Metraipolis › archive › dc_40bb5d972ec5

VGI-Bench: Probing Visual Intelligence in Video Generation Models — arXiv:2608.19583

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19583
License (as archived)
CC0-1.0
Archived
2026-10-18T12:04:34.232Z
SHA-256 of the archived text
141e644660fa26a0611dc042c6f1670f4319cc6bd147d63fe3cdacb0c23b7957
Stable URL of this page
https://metraipolis.com/documento/dc_40bb5d972ec5

How to cite

VGI-Bench: Probing Visual Intelligence in Video Generation Models — arXiv:2608.19583 — arXiv (en), https://arxiv.org/abs/2608.19583 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40bb5d972ec5 (Metraipolis archive dc_40bb5d972ec5, sha256 141e644660fa26a0611dc042c6f1670f4319cc6bd147d63fe3cdacb0c23b7957)
BibTeX
@misc{dc40bb5d972ec5,
  title = {VGI-Bench: Probing Visual Intelligence in Video Generation Models — arXiv:2608.19583},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19583},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40bb5d972ec5; sha256 141e644660fa26a0611dc042c6f1670f4319cc6bd147d63fe3cdacb0c23b7957},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19583. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains challenging: benchmarks should adopt inputs aligned with the visual priors of current video models, require valid evolving processes rather than only plausible final states, and calibrate task difficulty to remain challenging yet partly feasible. To this end, we introduce VGI-bench, containing 27 tasks and 810 instances, organized by a two-level taxonomy of task domains and skill tags for fine-grained evaluation of visual reasoning capabilities of video generation models. Our evaluations show that current generative systems can solve a subset of visually grounded reasoning tasks, but remain far from reliable, with even the strongest model, Seedance 2.0, achieving only 51.0% under our evaluation criteria. Our analysis further explore the output failure modes, input condition sensitivity, performance transfer boundary from synthetic fine-tuning, and internal denoising perspective revealing limited self-correction, where later steps mainly refine early hypotheses rather than correct reasoning errors. We hope VGI-bench will help stimulate the development of next-generation video generation models. Website: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.19583 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T12:01:57.700Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).