Jingjing Wu

4

Papers

39

Total Citations

Papers (4)

MLLMs Need 3D-Aware Representation Supervision for Scene Understanding

NeurIPS 2025arXiv

Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observations

WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting

Recognition-Synergistic Scene Text Editing