1
Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs
无需训练就能剪掉多余视觉token,让视频大模型推理更快、理解更细。
arXiv:2604.20937v2 Announce Type: replace Abstract: Video Large Language Models (Video LLMs) incur high inference latency due to a large number of vis…