Junwei Liang

Assistant Professor, Hong Kong University of Science and Technology

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

3EED: Ground Everything Everywhere in 3D

#4603 · Rong Li, Yuhao Dong, Tianshuai Hu, Alan Liang, Youquan Liu, Dongyue Lu, Liang Pan, Lingdong Kong, Junwei Liang, Ziwei Liu

We present 3EED, the first large-scale benchmark for 3D visual grounding across vehicles, drones, and quadrupeds, with over 134K 3D objects and 25K human-verified expressions in diverse outdoor scenes.

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization

#2406 · Jiaming Zhou, Ke Ye, Jiayi LIU, Teli Ma, Zifan Wang, Ronghe Qiu, Kun-Yu Lin, Zhilin Zhao, Junwei Liang

Proposing a zero-shot cross-task manipulation generalization benchmark and a novel generalizable VLA method.