#machine-learning News & Analysis

Application of Artificial Intelligence and Machine Learning in Libraries: A Systematic Review

SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model

Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering

Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation

Pythagoras-Prover introduces a family of efficient Lean theorem provers that achieve state-of-the-art performance with significantly fewer parameters than existing models, using novel training techniques including curriculum learning and augmented data generation. The 4B-parameter model outperforms DeepSeek-Prover-V2-671B by 167x parameter efficiency, while the 32B model sets new benchmarks on formal mathematics tasks.

Evaluation Sovereignty in Metadata-Driven Classification: A Multi-Track Framework for Weakly Supervised Information Systems

Is It You or Your Environment? A Bayesian Inference Framework for Genomically-Anchored Personalized Physiological Interpretation

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering

Mapping AI Programs in the U.S: A Status Report from Early 2026 and an Analysis of AI Majors and Minors

Improving Crash Frequency Prediction from Simulated Traffic Conflicts Using Machine Learning Based Microsimulation

LLM-Powered Personalized Glycemic Assessment in Type 2 Diabetes with Wearable Sensor Data

A Machine Learning Framework for Real-Time Personalized Ergonomic Pose Analysis

Emotional regulation improves deep learning-based image classification

An LLM System for Autonomous Variational Quantum Circuit Design

Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems

When it comes to predicting people’s preferences, it pays to consider “the power of three”

MIT researchers have advanced random utility models, a framework nearly a century old for predicting consumer preferences, by introducing what they call 'the power of three.' This upgrade enhances the accuracy and applicability of preference prediction across various domains, potentially impacting how businesses model consumer behavior and decision-making.

From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inference

SemantiClean is a modular framework that extracts semantic signals from e-commerce session data to predict purchase intent and customer behavior while prioritizing auditability and reproducibility over raw predictive accuracy. The system uses a predefined library of 24 behavioral elements organized across four layers and implements safeguards against signal inflation, representing a shift toward transparent, governance-focused AI systems over conventional black-box optimizers.

Forecasting Future Behavior as a Learning Task

Researchers propose treating AI behavior forecasting as a learnable task rather than relying on explainability methods, training specialized models to predict how large reasoning models will perform on new inputs. Behavior Forecasters outperform GPT-5.4 and Claude Opus-4.6 at predicting LRM consistency and input-sensitivity while operating at significantly lower inference costs.

StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery

Researchers introduce StatefulDiscovery, a framework that enables AI agents to conduct open-ended scientific discovery by maintaining explicit investigation state and coupling it with evidence-calibrated claim formation. The system addresses the challenge of avoiding overinterpretation by coordinating exploration trajectory with evidential support, demonstrated across 40 real-data tasks where it outperformed baseline approaches in producing well-supported, high-value claims.

Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents

Researchers have released Afrispeech Semantics, a comprehensive benchmark evaluating how well audio language models perform semantic reasoning tasks beyond basic transcription. The study tests models across five key areas including entailment, consistency, plausibility, and accent variation, revealing significant gaps in current audio AI systems' ability to understand spoken language nuances.

RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark

Researchers introduce RAIL, a new evaluation framework for large audio-language models grounded in cognitive science principles rather than task-specific metrics. The benchmark, based on the Cattell-Horn-Carroll cognitive framework, reveals that state-of-the-art audio-language models exhibit uneven performance across core auditory cognitive abilities, highlighting a gap between how humans and current AI systems process audio information.

RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways

Researchers introduce RoVE (Rotary Value Embeddings), a parameter-free modification to Rotary Position Embeddings (RoPE) that makes value tokens position-sensitive in attention mechanisms. Testing on GPT-2 models demonstrates consistent improvements in few-shot learning, out-of-distribution performance, and long-context retrieval tasks.

FreeBridge: Variational Schr\"odinger Bridges for Cellular Transition Dynamics

FreeBridge, a new computational method based on Schrödinger Bridges, addresses a fundamental challenge in cellular biology by inferring continuous cell transition pathways from static snapshots. The approach constrains predicted intermediate cell states to geometrically valid regions observed in real data, improving both accuracy and biological interpretability in perturbation modeling across multiple imaging datasets.

Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining

Researchers present a staged-promotion protocol for efficiently screening machine learning configurations during micro-pretraining, using fixed budget increments across heterogeneous hardware to reduce experimental costs while mitigating the risk of selecting configurations that perform well only at tiny scales. The study demonstrates that early-stage rankings are unstable across hardware types, but a frozen promotion rule successfully identified a consistent top performer while reducing total GPU-hours from 432 to 169.2.

APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection

APEX introduces a data-efficient framework for automatic prompt optimization in large language models by dynamically categorizing training data into Easy, Hard, and Mixed tiers. The system prioritizes Mixed-tier data to identify high-leverage subsets that improve prompt quality, achieving 11.2% performance gains on Gemini 2.5 Flash with 40% fewer evaluations than static approaches.