Bo Wu

LLMs trained on raw code text learn surface-level cues that trigger false positives when detecting vulnerabilities in other languages, but simply feeding them ASTs at inference time can dramatically reduce these errors.

Achieve faster, more accurate turn-taking in spoken dialogue by fusing streaming speech recognition with raw audio cues – even when it's noisy.

Achieve kilometer-scale regional weather forecasts that significantly outperform operational NWP and AI baselines by intelligently coupling global and regional models.