Robots Learn by Playing: Building Predictive World Models Through Autonomous Exploration
New research demonstrates a system where robots autonomously explore their environment, generating the data needed to build highly accurate video world models.
Science
Beyond Physical Hallucinations: An Agent That Completes the Physics
![A fully coupled simulation, incorporating an autonomous mechanism activated upon detection of low De numbers, successfully stabilized the effective stress path and prevented falsely predicted rock fracture-arresting stress reduction at [latex] p^{\prime}=8.9 \text{ MPa} [/latex]-whereas a model constrained to undrained conditions drove the path directly into the failure zone, demonstrating the essential role of diffusive dissipation in preserving qualitative physical correctness.](https://arxiv.org/html/2603.09756v1/phase3_stress_path_comparison.png)
Researchers have developed an AI agent capable of autonomously formulating and solving multi-physics problems by reasoning about known physical laws, leading to more accurate and reliable simulations.
Giving Robots a Human Touch: Mastering Dexterous Control
Researchers have developed a comprehensive framework to transform a commercial robotic hand into a high-performance platform for advanced manipulation tasks.
AI and Qualitative Insights: A Cautious Outlook for Software Engineering
A new review examines the promise and limitations of using generative AI tools to analyze qualitative data in software engineering research.
Caterpillar-Inspired Robot Navigates Tight Spaces
Researchers have developed a flexible, spring-based robot modeled after caterpillar locomotion for effective exploration of confined environments.
Beyond Search: How AI and Vector Databases Fuel Each Other
A new synergy between artificial intelligence and vector search is unlocking powerful capabilities in information retrieval and generative AI.
Making Sense of AI: How Creative Communities Teach Themselves
New research reveals that understanding artificial intelligence isn’t about formal education, but about hands-on experimentation and shared learning within online creative spaces.
Watching and Learning: Human Video Guides Next-Gen Robot Control
![ZeroWBC orchestrates human motion through a two-stage process-first predicting sequences of movement tokens from images and text using a [latex]VQ-VAE[/latex] and a refined [latex]Qwen2.5-VL[/latex] model, then refining and sustaining these motions via an reinforcement learning policy guided by progressively challenging curriculum learning-a design acknowledging that even the most sophisticated systems ultimately navigate inherent limitations in long-term predictability and control.](https://arxiv.org/html/2603.09170v1/x1.png)
Researchers have developed a new framework that enables humanoid robots to learn complex, natural movements simply by observing human egocentric video.
Uncovering Hidden Equations: AI Finds Stochastic Dynamics
![The research introduces a method for discovering interpretable stochastic differential equations directly from observed time series data through genetic programming, optimizing both the drift [latex] f(x) [/latex] and diffusion [latex] g(x) [/latex] terms via tree-based adaptation-including crossover, exemplified by subtree exchange, and mutation of operators-to model the dynamics of stochastic systems.](https://arxiv.org/html/2603.09597v1/x1.png)
Researchers have developed a new artificial intelligence technique that automatically discovers the underlying equations governing complex, random systems.
Simulating Humans to Build Better Robots
A new framework uses detailed human modeling and artificial intelligence to design robots that interact with people more naturally and effectively.