Poster Thu, Sep 10, 2026 • 7:30 AM – 9:30 AM PDT ExHall # 161

Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?

Zhaoyang Wei ⋅ Zipeng Wang ⋅ Yushe Cao ⋅ Chenhui Qiang ⋅ Shuaibing Cheng ⋅ Xuesong Yang ⋅ Sen Nie ⋅ Bowen Jiang ⋅ Wenchao Ding ⋅ Yanchao Hao ⋅ Zheng Wei ⋅ Xuehui Yu ⋅ Zhenjun Han

Keywords: Video Understanding, Generation and Multimodal Learning