Wenhu Chen

New methods improve machines' ability to create images from textual prompts.

A new system that connects music and language for better understanding.

RG-LCD enhances image generation from text, aligning with human preferences effectively.

A new framework simplifies video editing tasks using image editing tools.

New dataset improves model performance on multi-image tasks.

Research reveals a new method for faster, high-quality video creation from text.

MAP-Neo aims for transparency and performance in AI language modeling.

MMLU-Pro challenges language models with harder questions and more answer options.

Researchers enhance how machines comprehend long and high-resolution videos.

A method to verify information sources visually and enhance trust online.