NEURIPS 2025 "3d representation learning" Papers
3 papers found
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
Zihan Wang, Seungjun Lee, Gim Hee Lee
NEURIPS 2025oralarXiv:2505.11383
5
citations
Point-MaDi: Masked Autoencoding with Diffusion for Point Cloud Pre-training
Xiaoyang Xiao, Runzhao Yao, Zhiqiang Tian et al.
NEURIPS 2025poster
What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers
Yi Wang, Jiaze Wang, Ziyu Guo et al.
NEURIPS 2025poster