Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
SHARC, a new framework for SHapley Additive exPlanations for Regulatory Capital, makes Gaussian Process Regression models auditable by decomposing Stressed Value-at-Risk into baseline, mean-driven, and volatility-driven …
AI models struggle in real-world negotiations because they focus on language rather than strategic economic decision-making. A new training method called Reinforcement Learning from Verifiable Rewards (RLVR) shows promis…
New research introduces a framework called Statistically Meaningful Geometry (SMG) to evaluate whether large language models (LLMs) are genuinely intelligent or merely pattern-matching. The framework aims to detect signs…
Researchers introduced a Gibbs algorithm that simplifies posterior sampling in Bayesian inversion, offering reliable convergence guarantees and computational efficiency. The method, verified through numerical simulations…
NVIDIA and Google researchers have developed a host offloading technique in JAX that reduces high-bandwidth memory bottlenecks during LLM training, achieving up to 57% throughput improvements on NVIDIA GB200 NVL72 system…
Researchers introduced CcGAN-AVAR, an extension of the Continuous conditional Generative Adversarial Network, to address label imbalance and improve efficiency in continuous conditional generative modeling. The model use…
Onnes, a digital twin for dilution refrigerators, uses AI and LLM agents to improve fault diagnosis in quantum computing hardware, achieving 100% recall and near-perfect classification accuracy with minimal training data…
New smooth Monte-Carlo estimators can evaluate the Euler characteristic in continuous neural fields 250 times faster than traditional persistent-homology methods, but they require strict design rules and sacrifice accura…
A new multi-agent motion prediction method using mode-world weighted regression loss and an iterative decoder has achieved first place in the Argoverse 2 benchmark, promising to improve autonomous vehicle safety by balan…
Researchers developed an AI-driven MRI protocol that cuts scan time from 27 to 14 minutes using an explainable AI framework with XGBoost, SHAP, and Recursive Feature Elimination, reducing features to eight while maintain…
Researchers developed a Tri-Branch Modular Fusion Neural Network that integrates 3D spatial geometry, discrete topological grammar, and macroscopic physicochemical descriptors to predict molecular properties. On the QM9 …
Researchers developed FedPPO-PG, a federated multi-agent reinforcement learning framework for smart grid transient stability control. In tests on the IEEE 39-bus system, it achieved 100% stabilization, reduced stability …
A developer built WoW Brain, a neurocognitive OS with 60+ adaptive trainers and an AI Neuro-Probe, using FastAPI, SQLite, and Jinja. The project revealed that real-world cognitive training requires hysteresis models for …
A developer outlines three strategic steps for building a custom AI-powered productivity suite: establishing a robust data layer, implementing multi-model AI strategies, and automating operational integration. The approa…
Microsoft released Aurora 1.5, an open-source update to its Earth system foundation model that adds 22 weather variables, hourly forecasts, and probabilistic ensemble forecasting. The model, available on GitHub and Huggi…
A study of neural-interface models reveals a critical gap between formal robustness certificates and real-world safety, with EEGNet's classification accuracy dropping 25.7% under attack while certificates remained valid.…
Researchers introduced VTC, a tensor compilation framework that eliminates unnecessary data movement in deep neural networks by using virtual tensors and index mappings. VTC outperforms existing ML compilers by up to 1.9…
Researchers have developed a new approach to overcome the quadratic cost of causal self-attention in long-context transformers, using state update design and structural interventions like sink tokens and short convolutio…
Compass, a new AI methodology for prostate cancer detection, analyzes 2D micro-ultrasound studies using a multi-view approach that mimics clinical practice by integrating rotational video sweeps, outperforming traditiona…
Researchers have developed a new compression algorithm for decentralized AI training that achieves up to 99% compression without degrading convergence, enabling billion-parameter models to be trained on low-end GPUs with…