PPaperPicks

Jianke Zhu

21 papers at tracked venues · 13 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding
  2. DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
  3. GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models
  4. Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning
  5. LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion
  6. MambaMap: Online Vectorized HD Map Construction using State Space Model
  7. PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance
  8. PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
  9. Reliable and Calibrated Semantic Occupancy Prediction by Hybrid Uncertainty Learning
  10. SAM4D: Segment Anything in Camera and LiDAR Streams
  11. ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression
  12. Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction
  13. VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
  14. Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering
  15. HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenes
  16. HVOFusion: Incremental Mesh Reconstruction Using Hybrid Voxel Octree
  17. Label-efficient Semantic Scene Completion with Scribble Annotations
  18. Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models
  19. MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction
  20. Not All Voxels are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation
  21. Osprey: Pixel Understanding with Visual Instruction Tuning