Zhenyu Wu
2 papers · Latest:
Computer Vision
DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency
DINORANKCLIP enhances vision-language pretraining by integrating a DINOv3 teacher for local structure and a novel high-order ranking consistency loss.
2605.06592
RoboticsDockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation
DockAnywhere improves mobile manipulation policy generalization by generating diverse demonstrations from a single one, decoupling base motions from manipulation skills.
2604.15023
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.