Metraipolis › archive › dc_ebaf4b1d3199

MLLM-Guided Semantic Correction for Text-to-Video Generation — arXiv:2608.16513

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16513
License (as archived)
CC0-1.0
Archived
2026-10-18T18:07:18.469Z
SHA-256 of the archived text
244b15cbd7b50de458e400cfb00580960f7c119355e5a7929b800e84c20917e0
Stable URL of this page
https://metraipolis.com/documento/dc_ebaf4b1d3199

How to cite

MLLM-Guided Semantic Correction for Text-to-Video Generation — arXiv:2608.16513 — arXiv (en), https://arxiv.org/abs/2608.16513 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebaf4b1d3199 (Metraipolis archive dc_ebaf4b1d3199, sha256 244b15cbd7b50de458e400cfb00580960f7c119355e5a7929b800e84c20917e0)
BibTeX
@misc{dcebaf4b1d3199,
  title = {MLLM-Guided Semantic Correction for Text-to-Video Generation — arXiv:2608.16513},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16513},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebaf4b1d3199; sha256 244b15cbd7b50de458e400cfb00580960f7c119355e5a7929b800e84c20917e0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16513. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation. However, these models often suffer from semantic errors such as missing objects, incorrect attributes, or mismatched actions. Although some semantic correction methods perform optimization before sampling or refinement after sampling, how to detect and correct semantic deviations during the video generation process remains underexplored. In this paper, we introduce a training-free, interpretable mid-generation correction framework that integrates multimodal large language model (MLLM) feedback directly into the diffusion sampling loop. Our framework achieves diffusion trajectory correction by injecting semantic evaluation signals during video synthesis, enabling the model to optimize the generated content through continuous self-reflection. We propose two key modules: a Semantic Assessment Supervisor that generates intermediate preview frames for semantic evaluations and deviation diagnostics, and a Semantic Modification Assistant that corrects semantic drift during inference via a controllable latent trajectory intervention. Our method improves semantic alignment, visual fidelity, and temporal consistency without modifying model parameters. We validate the effectiveness of our approach through extensive experiments across multiple benchmarks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16513 — 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 2026-10-18T16:29:14.125Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).