| title | VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis |
|---|---|
| authors | Jinho Park, Youbin Kim, Hogun Park, Eunbyung Park |
| date | 2026-05-21 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.22570 |
| upvotes | 20 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential challenge. However, existing spatio-temporal reasoning benchmark datasets primarily rely on static image sets or passively curated video data, which limits the evaluation of fine-grained reasoning capabilities. In this paper, we introduce VGenST-Bench, a video benchmark that employs generative models to actively synthesize highly controlled and diverse evaluation scenarios. To construct VGenST-Bench, we propose a multi-agent pipeline incorporating a human quality control stage, ensuring the quality of all generated videos and QA pairs. We establish a comprehensive 3x2x2 video taxonomy, encompassing Spatial Scale, Perspective, and Scene Dynamics to span diverse scenarios. Furthermore, we design a hierarchical task suite that decouples low-level visual perception from high-level spatio-temporal reasoning. By shifting the paradigm from passive curation to active synthesis, VGenST-Bench enables fine-grained diagnosis of spatio-temporal understanding in MLLMs. |
cite
@misc{park2026vgenst,
title={VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis},
author={Jinho Park and Youbin Kim and Hogun Park and Eunbyung Park},
year={2026},
eprint={2605.22570},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.22570}
}