 MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning SegmentationFoundations and Trends® in Signal Processing (FTSP), 2025 |
 LESS: Label-Efficient and Single-Stage Referring 3D SegmentationNeural Information Processing Systems (NeurIPS), 2024 |
 A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances,
and Future DirectionsIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024 |
 OccuSeg: Occupancy-aware 3D Instance SegmentationComputer Vision and Pattern Recognition (CVPR), 2020 |
