arXiv 2026 ยท preprint

BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender

Figure: BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender

Yolo Y. Tang, Daiki Shimada, Jiayue Meng, Jing Bi, Pinxin Liu, Yicheng Wang, Yunzhong Xiao, Zhangyun Tan, Zeliang Zhang, Chao Huang, Susan Liang, Qianxiang Shen, Luchuan Song, Ali Vosoughi, Mingqian Feng, Melika Filvantorkaman, Chenliang Xu

Benchmark for agentic video understanding via programmatic reconstruction of 288 real indoor videos in Blender, scored by dual VQA and latent similarity across 51 agent configurations from 10 model families.

Paper Code Project page

Benchmark for agentic video understanding via programmatic reconstruction of 288 real indoor videos in Blender, scored by dual VQA and latent similarity across 51 agent configurations from 10 model families.

All publications