Lingdong Kong
- 3EED: Ground Everything Everywhere in 3D
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies
- MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
- Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding
- Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras
- VideoLucy: Deep Memory Backtracking for Long Video Understanding