Michael Ying Yang

Uncertainty-aware fusion can dramatically improve online 3D scene graph generation, outperforming traditional methods while maintaining real-time performance.

UNIVERSE achieves a remarkable 4.3× speedup in trajectory inference while maintaining planning accuracy, revolutionizing how video dynamics inform autonomous driving actions.

Achieving state-of-the-art RRSIS performance with just 2.4% parameter updates challenges the norm of full fine-tuning in multimodal models.

Autonomous driving models can now achieve remarkable zero-shot generalization by leveraging the power of large-scale video generation models to jointly predict future actions and visuals.