Jinxin Zhou

From Compression to Expression: A Layerwise Analysis of In-Context Learning

Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation

Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity

Spatial Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation

GENERALIZATION, ROBUSTNESS AND ADAPTABILITY OF PROGRESSIVE NEURAL COLLAPSE