Yike Guo

New methods for training large language models more efficiently emerge.

CoCoGesture creates lifelike gestures that match spoken words, enhancing interaction.

Explore how large language models enhance creativity through multimedia generation.

A new method to create music that fits video content effectively.

A new method improves the search for mathematical expressions from data.

Honest Computing emphasizes trust and ethics in data handling.

MMTrail combines visual and audio descriptions for better video-language models.

This study examines how well LLMs understand and generate music.

A new method enhances language models for better performance and lower resource use.

NoRA offers a smarter way to adapt large models with fewer resources.

X-Codec improves audio generation by integrating semantic understanding into processing.

New models improve speed and accuracy of wildfire forecasts.

A new method offers improved 3D modeling from just one image, enhancing realism.

New predictive tool enhances wildfire management and response strategies.

Researchers develop new model for lively singing videos, enhancing animations.