"video comprehension" Papers
3 papers found
HoliTom: Holistic Token Merging for Fast Video Large Language Models
Kele Shao, Keda TAO, Can Qin et al.
NeurIPS 2025oralarXiv:2505.21334
18
citations
Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
Shaojie Zhang, Jiahui Yang, Jianqin Yin et al.
ICCV 2025posterarXiv:2506.22139
23
citations
Temporal Reasoning Transfer from Text to Video
Lei Li, Yuanxin Liu, Linli Yao et al.
ICLR 2025oralarXiv:2410.06166
20
citations