Wenjie Liu

Integrating vision and radar data can drastically enhance the quality of point clouds, improving detection accuracy in challenging environments.

By leveraging frequency domain analysis, this approach significantly enhances the robustness of 3D perception systems against diverse driving conditions without needing target-domain samples.

Achieve 92% fewer transmissions in UAV obstacle avoidance by intelligently selecting which sensing and control signals to send, without sacrificing task success.

Control diffusion models with physically-based rendering parameters by reformulating Monte Carlo integration as a stochastic differential equation.