Navigating the Crowd: AI-Powered UGV Pathfinding
A new deep reinforcement learning framework empowers unmanned ground vehicles to safely and efficiently navigate complex, crowded environments.
Science
Your AI Knows Too Much: The Privacy Risks of Personalized Assistants
New research reveals that popular AI assistants built on retrieval-augmented generation routinely leak sensitive user data during everyday conversations.
Modeling Water’s Edge: Machine Learning Refines Melting Point Predictions
![The difference in chemical potential between ice Ih and water-represented as [latex]\Delta\mu\_{\mathrm{ice}-\mathrm{liq}}(T)[/latex]-varies with temperature, with melting temperatures [latex]T\_{\mathrm{m}}[/latex] precisely defined as the points where this potential difference equals zero.](https://arxiv.org/html/2512.23939v1/x7.png)
New research rigorously assesses the accuracy of machine learning potentials in simulating the thermodynamic behavior of water and ice, revealing critical discrepancies in existing models.
Surgical Precision, AI Insight: Decoding Skill in Microanastomosis
A new artificial intelligence framework offers automated assessment of surgical skill during delicate microanastomosis procedures.
Unfolding Protein Prediction with Scale
A new model, SeedFold, demonstrates that scaling both data and model size, combined with a novel attention mechanism, dramatically improves the accuracy of biomolecular structure prediction.
Sky Networks: Intelligent Beamforming for Airborne Communications
A new approach optimizes signal transmission from constellations of high-altitude platforms, promising more reliable and efficient wireless connectivity.
Unmasking Hidden Causes: A New Approach to Causal Discovery
![Performance of a decorrelation method diminishes with increasing pervasive and localized confounding, as evidenced by the reduction in [latex]\Delta F1[/latex] score across varying strengths and densities of these confounding factors.](https://arxiv.org/html/2512.24696v1/figures/dcl2_rep10_SHD_vs_Ld.png)
Researchers have developed a method to infer causal relationships even when unobserved variables are actively distorting the data.
Flowing Towards Better Policies: Reinforcement Learning Gets a Generative Boost
Researchers are integrating flow-based generative models into reinforcement learning algorithms to improve policy optimization and sample efficiency.
Uncovering Hidden Symmetries in High-Dimensional Data
A new machine learning approach reveals the fundamental invariants governing complex tensors, offering a powerful tool for analyzing data across diverse scientific fields.
Bridging the Reality Gap: Adapting 3D Object Detection to New Environments
New research demonstrates effective techniques for training 3D object detection systems with limited labeled data in unfamiliar driving conditions.