Weijia Shi

A new framework enhances reasoning in language models through visual sketches.

Research shows how multilingual feedback can enhance language model reliability.

Assessing strategies to manage copyright issues in language models.

Examining the trade-off between predicting text and user-driven actions in language models.

Larger datastores improve the performance and accuracy of retrieval-based language models.

Learn how Negative Token Merging is changing AI image generation.

New framework improves text and image model integration for enhanced performance.