Bingsheng He

Forget domestic data – cross-market signals hidden in annual reports can significantly boost return prediction, especially when transferring insights from the US to Japan.

LLMs can track depression severity from counseling transcripts more effectively by combining clinical signals with turn-level embeddings and symptom-specific predictors, even when dealing with limited data or longitudinal context.

Multi-agent LLM systems for idea generation can backfire, with smarter models and more communication leading to *less* diverse ideas due to structural coupling.