Xin Li

Connecting Where You Look With What You Understand: Trajectory-Driven Localized Understanding for Interactive Vision-Language Models

Norm$\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention

OVRD: Open-Vocabulary Relation DINO with Text-guided Salient Query Selection

FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation

PolaFormer: Polarity-aware Linear Attention for Vision Transformers

Learning Spatial-Semantic Features for Robust Video Object Segmentation