Yuxiang Zhao

CoEvoer achieves unprecedented accuracy in upper-body pose estimation by leveraging cross-dependencies among facial, hand, and torso features.

By reasoning about intentions across time, CiT enables more accurate trajectory prediction, especially when considering the ego-agent's own motion.

Interactive voice conversion just got real: X-VC achieves state-of-the-art streaming WER and speaker similarity with significantly lower latency by operating directly in codec space.

Achieve human-like full-duplex voice interactions with SoulX-Duplug, a plug-and-play module that slashes latency and improves turn management by acting as a semantic VAD.

Forget task-specific architectures: a single Vision-Language-Action foundation model, ABot-N0, now dominates embodied navigation across five distinct tasks.