When Algorithms Tell Stories
A new wave of generative art is challenging our understanding of narrative, pushing beyond plausible storytelling to explore the unique potential of machine creativity.
Science
Guiding Hands: A New Approach to Humanoid-Object Interaction
Researchers have developed a framework that uses predictive guidance and persistent object tracking to enable more robust and adaptable interactions between humanoid robots and the objects around them.
AI Uncovers New Paths to Cancer Treatment
A new system combines artificial intelligence with biomedical knowledge to suggest promising drug combinations guided by patient biomarkers.
Building Trust with Robot Partners
New research reveals how a robot’s responsiveness can foster trust during collaborative tasks, but consistent communication is key.
The Self-Improving Scientist: AI Automates the Research Lifecycle
A new artificial intelligence system is streamlining scientific discovery by automating everything from data analysis to experiment design and iterative refinement.
Smarter Warehouses: Balancing Robots and Humans with AI
New research demonstrates how multi-objective reinforcement learning can optimize tote allocation in fulfillment centers, improving efficiency and space utilization in collaborative human-robot systems.
Modeling the Invisible: Synthetic Data’s Rise in MR Spectroscopy
As the demand for robust data analysis grows, researchers are increasingly turning to simulated datasets to augment limited experimental data in Magnetic Resonance Spectroscopy.
Beyond Automation: Intelligent Open RAN with Goal-Driven AI
A new framework leverages agentic AI to move beyond simple automation in Open RAN, enabling networks to dynamically adapt to changing demands and optimize performance.
Uncovering Hidden Equations with Probabilistic Trees
![Across 1010 repetitions of a 90/10 train-test split, the [latex]\mathsf{VaSST}[/latex] model-configured with [latex]K=3[/latex] and [latex]D=3[/latex]-demonstrates robust performance in learning the function [latex]\mathbf{y}=\mathbf{x}\_{0}^{2}-\mathbf{x}\_{1}+\tfrac{1}{2}\mathbf{x}\_{2}^{2}[/latex] across varying noise levels, as evidenced by consistently low out-of-sample Root Mean Squared Errors (RMSE).](https://arxiv.org/html/2602.23561v1/2602.23561v1/figures/in-sample-rmse_boxplots_3noise_sim1.png)
A new framework leverages variational inference and soft symbolic trees to automatically discover interpretable mathematical relationships within complex datasets.
Beyond Imitation: A Single Controller for Dynamic Humanoid Movement
Researchers have developed a new framework that allows humanoid robots to seamlessly track a wider range of complex motions with a single control system.