Song Wang

20

Papers

97

Total Citations

Papers (20)

Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning

Reasoning of Large Language Models over Knowledge Graphs with Super-Relations

Bidirectional Autoregessive Diffusion Model for Dance Generation

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

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

Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective

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

Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration

Monocular Semantic Scene Completion via Masked Recurrent Networks

Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction

BrainMAP: Learning Multiple Activation Pathways in Brain Networks

Tuning-Free Accountable Intervention for LLM Deployment – a Metacognitive Approach

Orthogonal Dictionary Guided Shape Completion Network for Point Cloud

Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation

From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration

The Source Image is the Best Attention for Infrared and Visible Image Fusion

MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction

SAM4D: Segment Anything in Camera and LiDAR Streams

DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation

Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning