VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting
Published in AAAI 2025, 2025
Muhammet Furkan Ilaslan, Ali Köksal, Kevin Qinghong Lin, Burak Satar, Mike Zheng Shou, Qianli Xu
Procedural planning with LLMs improves when text and video prompts are visually grounded together.
arXiv Paper (AAAI) Code Dataset
BibTeX
@inproceedings{DBLP:conf/aaai/IlaslanKLSSX25,
author = {Muhammet Furkan Ilaslan and
Ali K{\"{o}}ksal and
Kevin Qinghong Lin and
Burak Satar and
Mike Zheng Shou and
Qianli Xu},
editor = {Toby Walsh and
Julie Shah and
Zico Kolter},
title = {{VG-TVP:} Multimodal Procedural Planning via Visually Grounded Text-Video
Prompting},
booktitle = {Thirty-Ninth {AAAI} Conference on Artificial Intelligence, Thirty-Seventh
Conference on Innovative Applications of Artificial Intelligence,
Fifteenth Symposium on Educational Advances in Artificial Intelligence,
{AAAI} 2025, Philadelphia, PA, USA, February 25 - March 4, 2025},
pages = {3886--3894},
publisher = {{AAAI} Press},
year = {2025},
url = {https://doi.org/10.1609/aaai.v39i4.32406},
doi = {10.1609/AAAI.V39I4.32406},
timestamp = {Wed, 18 Mar 2026 17:07:12 +0100},
biburl = {https://dblp.org/rec/conf/aaai/IlaslanKLSSX25.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}