Tianyun Zhang

Scaling reasoning and pretraining loss does not buy self-awareness: top models beat human averages overall yet still fail markedly at metacognition, proving awareness is an independent capability axis.

Static labels in medical AI are giving way to dynamic models that can simulate disease evolution and guide personalized interventions.

By generating synthetic gradients to bridge gaps between sparse benign updates, EnCAgg recovers more clean data in federated learning, even under dynamic model poisoning.