Fei Wang

This work proposes QUALS, a large-scale time series corpus equilibrium framework that significantly enhances data efficiency, enabling existing models to achieve superior performance using only a small fraction of the original training data.

Clinical behavioral screening can reach a 0.59 F1 without ever exposing raw video or audio of minors, but moving from coarse screening to granular psychometric item prediction hits an immediate performance wall across current multimodal architectures.

World models no longer require fragile offline reconstruction pipelines—baking native physics, depth, and camera pose directly into a unified multimodal generative process unlocks self-calibrating, closed-loop 3D spatial simulation at scale.

Zeus achieves superior time series analysis performance without any task-specific tuning, challenging the norm of fine-tuning for diverse tasks.