platooning rates by up to 26.2% for connected automated vehicles (CAVs) in mix…

Researchers propose a loss-aware feature-map pruning framework for convolutional neural networks that uses multi-armed bandits (UCB1 and Thompson Sampling) to identify and remove redundant feature maps while preserving a…

Researchers propose MIITA, a Memory-Induced Inference-Time Adaptation framework that enables small language models to perform continual learning under constrained storage without catastrophic forgetting. MIITA stores sup…

Researchers propose Co-E, a training-free system that synchronizes graph and text working memory for multi-hop question answering, outperforming comparable open-backbone baselines on six benchmarks and rivaling larger or…

Researchers propose CHiPS, a lightweight character-level authorship attribution method for Romanian texts that uses character histograms and positional signals without tokenization or pretrained language models. On a loc…

A new study introduces LENS, a protocol for evaluating whether machine-unlearning algorithms can suppress disinformation-aligned narrative frames in large language models. Testing on four near-12B multilingual models, th…

Researchers introduced LC-SEPLM (Long-range Contact-supervised ESM Protein Language Model), which adapts ESM2 with LoRA and long-range residue-pair contact supervision while retaining sequence-only downstream inference. …

Researchers propose DAMamba-UNet3D, a parameter-efficient state-space model U-Net for 3D medical image segmentation that achieves a mean Dice of 0.815 on BraTS 2020 with ~5.3 million parameters, roughly 13 times fewer th…