ByteDance Seed/SimArt 模型预训练权重发布

ByteDance-Seed/SimArt

要点速览

ByteDance Seed/SimArt 模型预训练权重发布，包含用于生成关节式 3D 对象结构（URDF 文件）的多模态大语言模型（MLLM）权重，以及用于编码解码 3D 零件几何形状到离散潜在空间的稀疏 VQ-VAE 模型权重。

正文

SIMART Checkpoints

This directory contains the pretrained weights for the SIMART models.

Description: This directory contains the weights for the Multi-Modal Large Language Model (MLLM).
Base Model: Fine-tuned from Qwen3-VL-8B (or similar Qwen-VL architecture).
Purpose: Used for generating articulated 3D object structures (URDF files) based on multi-modal inputs.

Description: This directory contains the weights for the Sparse VQ-VAE model.
Purpose: Used for encoding and decoding 3D part geometries into/from discrete latent spaces.
Contents:
- encoder.pt: Weights for the VQ-VAE encoder.
- vq.pt: Weights for the Vector Quantizer (codebook).
- decoder.pt: Weights for the VQ-VAE decoder.