Chuang Gan

A new model improves efficiency in handling diverse vision tasks.

A new approach to improve agent decision-making in complex environments.

MultiPLY enhances language models through interactive multisensory data processing in 3D environments.

Introducing a dataset to test AI's understanding of physical interactions with soft bodies and liquids.

Innovative tactile simulators enhance robot object handling skills.

This article explores how teaching AI with easy tasks leads to better performance.

This article explores using LLMs and simulations to enhance scientific research.

A new method creates stable 3D objects from images, maintaining appearance and structure.

A new approach to combine singing and dance through advanced computer techniques.

A new benchmark tests compositional reasoning in advanced models.

A new method helps robots find fallen objects using sound.

A cost-effective approach for analyzing high-resolution images and text.

This model predicts object movement and analyzes video content effectively.

Innovative method combines 2D images with depth to design realistic 3D spaces.

Video Curious Agent simplifies finding key moments in lengthy videos.