Lights Shi

Tracking text progress directly from latent speech tokens rather than rendered audio cuts alignment error by 88% while slashing compute overhead by 20x.

WALL-SS achieves unprecedented long-horizon visual simulation for robots, improving action following and trajectory accuracy while maintaining coherence over extended interactions.

X2Streaming-TTS achieves true token-level synthesis with a median time to first audio token of just 15.8 ms, outperforming traditional pseudo-streaming models in quality and responsiveness.