Beyond Clicks: Learning User Intent for Smarter Desktop Automation
A new framework, IntentCUA, bridges the gap between raw user actions and high-level goals, enabling more robust and efficient automation of complex computer tasks.
Science
Simulating Smarter Policies: Optimizing Agent-Based Models for Environmental Challenges
A new framework leverages Bayesian optimization to efficiently refine policies within complex simulations, offering a powerful tool for addressing real-world environmental issues.
Mastering Tools Without Training: A New Approach to Robotic Dexterity
Researchers have developed a novel framework that enables robots to manipulate unfamiliar tools and complete tasks without task-specific training data.
Beyond Prediction: Reframing Time Series with Dynamical Systems
A new perspective on time series analysis argues that understanding the underlying system dynamics, rather than simply forecasting future values, is crucial for robust and generalizable models.
From Steel to Softness: Bridging the Grasp Gap for Robots
![The Conditional Flow Matching (CFM) framework synthesizes grasps by learning a continuous transformation-guided by a conditional velocity field [latex]\mathbf{v}_{\theta}[/latex]-from initial rigid poses generated by Anygrasp [latex]\mathcal{G}_{\text{Anygrasp}}[/latex] to target soft gripper poses [latex]\mathcal{G}_{\text{CFM}}[/latex], a process parameterized by a feed-forward MLP and conditioned on scene geometry encoded by a U-Net autoencoder into a latent vector.](https://arxiv.org/html/2602.17110v1/x2.png)
New research demonstrates a method for transferring grasp planning from traditional rigid robot grippers to the more versatile, but challenging, domain of soft robotics.
Ask and Verify: Smarter SQL Queries with Agentic Data Exploration
A new framework, APEX-SQL, improves the accuracy of converting natural language questions into database queries by actively learning and validating its assumptions about the underlying data.
Robots Learn by Watching: Building Task Models from Limited Examples
A new approach enables robots to infer complex tasks by observing just a few demonstrations, focusing on how objects relate and change during execution.
Symmetry’s Guiding Hand: AI Predicts Stable Materials with Unprecedented Accuracy
A new generative AI framework harnesses the power of crystal symmetry to dramatically improve the prediction of stable and novel materials.
Seeing is Sensing: A 3D-Printed Optical Sensor for Soft Robotics
Researchers have developed a new soft optical sensor with an integrated lens, enabling improved light control and precision in mechanosensing applications.
Trusting the Machine: Balancing Oversight and Autonomy
As increasingly complex AI agents take on critical tasks, ensuring effective human oversight becomes paramount, but constant monitoring isn’t scalable.