Wei Wang

CORAM achieves up to 1.35 points of performance improvement in model merging, redefining the boundaries of orthogonal transformations in AI.

Delays in cloud-side inference can be effectively compensated, retaining over 80% performance in imitation-learning tasks even under significant latency.

Current AI-generated videos that mislead viewers are also the most challenging for existing detection systems to identify, revealing a critical vulnerability in misinformation defenses.