#machine-learning News & Analysis

Multi-Class Human/Object Detection on Robot Manipulators using Proprioceptive Sensing

SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?

DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning

Compression-Driven Anomaly Detection in Brain MRI Using an Interpretable Quantum Autoencoder

The Remittance Blueprint: Data-driven Intelligence for Sri Lanka

How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks

What happened after 2,000 people tried to hack my AI assistant

An AI assistant developer conducted a security test inviting 2,000 people to attempt hacking their system, revealing vulnerabilities in AI safety and adversarial robustness. The exercise demonstrates both the challenges of securing AI systems against coordinated attacks and the importance of red-teaming in identifying real-world attack vectors before malicious actors exploit them.

Estimating Uncertainty in Classifier Performance with Applications to Large Language Models and Nested Data

Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law

Explainable Ensemble-Based Machine Learning Models for Detecting the Presence of Cirrhosis in Hepatitis C Patients

Statistical and Structural Approaches to Algorithmic Fairness

Lacuna: A Research Map for Machine Learning

Multipath Adaptive Gated Bottleneck Latent ODE with Raman Data Fusion for Cell Culture Process Forecasting

Decision-Aligned Evaluation of Uncertainty Quantification

Byzantine-Robust Aggregation for Securing Decentralized Federated Learning

Learning to Select Maximum Clique Algorithms: From Traditional Machine Learning to a Dual-Channel Hybrid Neural Architecture

Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes

Digital Twin-Driven Communication-Efficient Federated Anomaly Detection for Industrial IoT

Study finds AI trading strategies underperform buy-and-hold investing over 20-year period

A recent study demonstrates that AI-driven trading strategies have underperformed simple buy-and-hold investing over a 20-year period, suggesting that algorithmic complexity does not guarantee superior returns. The finding challenges the prevailing narrative around AI's potential in financial markets and highlights the persistent value of passive, long-term investment approaches.

Revolut enhances fraud detection with PRAGMA model on Nvidia platform

Revolut has deployed its PRAGMA fraud detection model on Nvidia's platform to enhance financial security and operational efficiency. The development represents a significant advancement in AI-driven banking solutions, potentially establishing new industry standards for fraud prevention across the financial sector.

Beyond Shapley: Efficient Computation of Asymmetric Shapley Values

Researchers present novel algorithms for computing Asymmetric Shapley Values (ASV), a machine learning explainability method that integrates causal knowledge. The work demonstrates polynomial-time computation in contexts where standard SHAP is #P-hard, with specialized algorithms for tree-structured causal graphs and approximation techniques for general directed acyclic graphs.

Elo-Disentangled Player-Style Embeddings for Human Chess via Rating-Conditioned Residual Move Model

Researchers developed a machine learning approach that separates chess playing strength (Elo rating) from individual player style by using a rating-conditioned base model combined with learned player embeddings. The method achieves 27-37% relative improvement in move prediction accuracy over existing models while successfully disentangling stylistic preferences from playing skill level.

Offline Multi-agent Continual Cooperation via Skill Partition and Reuse

Researchers introduce COMAD, a framework for multi-agent reinforcement learning systems to continually discover and reuse coordination skills from offline data without catastrophic forgetting. The approach uses skill partitioning and density-based reusability estimation to enable agents to efficiently transfer knowledge across sequential tasks in open environments.

Velocity Prediction in Automatic Guitar Transcription

Researchers present a novel methodology for predicting note velocity in automatic guitar transcription by leveraging synthetic training data from virtual instruments. The approach uses transfer learning to adapt velocity prediction weights from synthetic data to real guitar audio, achieving state-of-the-art transcription performance while successfully addressing a previously under-explored aspect of music transcription models.

Recursive QLSTM with Dynamic Variational Quantum Circuit Adaptation

Researchers propose Recursive QLSTM, a quantum machine learning model that extends quantum long short-term memory networks through recursive metacore-based constructions for improved sequential data processing. The model demonstrates enhanced temporal information propagation across variable input sequence lengths, offering a flexible framework for quantum computing applications in time-series analysis.