Xiaohan Ding

Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability

Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines

RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets

What Makes for Good Visual Tokenizers for Large Language Models

From Language to 3D Worlds: Adapting Language Models for Point Cloud Perception

Towards Unified and Effective Domain Generalization

Advancing Vision Transformers with Group-Mix Attention

Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities

Prompt-Guided Dynamic Network for Image Super Resolution