Zuhao Yang

StreamOPD achieves near teacher-level performance in streaming video understanding without relying on memory or retrieval, reshaping the landscape of post-training techniques.

Atomic visual perception in MLLMs is largely unsolved, with no model surpassing 60% accuracy on a new benchmark designed to isolate perceptual capabilities.

Kimi K3's innovative architecture achieves a 2.5x scaling efficiency improvement, enabling robust performance across diverse long-horizon tasks.