Science

A new framework leverages the power of diffusion models to create diverse and robust policies, bridging the gap between offline data and real-world robot performance.

New research tackles the challenges of creating robust multimodal systems capable of generalizing beyond their training data and handling incomplete or misleading information.

A new approach leverages discrete representations of protein structure to efficiently generate diverse and realistic conformational ensembles, offering a fresh perspective on modeling protein dynamics.

New research reveals occupant behavior during demand response events is driven by factors extending beyond simple thermal preferences.

Researchers have developed a new framework to reliably train and evaluate AI agents’ ability to use tools without the limitations of real-world API access.

A new approach leverages the power of artificial intelligence to automatically derive accurate and understandable models of static friction for robotic systems.

Researchers have developed a deep learning framework capable of accurately modeling diverse physical systems governed by different partial differential equations.

New research demonstrates a method for rapidly teaching robots diverse manipulation skills with minimal training data.

A new system harnesses the power of artificial intelligence to build and execute complex network measurement studies, lowering the barriers to in-depth internet analysis.

Researchers have developed an untethered, shape-morphing robot capable of seamlessly transitioning between land, underwater, and surface locomotion with improved energy efficiency.