Si Liu

Many robotic policies that seem successful in manipulation tasks actually compromise safety, with SoftVTBench revealing a stark contrast between goal completion and physical safety metrics.

Each evaluation run in EVA-Client not only assesses performance but also enriches the training dataset, creating a continuous feedback loop for policy improvement.

TopoGPT achieves a remarkable leap in lane topology reasoning, producing geometrically consistent lane graphs that outperform existing methods by substantial margins.

A novel framework enables zero-shot localization across ground and drone views, outperforming traditional methods by leveraging a rich dataset and advanced geometric modeling.