Dong Wang

31

Papers

567

Total Citations

Papers (31)

GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting

NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions

SUTrack: Towards Simple and Unified Single Object Tracking

Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

Exploring Enhanced Contextual Information for Video-Level Object Tracking

Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking

EvSign: Sign Language Recognition and Translation with Streaming Events

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer

Color Event Enhanced Single-Exposure HDR Imaging

Open-Vocabulary Octree-Graph for 3D Scene Understanding

CLIP-driven View-aware Prompt Learning for Unsupervised Vehicle Re-identification

Hybrid Latent Reasoning via Reinforcement Learning

Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games

NeurIPS 2025arXiv

Efficient Motion Prompt Learning for Robust Visual Tracking

AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations

VehicleMAE: View-asymmetry Mutual Learning for Vehicle Re-identification Pre-training via Masked AutoEncoders

Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding

Anti-Tamper Protection for Unauthorized Individual Image Generation

MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation

CAT: A Unified Click-and-Track Framework for Realistic Tracking

Knowledge Graph Completion with Relation-Aware Anchor Enhancement

DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation

Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction

Box2Poly: Memory

Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

Efficient Diffusion as Low Light Enhancer

Implicit Event-RGBD Neural SLAM

Improving Transferable Targeted Attacks with Feature Tuning Mixup