Jinyu Yang

5

Papers

13

Total Citations

Papers (5)

X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs

OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization

CoLLM: A Large Language Model for Composed Image Retrieval

Harnessing Language Model for Cross-Heterogeneity Graph Knowledge Transfer

Depth-Aware Concealed Crop Detection in Dense Agricultural Scenes