Downloads · 30 days
0
marcusvlc/3D-MRL
3D-MRL is a machine learning model from marcusvlc. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model repo provides the official pretrained models used in the paper 3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning.
Downloads · 30 days
0
Access
Public
Updated Aug 25, 2026
Repo size
4.8 GB
Likes
0
Public
Click a slice to open those files.
.pt2.9 GB · 60%
From the Hugging Face model README
This model repo provides the official pretrained models used in the paper 3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning.
You can find model usage and code in the GitHub repo.
3D-MRL is built using the awesome ULIP, Point-BERT, OpenShape, Uni3D, TAMM, MixCon3D and DuoDuo CLIP.
This work was supported in part by the São Paulo Research Foundation (FAPESP), under grants #2024/09462-1 and #2026/01721-3. The authors gratefully acknowledge the Center for Mathematical Sciences Applied to Industry (CeMEAI) for providing computational resources, funded by FAPESP under grant #2013/07375-0.