← 研踪 PaperTrailarXiv:2501.16698 · v3
3D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action Generation
首次提交 2025-01-28 12:31
版本更新 2026-11-16 17:43
雷达观测 2026-11-17 17:11
摘要
Spatial intelligence, encompassing 3D perception and reasoning, is the essential next frontier of AI. Scaling current 3D vision-language models (VLMs) that rely on dense Transformers for spatial tasks incurs prohibitive computational costs. In this paper, we introduce 3D-MoE, a 3D VLM leveraging an efficient mixture-of-experts architecture with a modality- and spatial-context-aware probabilistic routing scheme, stably cultivated by a novel routing curriculum. To seamlessly extend 3D-MoE to embodied AI, we integrate a diffusion-based action head, Pose-DiT, transforming 3D-MoE into a 3D vision-language-action (VLA) model. By employing a rectified flow framework, Pose-DiT generates precise 6D pose actions in a single sampling step. Extensive experiments demonstrate that 3D-MoE achieves superior performance on diverse 3D vision-language benchmarks with drastically fewer activated parameters and yields higher success rates while enabling real-time inference for robot manipulation tasks. Code is available at https://github.com/yueen-ma/3D-MoE.
作者备注:Accepted to EMNLP 2026. 20 pages
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-16 17:43 · 最新观测版本
3D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action Generation
Spatial intelligence, encompassing 3D perception and reasoning, is the essential next frontier of AI. Scaling current 3D vision-language models (VLMs) that rely on dense Transformers for spatial tasks incurs prohibitive computational costs. In this paper, we introduce 3D-MoE, a 3D VLM leveraging an efficient mixture-of-experts architecture with a modality- and spatial-context-aware probabilistic routing scheme, stably cultivated by a novel routing curriculum. To seamlessly extend 3D-MoE to embodied AI, we integrate a diffusion-based action head, Pose-DiT, transforming 3D-MoE into a 3D vision-language-action (VLA) model. By employing a rectified flow framework, Pose-DiT generates precise 6D pose actions in a single sampling step. Extensive experiments demonstrate that 3D-MoE achieves superior performance on diverse 3D vision-language benchmarks with drastically fewer activated parameters and yields higher success rates while enabling real-time inference for robot manipulation tasks. Code is available at https://github.com/yueen-ma/3D-MoE.
查看此版本解读 →查看此版本原文 ↗