Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 51

Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs

Sanghwan Kim ⋅ Rui Xiao ⋅ Stephan Alaniz ⋅ Yongqin Xian ⋅ Zeynep Akata

Keywords: Video Understanding, Generation and Multimodal Learning