AI.info

He Wang

Explore He Wang on AI.info.

• Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
• S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text Understanding
• Text-guided Fine-Grained Video Anomaly Understanding
• The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
• TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking