Robots Learn to Critique Themselves, Improving Social Skills
New research demonstrates a system allowing robots to independently assess and refine their behavior, leading to more natural and effective human interactions.
Science
AI Agents Unlock New Insights from the Biology of Ageing
A novel framework leveraging artificial intelligence and gene ontology is demonstrating a powerful new approach to understanding the complex mechanisms behind ageing.
Designing Robots That Bend to Your Will
A new approach combines advanced simulation and optimization to rapidly create soft robots tailored to specific tasks.
Beyond Prediction: AI That Can Actually *Do* Science
A new vision for artificial intelligence moves beyond data analysis to enable autonomous scientific exploration through embodied agents that perceive, act, and discover.
Agents That See and Understand: Navigating the World with Language
A new multi-agent system uses the power of vision-language models to achieve open-vocabulary object-goal navigation without task-specific training.
Words Matter: How Speech Transcription Quality Impacts Alzheimer’s Detection
A new study reveals that improving the accuracy of converting speech to text can dramatically boost the performance of algorithms designed to identify early signs of Alzheimer’s disease.
Simulating the City: A New Approach to Traffic Flow
![The system models multi-actor interactions within a simulated traffic environment, recursively unrolling trajectories by encoding actor states and their neighbors into interaction-aware spatial embeddings, then refining these embeddings through temporal attention to parameterize a Gaussian distribution from which subsequent states are sampled, effectively creating a closed-loop predictive model of dynamic systems where state decays into probabilistic futures [latex]HH[/latex] timesteps ahead.](https://arxiv.org/html/2603.18266v1/x1.png)
Researchers are leveraging generative models to create more realistic and safer simulations of complex traffic intersections.
The Illusion of Personality in AI
Despite increasingly human-like interactions, attributing personality traits to large language models is a flawed premise, but a revealing analytical tool.
The Persona Paradox: Balancing Alignment and Accuracy in Large Language Models
New research reveals that while imbuing AI with expert personalities can improve how well it follows instructions, it often comes at the cost of factual recall.
Modeling Life’s Networks: A New Tool for Biochemical Systems
![A dynamic simulation of a feedback-inhibited linear pathway demonstrates that pulsed inputs of [latex]X_1[/latex] drive production of [latex]X_4[/latex] and [latex]X_5[/latex], with feedback inhibition limiting upstream accumulation of [latex]X_1[/latex] during pulses due to [latex]X_4[/latex] suppressing the initial reaction rate.](https://arxiv.org/html/2603.19115v1/x1.png)
Researchers have developed a Julia package to simplify the construction, simulation, and analysis of complex biochemical networks using a powerful mathematical framework.