Hailing Wang

Dual-branch fusion models can significantly enhance event recognition in distributed acoustic sensing, achieving nearly 90% accuracy while minimizing false alarms.

Unimodal models might already understand each other better than we thought: a shared relational structure, formalized via category theory, unlocks zero-shot cross-modal alignment.

Achieve real-time (76 FPS) HDR novel view synthesis with significantly improved reconstruction of high dynamic range details by explicitly modeling scene reflectance and illumination.