Researchers have developed ELLA, a social robot powered by generative AI, to engage young children in interactive storytelling and foster language development within the home environment.
Researchers have developed a multi-task reasoning model that significantly improves predictive accuracy and reasoning capabilities in molecular science, pushing the boundaries of what’s possible with artificial intelligence.
![Accumulated insights progressively refine a complex workflow, demonstrated by a learning curve showing decreasing error [latex]AHC error[/latex] across multiple runs, an episode avoidance matrix revealing successful navigation around potential pitfalls, and a shift in tool usage from reactive infrastructure debugging to proactive physics exploration-suggesting that knowledge not only mitigates failure but actively guides discovery.](https://arxiv.org/html/2603.13191v1/x2.png)
New research demonstrates how equipping AI with persistent memory transforms them from task executors into autonomous researchers capable of independent scientific discovery.
Researchers are developing intelligent robotic guide dogs that utilize natural language to not only navigate environments, but also describe surroundings and respond to user queries.
A new approach intelligently balances network connections to maximize homophily – the tendency for individuals to connect with similar others.
A new framework uses evolutionary optimization and real-time rendering to dramatically improve the accuracy and speed of surgical instrument tracking during complex procedures.
![The study demonstrates how a fluid’s local chemical potential, defined as [latex]\beta\mu_{loc}(x) = \beta\mu - \beta V_{ext}(x)[/latex], and density profile [latex]\rho(x)[/latex] influence metadensity functionals-approximated here through mean-field theory and neural networks-to predict the scaled metadirect correlation function [latex]c_{\phi}(x,r)[/latex], revealing that even complex interparticle interactions governed by a repulsive potential can be modeled with surprising accuracy through automatic differentiation.](https://arxiv.org/html/2603.11973v1/x4.png)
A new machine learning framework enhances classical density functional theory by directly incorporating interparticle interactions, promising more accurate and efficient modeling of fluid behavior.
New research reveals that the way sparse Mixture-of-Experts transformers allocate computational resources contains surprisingly clear signals about the tasks they are performing.
A new framework intelligently coordinates specialized AI tools to process diverse requests, offering a faster, more cost-effective alternative to traditional approaches.
![The study evaluated multiple methods for predicting host-guest binding free energies on a benchmark dataset, quantifying performance through metrics like root mean squared error [latex]RMSE[/latex], Pearson correlation coefficient [latex]rr[/latex], and Spearman rank correlation ρ, all with 95% confidence intervals to assess prediction reliability.](https://arxiv.org/html/2603.12253v1/x2.png)
A new computational method promises to accelerate virtual screening by directly calculating binding free energies from molecular dynamics simulations.