Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced a GPU-accelerated framework for segmenting anisotropic 3D microscopy volumes without dense annotations, achieving accuracy matching inter-expert agreement. The method, applied to kidney glomerular …
Researchers introduced CMU-Drive, a closed-loop end-to-end benchmark for evaluating cooperative autonomous driving with multiple connected autonomous vehicles in safety-critical scenarios, and V2V-VLA, a cooperative Visi…
Researchers at the University of Yaoundé I and the University of Buea implemented an embedding initialization strategy for unseen low-resource languages in multilingual neural machine translation, testing it on Limbum-to…
Researchers propose TEMPER, a tensorized parameterization for residual routing in deep neural networks that reduces additional parameters by about 84% compared to manifold-constrained hyper-connections (mHC) at eight res…
PhysAttNet, a physics-informed attention framework introduced in arXiv:2608.07681v1, improves time series forecasting accuracy and generalization in industrial and astrophysical applications by augmenting a lightweight C…
Researchers introduced V-Simba, a visual reinforcement learning architecture built on Soft Actor-Critic (SAC) with data augmentation, which matches or outperforms state-of-the-art methods on the DMC, Adroit, and Meta-Wor…
Researchers propose SIMBA, a diffusion-model-agnostic framework for influence maximization that replaces complex neural architectures with a lightweight two-layer graph neural network surrogate and direct discrete search…
Researchers propose Backward Compatibility Loss in Tree-based eXplanations (BCLTX), a metric to suppress changes in decision tree explanations before and after model updates, and CART with Backward Compatibility in Tree-…
A new arXiv paper challenges the notion that interpretability comes at the cost of capability, showing that making interpretability a training constraint allows it to scale with model capability across three orders of ma…
Reasoning language models fail to strategically allocate a shared test-time compute budget across multiple questions, according to a new arXiv preprint (arXiv:2608.07968v1). The study introduces an exam-style framework a…
A new arXiv study (2608.07471v1) applies machine learning to recognize fraudulent banking transactions, proposing an artificial neural network model that improves detection accuracy. The logistic regression algorithm ach…
Researchers introduce CODS, a critic-guided data selection method for reusable offline reinforcement learning, which at a 10% budget retains 96.6% of eligible-pool performance across 20 D4RL task-algorithm cells. CODS ou…
Researchers developed neural-operator surrogates that predict hydrodynamic fields for planar and volumetric eel swimmers, achieving a full-domain global relative L2 error of 3.51% on five held-out high-Reynolds-number tr…
A new arXiv preprint (2608.07725v1) introduces a constant-aware comparison protocol for average-reward reinforcement learning regret, deriving an explicit finite lower certificate for communicating MDPs that improves the…
Researchers introduced LUCID, a hierarchical model-based reinforcement learning framework for long-horizon humanoid loco-manipulation, which plans over reusable skills via imagined rollouts of a learned dynamics model. I…
A study of three generative vision-language models on chest radiographs found that reference agreement does not transfer reliably across institutions, with the best estimation strategy achieving a mean Brier score of 0.0…
Researchers propose Barycentric Rational Forecasting with Chebyshev Enhancement (BRACE), a method that uses barycentric rational functions to forecast cached features in Diffusion Transformers (DiTs), improving inference…
A new multimodal framework combining Swin Transformer image features with clinical metadata achieved 92.55% test accuracy and a 91.33% macro F1-score on a public dataset for skin lesion classification, outperforming unim…
An evaluation of 19 unsupervised anomaly detection models on the BowTie manufacturing dataset found that performance is less stable than on standard benchmarks like MVTec AD, highly sensitive to preprocessing, and incons…
DocAtlas, a new system for long-document understanding that treats the process as mutable-state interaction, achieves 71.4% on MMLongBench-Doc with GPT-5.4, surpassing the human-expert reference of 65.8%. A Qwen3.5-4B VL…