Zijia Zhao
4
papers
14
total citations
papers (4)
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
ICLR 2025arXiv
14
citations
Efficient Motion-Aware Video MLLM
CVPR 2025arXiv
0
citations
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
CVPR 2024arXiv
0
citations
VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
NeurIPS 2023arXiv
0
citations