Junshu Sun

3
Papers
2
Total Citations

Papers (3)

Video Language Model Pretraining with Spatio-temporal Masking

CVPR 2025
1
citations

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

NeurIPS 2025arXiv
1
citations

Relieving the Over-Aggregating Effect in Graph Transformers

NeurIPS 2025
0
citations