MolmoAct2：面向真实世界部署的动作推理模型

MolmoAct2: Action Reasoning Models for Real-world Deployment

AI 导读

MolmoAct2 是一个为实际部署设计的全开放动作推理模型，在五个方面取得进展。其核心是专为空间与具身推理训练的 VLM 骨干 MolmoER，基于 330 万样本语料库训练。团队发布了三个新数据集，包括迄今最大开放双手数据集 MolmoAct2-BimanualYAM（720 小时遥操作轨迹），并开源了动作分词器 OpenFAST。模型采用层间 KV 缓存条件化架构，嫁接连续动作专家，还引入自适应深度推理变体 MolmoThink，以极低延迟保持几何基础。在广泛实证研究中，MolmoAct2 在 7 个仿真与真实世界基准上超越 Pi-05 等基线，MolmoER 在 13 个具身推理基准上超过 GPT-5 和 Gemini Robotics ER-1.5。模型权重、训练代码与数据均已公开。

推荐理由

开源具身动作推理模型首次全面超越 GPT-5 和 Gemini Robotics，还附赠最大的双手操作数据集和全套训练代码，做机器人的同学本周必读。

正文 · 原文

Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment. Frontier models are closed, open-weight alternatives are tied to expensive hardware, reasoning-augmented policies pay prohibitive latency for their grounding, and fine-tuned success rates remain below the threshold for dependable use. We present MolmoAct2, a fully open action reasoning model built for practical deployment, advancing its predecessor along five axes. We introduce MolmoER, a VLM backbone specialized for spatial and embodied reasoning, trained on a 3.3M-sample corpus with a specialize-then-rehearse recipe. We release three new datasets spanning low-to-medium cost platforms, including MolmoAct2-BimanualYAM, 720 hours of teleoperated bimanual trajectories that constitute the largest open bimanual dataset to date, together with quality-filtered Franka (DROID) and SO100/101 subsets. We provide OpenFAST, an open-weight, open-data action tokenizer trained on millions of trajectories across five embodiments. We redesign the architecture to graft a flow-matching continuous-action expert onto a discrete-token VLM via per-layer KV-cache conditioning. Finally, we propose MolmoThink, an adaptive-depth reasoning variant that re-predicts depth tokens only for scene regions that change between timesteps, retaining geometric grounding at a fraction of prior latency. In the most extensive empirical study of any open VLA to date, spanning 7 simulation and real-world benchmarks, MolmoAct2 outperforms strong baselines including Pi-05, while MolmoER surpasses GPT-5 and Gemini Robotics ER-1.5 across 13 embodied-reasoning benchmarks. We release model weights, training code, and complete training data. Project page: https://allenai.org/blog/molmoact2