today local_bar

Jilin Mei

MS student, Fudan University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D

#116 · Jiahui Zhang, Yurui Chen, Yueming Xu, Ze Huang, Jilin Mei, Junhui Chen, Yanpeng Zhou, Yu-Jie Yuan, Xinyue Cai, Guowei Huang, Xingyue Quan, Hang Xu, Li Zhang

We introduce SPAR-7M and SPAR-Bench, a large-scale 2D-supervised dataset and benchmark for spatial reasoning, built using 3D ground-truth.