Hang Xu

6 papers Huawei Noah’s Ark Lab

• 4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
• From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D
• INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
• PandaPose: 3D Human Pose Lifting from a Single Image via Propagating 2D Pose Prior to 3D Anchor Space
• SeePhys: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning
• Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization