Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
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…
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 from the GRAPES-3 collaboration at the Tata Institute of Fundamental Research have developed a machine learning pipeline to distinguish secondary muon and punch-through hadron tracks in the GRAPES-3 muon tele…
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 proposed a hardware-aware pruning and quantization strategy for Graph Convolutional Neural Networks to adapt them for embedded FPGA platforms in event-based vision. The method achieved BRAM memory reductions …
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…
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 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 fine-tuned latent diffusion models Protogen v3.4 and Stable Diffusion v1.4 on a dataset of Ulos motifs to generate novel designs for the traditional Indonesian textile. Protogen v3.4 outperformed Stable Diffu…
Researchers developed a deep learning pipeline integrating semantic segmentation, regression-based severity estimation, and disease classification for quantifying stress severity in field crops. The system, using U-Net w…
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 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 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 developed a multimodal generative framework for structural and functional MRI features, evaluating VAEs, transformers, GANs, and diffusion models. Their proposed graph VAE (gMMVAE) outperformed other variants…
Researchers introduced TriRoute, a unified controller that jointly optimizes attention resolution, expert selection, and KV-cache bit-width for language models, achieving Pareto-dominant performance over independent meth…
Researchers developed a physics-guided machine learning framework that integrates domain knowledge into deep learning models to predict fuel density for wildfire management, outperforming purely data-driven approaches in…
Researchers propose UASPL, a self-paced learning method that uses evidential neural networks to incorporate uncertainty estimation into sample selection, improving classification performance and interpretability. Experim…
Researchers introduced STST-JEPA, a self-supervised transformer for EEG analysis, pretrained on 47,703 sessions from ages 5-81. The model achieved a mean absolute error of 3.06 years in age regression and ranked first on…
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 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…