Multiple papers accepted by top conferences including NeurIPS 2025, ICCV 2025, and CVPR 2025. Some notable publications include:
- '3EED: Ground Everything Everywhere in 3D' accepted by NeurIPS 2025
- 'Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras' accepted by NeurIPS 2025, Spotlight (3.2%)
- 'GA-MonoSSC: Global-Aware Monocular Semantic Scene Completion with State Space Models' accepted by ICCV 2025
- 'SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding' accepted by CVPR 2025
- 'TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation' accepted by CVPR Workshop on Autonomous Driving, 2024
- 'An Examination of the Compositionality of Large Generative Vision-Language Models' accepted by NAACL 2024
Research Experience
Involved in multiple research projects such as SeeGround, 3EED, and Talk2Event.
Education
The Hong Kong University of Science and Technology (Guangzhou campus), PhD student, Advisor: Prof. Junwei Liang, Field: AI Thrust
Background
PhD student in AI Thrust at The Hong Kong University of Science and Technology (Guangzhou campus), advised by Prof. Junwei Liang. Current research focuses on 3D scene understanding and embodied AI.
Miscellany
Personal interests and other information not provided