<?xml version="1.0" encoding="US-ASCII"?>
<dblp>
<inproceedings key="conf/cvpr/LiCWHHGWL25" mdate="2026-02-12">
<author>Hongyu Li</author>
<author>Jinyu Chen</author>
<author>Ziyu Wei</author>
<author>Shaofei Huang 0001</author>
<author>Tianrui Hui</author>
<author>Jialin Gao</author>
<author>Xiaoming Wei</author>
<author>Si Liu 0001</author>
<title>LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding.</title>
<pages>8592-8603</pages>
<year>2025</year>
<booktitle>CVPR</booktitle>
<ee type="oa">https://openaccess.thecvf.com/content/CVPR2025/html/Li_LLaVA-ST_A_Multimodal_Large_Language_Model_for_Fine-Grained_Spatial-Temporal_Understanding_CVPR_2025_paper.html</ee>
<ee>https://doi.org/10.1109/CVPR52734.2025.00803</ee>
<crossref>conf/cvpr/2025</crossref>
<url>db/conf/cvpr/cvpr2025.html#LiCWHHGWL25</url>
</inproceedings>
</dblp>
