Danyang Zhang

HarmVideoBench reveals that existing benchmarks miss critical layers of harmful video understanding, while a new method boosts model accuracy by over 20%.

State-of-the-art image-to-video models are alarmingly vulnerable to visual prompt attacks, achieving up to 100% success in triggering harmful outputs.

A 1000x larger video reasoning dataset reveals early signs of emergent generalization, offering a new foundation for training and evaluating spatiotemporal AI.