Jian Chen

By unifying specialized detectors with flexible reasoning, Echo-α achieves state-of-the-art ultrasound interpretation, suggesting a path toward more accurate and interpretable medical AI.

LLM agents can be made more reliable by structurally verifying their internal reasoning, rather than relying on consensus which conflates agreement with faithfulness.

Forget one-to-one video segment alignments: this new framework leverages global video context to significantly improve multimodal translation, especially for long videos.