PPaperPicks

Wei Wu

12 papers at tracked venues · 11 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. AirScape: An Aerial Generative World Model with Motion Controllability
  2. DriveScape: High-Resolution Driving Video Generation by Multi-View Feature Fusion
    CVPR 2025 · Wei Wu
  3. FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers
  4. GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-Based Transformer
  5. InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation
  6. RoboScape: Physics-informed Embodied World Model
  7. RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments
  8. UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection
  9. DreamLIP: Language-Image Pre-training with Long Captions
  10. HoloVic: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative
  11. SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
    NeurIPS 2024 · Wei Wu
  12. SwiftPillars: High-Efficiency Pillar Encoder for Lidar-Based 3D Detection