Xiaoyang Wu

16

Papers

255

Total Citations

Papers (16)

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

GPT4Point: A Unified Framework for Point-Language Understanding and Generation

Sonata: Self-Supervised Learning of Reliable Point Representations

Multi-Space Alignments Towards Universal LiDAR Segmentation

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning

NeurIPS 2025arXiv

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

Understanding Imbalanced Semantic Segmentation Through Neural Collapse

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Point Transformer V3: Simpler Faster Stronger

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling