Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A 124M-parameter GPT-2 model trained from scratch on OpenWebText data using a custom deep learning library achieved a validation loss of 2.764 nats and a perplexity of 15.87 after 56,000 steps (27.5B tokens). The model, …
A developer has been refining KMDS, a framework for building repeatable and auditable machine learning systems, with recent updates focusing on analytical governance. New features include a Feature Advisor service that r…
A new arXiv preprint (2606.18164) by Niklas Forner and coauthors analyzes how transformers learn chain-of-thought state tracking in a solvable setting, training a simplified one-block transformer on permutation compositi…
A guide explains the Naive Bayes algorithm, a simple yet effective machine learning method widely used for classification tasks, highlighting its practical applications and enduring relevance in AI.
A beginner's guide on Towards AI explains ensemble learning methods bagging and boosting, covering decision trees, Random Forest, and XGBoost with analogies, examples, and code.
Researchers introduced a geosteering framework that combines particle filtering with reinforcement learning to optimize well trajectory decisions under geological uncertainty. The framework evaluates three decision-makin…
Researchers tested Word2Vec on Toki Pona, a constructed language with only ~130 words, using 1.4 million sentences. They found that non-core tokens like loanwords improved embedding quality by drawing similar words close…
A comparative study of classification models within the InferBERT framework for pharmacovigilance found that domain-specific pre-trained BioBERT outperformed larger models like Med-LLaMA in detecting causal adverse drug …
Researchers introduced SpeechDx, a large-scale benchmark for clinical speech AI spanning 12 datasets and 27 tasks across diverse health conditions, designed to evaluate generalization by structuring tasks according to di…
Researchers developed an online adaptive clinical decision support AI system that integrates treatment effect estimation, patient digital twins, and reinforcement learning to recommend treatments in real-time while ensur…
Researchers introduced the Simple Strands Agent (SSA) to minimize the 'intent-execution gap' between AI models and their harnesses, improving agent performance. Analyzing 138k trajectories, they found that fine-grained m…
Researchers show that grokking in deep neural networks is caused by noise-driven escape from metastable phases during first-order L2 regularization phase transitions. Using linear DNNs, they demonstrate that SGD noise he…
Researchers propose an end-to-end graph neural surrogate for forecasting CO2 plume migration in geological storage, evaluated on the SPE11A benchmark. The model uses an anisotropic message-passing mechanism to capture di…
Researchers introduced the first foundation model-orchestrated workflow for crash safety design, enabling surrogate-assisted pedestrian protection exploration that reduces evaluation time from hours to seconds. The workf…
Researchers developed a diffusion-based model that generates irregular clinical time series by jointly modeling laboratory values and their observation patterns, using the MIMIC-III-derived DACMI benchmark. The approach …
Researchers propose a three-layer architecture for verbal reinforcement learning in LLM agents, addressing the retention-forgetting dilemma in non-stationary environments. The system uses rules, evidence, and skills with…
Researchers proposed a BiSpectral Mamba framework combining multi-scale CNN, spectral attention, bidirectional state-space modeling, and quantum-inspired learning for hyperspectral crop field analysis, achieving 84.83% a…
Researchers introduced GeoDisaster, a benchmark for operational geospatial disaster reasoning with 2,921 instances across 43 question types, and proposed an orchestrated multi-agent framework with 18 disaster-oriented to…
Researchers introduced REINS, a training-free method that steers video diffusion models away from unsafe content at inference time by manipulating internal representations. The approach, which adds a safety direction to …
Researchers propose SierpinskiCam, a method for video retaking that uses Sierpinski triangle pattern cues to improve camera controllability and geometric consistency under large viewpoint changes. The approach augments g…