Jindong Gu

This article discusses a new benchmark for combining images and text to find events in videos.

A new benchmark evaluates language models' effectiveness in robotic applications.

A new method improves dataset distillation, enhancing model training efficiency.

This article discusses safety issues in text-to-image models and proposes solutions.

Exploring methods to improve multimodal models in breaking down visual questions.

Introducing a model that finds specific moments in long videos with ease.