Hao Zhao

4 papers Tsinghua University, Tsinghua University

• Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
• OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
• SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models
• Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting