Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 175

GTR: Guide-Then-Refine Token Compression for Training-Free Acceleration of Video-LLMs

Sijin Zhou ⋅ wei feng ⋅ Zhuang Qi ⋅ Zhonghua Wang ⋅ Lie Ju ⋅ Xiang An ⋅ Mehrtash Harandi ⋅ Zongyuan Ge

Keywords: Video Understanding, Generation and Multimodal Learning