HY-Embodied-0.5：面向现实世界代理的具身基础模型
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
AI总结：
本文提出HY-Embodied-0.5，旨在提升现实世界代理的具身智能能力，通过混合Transformer架构和迭代自演化训练方法，实现高效和强大的模型变体，验证了其在多个基准测试中的优越性能。
摘要：
我们介绍了HY-Embodied-0.5，一组专为现实世界具身代理设计的基础模型。为弥合通用视觉语言模型（VLMs）与具身代理需求之间的差距，我们的模型增强了具身智能所需的核心能力：空间和时间视觉感知，以及高级具身推理能力。HY-Embodied-0.5系列包含两个主要变体：一个具有200亿激活参数的高效模型，适用于边缘部署；另一个具有3200亿激活参数的模型，专为复杂推理设计。为支持具身任务所需的细粒度视觉感知，我们采用混合Transformer（MoT）架构以实现模态特定计算。通过引入潜在令牌，此设计有效增强了模型的感知表示。为提高推理能力，我们引入了迭代、自我进化的训练范式。此外，我们采用on-policy蒸馏将大模型的先进能力转移到小模型，从而最大化紧凑模型的性能潜力。在22个基准测试中的广泛评估显示了我们方法的有效性。我们的MoT-2B模型在16个基准测试中优于同样规模的最新模型，而32B变体的性能与前沿模型如Gemini 3.0 Pro相当。在下游机器人控制实验中，我们利用我们稳健的VLM基础来训练一个有效的视觉-语言-动作（VLA）模型，在现实世界的物理评估中取得了令人印象深刻的结果。代码和模型在https://github.com/Tencent-Hunyuan/HY-Embodied上开源。
英文摘要：
We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents. To bridge the gap between general Vision-Language Models (VLMs) and the demands of embodied agents, our models are developed to enhance the core capabilities required by embodied intelligence: spatial and temporal visual perception, alongside advanced embodied reasoning for prediction, interaction, and planning. The HY-Embodied-0.5 suite comprises two primary variants: an efficient model with 2B activated parameters designed for edge deployment, and a powerful model with 32B activated parameters targeted for complex reasoning. To support the fine-grained visual perception essential for embodied tasks, we adopt a Mixture-of-Transformers (MoT) architecture to enable modality-specific computing. By incorporating latent tokens, this design effectively enhances the perceptual representation of the models. To improve reasoning capabilities, we introduce an iterative, self-evolving post-training paradigm. Furthermore, we employ on-policy distillation to transfer the advanced capabilities of the large model to the smaller variant, thereby maximizing the performance potential of the compact model. Extensive evaluations across 22 benchmarks, spanning visual perception, spatial reasoning, and embodied understanding, demonstrate the effectiveness of our approach. Our MoT-2B model outperforms similarly sized state-of-the-art models on 16 benchmarks, while the 32B variant achieves performance comparable to frontier models such as Gemini 3.0 Pro. In downstream robot control experiments, we leverage our robust VLM foundation to train an effective Vision-Language-Action (VLA) model, achieving compelling results in real-world physical evaluations. Code and models are open-sourced at https://github.com/Tencent-Hunyuan/HY-Embodied.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
