PPaperPicks

Deng Cai

Zhejiang University, College of Computer Science, State Key Laboratory of CAD&CG, Hangzhou, China

20 papers at tracked venues · 18 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Enhancing Spatial Reasoning Through Visual and Textual Thinking
  2. Controlling Thinking Speed in Reasoning Models
  3. Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
  4. FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
  5. GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
  6. Magicid: Hybrid Preference Optimization for Id-Consistent and Dynamic-Preserved Video Customization
  7. PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation
  8. STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction
  9. TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
  10. Towards Label-Free 3D Visual Grounding with Vision Foundation Models
  11. Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
  12. From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
  13. G2LTraj: A Global-to-Local Generation Approach for Trajectory Prediction
  14. Learning Occupancy for Monocular 3D Object Detection
  15. Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-Dataset 3D Object Detection
  16. Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving
  17. Semi-supervised 3D Object Detection with PatchTeacher and PillarMix
  18. TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation
  19. TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training
  20. Towards Fine-Grained HBOE with Rendered Orientation Set and Laplace Smoothing