Jinsong Lan

5

Papers

69

Total Citations

Papers (5)

Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignment

Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models

Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training

Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling