Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced Physics-Audited Agentic Scientific Machine Learning (PA-SciML), a verification-first workflow that ensures surrogate models discovered by LLM agents satisfy physics constraints such as boundary con…
Researchers propose a deep reinforcement learning framework (MORP-DRL) for multi-objective portfolio optimization that jointly maximizes expected return and minimizes downside risk using CVaR and EVaR. The PPO-based stra…
A new study analyzing seven pretrained models reveals that the positional encoding scheme in transformers determines the spectral properties of attention heads, with RoPE inducing rotational spectra and absolute/ALiBi sc…
Researchers propose ROAM, a framework that uses LLM reasoning to adapt frozen specialist models to new scenarios without retraining, reducing MAE by over 20% in industrial processes with minimal overhead.
Researchers found that formal robustness certificates for embedded neural-interface models can pass even when task accuracy collapses, with EEGNet classification accuracy dropping 25.7% under attack while the certificate…
A new audit of grokking representation metrics reveals that effective rank measurements at the grokking transition overstate converged values by 3-5x on MLPs and 1.3-1.5x on transformers, with compression lagging accurac…
Researchers introduced Gimitest, an open-source framework for testing reinforcement learning policies across diverse environments and algorithms. The tool supports single- and multi-agent RL policies, aiming to improve r…
Researchers introduced CoFINN (Conservation Flux Informed Neural Networks), a physics-informed deep learning framework that embeds finite-volume conservation physics into CNN training for compressible flow prediction. Te…
Researchers propose Dynamic-in-Few-Step, a post-training acceleration framework that integrates dynamic structural sparsification into few-step distillation for video diffusion models. The method transforms a pre-trained…
Researchers introduced SpaR3D-MoE, a framework that enhances multimodal large language models with adaptive 3D spatial reasoning from sparse RGB inputs. It uses a spatiotemporal manifold sampling mechanism and a geometry…
Researchers introduced a method for extracting rail tracks from classified 3D point clouds using a fully convolutional recurrent neural network trained on synthetic data. The approach rasterizes points, applies the netwo…
Researchers at arXiv introduced Scrambled Edges, a counterfactual test that injects physically implausible edge cues into images, causing vision models to produce geometrically distorted depth predictions. The study foun…
Machine learning has fundamentally reoriented scientific practice from inference toward prediction, according to a new analysis of 4.9 million publications and 255 ML techniques by Malena Méndez Isla et al. The study ide…
Researchers at the GRAPES-3 experiment developed a graph neural network (GNN)-based pipeline for cosmic ray energy reconstruction, achieving improved accuracy and automated feature extraction on sparse detector arrays. T…
Researchers introduced Pyligent, a training framework that teaches AI models to recover from errors by learning from failed reasoning branches. In tests on hidden graphs, Sudoku, and Blocksworld, Pyligent improved solve …
Researchers propose InductWave, a wavelet-based inductive embedding method for logical query answering on knowledge graphs that handles unseen entities during training. The model achieves state-of-the-art performance wit…
Researchers have developed BatteryMat, a three-tier machine-learning-to-density-functional-theory (ML-DFT) workflow for screening lithium-ion cathode materials, as detailed in a July 7, 2026 arXiv preprint. The pipeline …
Researchers introduced a Siamese Neural Network framework to identify phase transitions in 3D percolation models using only 22 labeled probability points from non-critical regions. The method located percolation threshol…
Researchers propose PRoVeFL, a federated learning framework that combines privacy preservation, Byzantine robustness, and verifiable aggregation using multi-key fully homomorphic encryption across multiple servers. The f…
Researchers propose a programmatic solution for generating product advertising headlines using reinforcement learning on transformer-based masked language models. The method conditions on multiple products and outperform…