Xikun Zhang

Training-time data augmentation can slash validation loss in language model pretraining, making it feasible to train effectively on limited datasets for hundreds of epochs.

Collective Skill Tree Search transforms LLMs into versatile agents capable of mastering complex tasks through a structured skill tree that enhances their adaptability and performance.

VLMs often rely on misleading visual cues instead of true chronological understanding, revealing critical flaws in their reasoning capabilities.