Yiwei Liu

Latent contextual influence can be explicitly transported and selectively realized in Transformers, enabling models to retain predictive information beyond immediate state.

DRIFT not only sets a new state-of-the-art in self-improvement for language models but also redefines how we can dynamically adapt learning strategies based on problem difficulty.

Current AI agents struggle with long-horizon professional tasks, achieving only 30% success in complex GUI workflows, revealing critical gaps in their capabilities.