Hengshuang Zhao

ACE-Brain-0.5 unifies spatial reasoning and action generation in embodied AI, achieving remarkable performance improvements across multiple benchmarks.

Tactile-WAM achieves a remarkable 38.9% improvement in action success rates by effectively managing tactile information in robot decision-making.

EO-WM achieves unprecedented accuracy in forecasting vegetation response to extreme weather, outperforming traditional models by effectively modeling uncertainty and cumulative stress.

FlowR2A unifies dense reward supervision and dynamic proposal generation, achieving state-of-the-art multimodal driving planning performance.

Rapidly prototype and benchmark robotic navigation scenarios using simple YAML configurations, eliminating the coding barrier in simulation.