Lumin Xu

6

Papers

167

Total Citations

Papers (6)

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

F-LMM: Grounding Frozen Large Multimodal Models

Ultra-High Resolution Segmentation via Boundary-Enhanced Patch-Merging Transformer

UniFS: Universal Few-shot Instance Perception with Point Representations

Unsupervised Continual Domain Shift Learning with Multi-Prototype Modeling