Wenzhao Zheng

15

Papers

288

Total Citations

Papers (15)

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes

EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding

Path Choice Matters for Clear Attributions in Path Methods

UniDrive: Towards Universal Driving Perception Across Camera Configurations

D3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection

SpectralAR: Spectral Autoregressive Visual Generation

LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction

SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction

Segment Any Motion in Videos

Learning Counterfactually Decoupled Attention for Open-World Model Attribution

PlaneRAS: Learning Planar Primitives for 3D Plane Recovery

Authentic 4D Driving Simulation with a Video Generation Model