Paper Detail

VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis

Jinho Park, Youbin Kim, Hogun Park, Eunbyung Park

huggingface Score 24.0

Published 2026-05-21 · First seen 2026-05-25

General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@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},
  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 synthesi},
  url = {https://huggingface.co/papers/2605.22570},
  keywords = {Multimodal Large Language Models, spatio-temporal reasoning, video benchmark, generative models, multi-agent pipeline, video taxonomy, hierarchical task suite, code available, huggingface daily},
  eprint = {2605.22570},
  archiveprefix = {arXiv},
}

Metadata

{}