English(EN)From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence
新模型和框架推动具身AI能力发展
作者PulseAugur 编辑部·[14 个来源]·
研究人员正在开发先进的模型和框架，以实现更具能力的具身人工智能。一种方法是Athena-Brain-8B，一个为设备端机器人大脑设计的8B LLM，展现出强大的通用智能和具身交互能力，并能给出简洁的响应。另一篇论文探讨了Edmund Berkeley和David L. Heiserman的历史工作，将其视为一个未被充分探索的具身智能架构，将逻辑与硬件和时间扩展行为联系起来。此外，一个1.5B的开源VLA模型MiniCPM-Robot，在操作和跟踪任务中表现出色，即使在低网络环境下也是如此，并且是PhyAI推理框架等更大生态系统的一部分。
AI
arXiv:2607.18985v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, there is a growing demand for compact models that can …
arXiv cs.AI
TIER_1English(EN)·Christopher A. Tucker·
arXiv:2607.16465v1 Announce Type: new Abstract: Edmund C. Berkeley is usually remembered as a writer who helped connect symbolic logic to computing machinery. That description is correct, but incomplete. Read across Berkeley's machine-oriented writings and projects, the central c…
Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-level structured annotations, and reusable tools for robot learning. We present Open-AoE, an open, commu…
Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have advanced this goal, while World Action Models (WAMs) are particularly promising because they connect can…
arXiv:2607.19876v1 Announce Type: cross Abstract: Evaluating the physical consistency of embodied world models(EWMs) is a critical open challenge. While closed-loop evaluation via simulator rollouts offers a more faithful assessment of physical plausibility than open-loop alterna…
arXiv:2607.18062v1 Announce Type: cross Abstract: This paper focuses on the problem of Embodied Task Planning, where an agent is required to execute a sequence of atomic actions within an interactive environment to complete a user-specified task. Though a variety of simulators an…
Tencent open-sources three embodied models at WAIC 2026: VLM for scene understanding, RxBrain cognitive model for planning with visual states, and VLA for continuous action at 500-1000Hz.
Youibot FabriVLA achieves 90.0% tier-average on Meta-World MT50 with just 1B parameters, surpassing Pi-Zero, as the industrial robot maker also debuts Fengxi humanoid robot with 4,000 unit orders.
Horizon Robotics affiliate Digua Robot announces Sunri S600 platform milestones as 2026 becomes embodied intelligence mass production year, addressing the three chasms of model-on-robot deployment.
