Yifei Liu

This paper proposes MOCO, a novel diffusion-based framework capable of processing multiple simultaneous inputs, including speech audio, text descriptions, and trajectory data, to generate coherent and lifelike motions without requiring aligned multimodal data.

Ecdysis is proposed, an efficient and effective framework that distinguishes model-specific accommodation from harness-level repair and biases adaptation toward systematic harness deficiencies by identifying recurring cross-task failure patterns.

Current AI-generated videos that mislead viewers are also the most challenging for existing detection systems to identify, revealing a critical vulnerability in misinformation defenses.