#machine-learning News & Analysis

Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models

From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers

Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models

Beyond Linear Surrogates: High-Fidelity Local Explanations for Black-Box Models

A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2

PAI: Fast, Accurate, and Full Benchmark Performance Projection with AI

Spectral Convolution on Orbifolds for Geometric Deep Learning

Automated Explanation Selection for Scientific Discovery

Evolved Sample Weights for Bias Mitigation: Effectiveness Depends on the Fairness Objective

Best Crypto Portfolio for 2026: Messari Pivots to AI and Pepeto Gives Early Investors the Entry That Large Caps Cannot Offer

Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning

The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning

Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification

A Scoping Review of AI-Driven Digital Interventions in Mental Health Care: Mapping Applications Across Screening, Support, Monitoring, Prevention, and Clinical Education

Unifying Optimization and Dynamics to Parallelize Sequential Computation: A Guide to Parallel Newton Methods for Breaking Sequential Bottlenecks

AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research

Visualizing Critic Match Loss Landscapes for Interpretation of Online Reinforcement Learning Control Algorithms

Researchers have developed a new visualization method for analyzing critic neural networks in reinforcement learning algorithms by creating 3D loss landscapes from parameter trajectories. The approach enables both visual and quantitative interpretation of critic optimization behavior in online reinforcement learning, demonstrated on control tasks like cart-pole and spacecraft attitude control.

Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations

Researchers introduce EAGLE, a new framework for explaining black-box machine learning models using information-theoretic active learning to select optimal data perturbations. The method produces feature importance scores with uncertainty estimates and demonstrates improved explanation reproducibility and stability compared to existing approaches like LIME.

Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering

Researchers developed a question-aware keyframe selection framework for video question answering that uses large multimodal models to generate pseudo labels and coverage regularization. The method significantly improves accuracy on temporal and causal questions in the NExT-QA dataset, making video analysis more efficient by reducing inference costs.

Interpretable Predictability-Based AI Text Detection: A Replication Study

Researchers replicated and improved upon an AI text detection system from the AuTexTification 2023 shared task, adding stylometric features and newer language models like Qwen and mGPT. The study achieved comparable or better performance than language-specific models while emphasizing the importance of clear documentation for reliable AI research replication.

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies

Researchers introduce Safe Flow Q-Learning (SafeFQL), a new offline safe reinforcement learning method that combines Hamilton-Jacobi reachability with flow policies for safety-critical real-time control. The method achieves better safety performance with lower inference latency compared to existing diffusion-based approaches, making it more suitable for real-time deployment.

NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation

Researchers introduce NV-Bench, the first standardized benchmark for evaluating nonverbal vocalizations in text-to-speech systems. The benchmark includes 1,651 multilingual utterances across 14 categories and proposes new evaluation metrics that show strong correlation with human perception.

First Proof

Researchers have released a set of ten previously unpublished research-level mathematics questions to test current AI systems' problem-solving capabilities. The answers are known to the authors but remain encrypted temporarily to ensure unbiased evaluation of AI performance.

Circuit Representations of Random Forests with Applications to XAI

Researchers developed a new method for converting random forest classifiers into circuit representations that enables more efficient computation of decision explanations. The approach provides tools for computing robustness metrics and identifying ways to alter classifier decisions, with applications in explainable AI (XAI).

Unsupervised Point Cloud Pre-Training via Contrasting and Clustering

Researchers propose ConClu, an unsupervised pre-training framework for point clouds that combines contrasting and clustering techniques to learn discriminative representations without labeled data. The method outperforms state-of-the-art approaches on multiple downstream tasks, addressing the challenge of expensive point cloud annotation.