Lingdong Kong

23

Papers

90

Total Citations

Papers (23)

Multi-Space Alignments Towards Universal LiDAR Segmentation

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds

GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency

Perspective-Invariant 3D Object Detection

Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations

Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

Monocular Semantic Scene Completion via Masked Recurrent Networks

VideoLucy: Deep Memory Backtracking for Long Video Understanding

NeurIPS 2025arXiv

Rethinking Range View Representation for LiDAR Segmentation

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

EventFly: Event Camera Perception from Ground to the Sky

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data and Metric Perspectives

OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies

CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase

Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Towards Label-free Scene Understanding by Vision Foundation Models