Xinwei He

3

Papers

27

Total Citations

Papers (3)

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models

WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation

Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval