用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/hiyenwong/ai_collection --skill unifying-von-neumann-hpc-neuromorphic-ebbrains命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Graph-native Python reimplementation of the Information Dynamics of Music (IDyOM) model that represents predictive memories as explicit graph objects for musical expectation modeling and network analysis.
Physics-aware end-to-end deep reinforcement learning methodology for quadcopter control with actuator dynamics modeling.
Reinforced Dreamer methodology for asymmetric reinforcement learning using latent guidance to improve world model representations and behaviors in model-based RL.
基于 SOC 职业分类
正在显示 SKILL.md
| name | unifying-von-neumann-hpc-neuromorphic-ebbrains |
| description | 统一冯诺依曼HPC与神经形态计算的EBRAINS工作流框架 - 透明跨平台执行SNN，支持异构架构无缝切换。 |
| version | 1.0.0 |
| author | arXiv:2606.08515 (Krishna Kant Singh et al.) |
| date | 2026-06-13T00:00:00.000Z |
| arxiv_id | 2606.08515 |
| activation_keywords | ["neuromorphic computing","von neumann hpc","ebbrains","heterogeneous architecture","snn acceleration","workflow orchestration","brain-inspired computing","transparent execution"] |
arXiv:2606.08515 - Submitted 7 June 2026
Authors: Krishna Kant Singh, Charl Linssen, Eric Müller, Eleni Mathioulaki, Wouter Klijn, Lena Oden
Categories: cs.DC
提出EBRAINS研究基础设施上的统一框架，实现冯诺依曼HPC与神经形态加速器的无缝集成，支持单一科学工作流在异构架构间透明执行。
现代科学工作流日益跨越多样计算架构:
EBRAINS统一框架:
Workflow Definition
├── Task Graph (DAG)
│ ├── HPC Tasks (传统计算)
│ ├── Neuromorphic Tasks (SNN推理)
│ └── Hybrid Tasks (混合执行)
└── Resource Mapping
├── CPU/GPU Clusters (HPC)
├── SpiNNaker/BrainScaleS (神经形态)
└── Dynamic Allocation
# Conceptual workflow
workflow = EBRAINSWorkflow()
# Define SNN model (architecture-agnostic)
snn = SpikingModel(...)
# Transparent execution
workflow.run(
model=snn,
backend='auto', # Auto-select: HPC/neuromorphic
optimization='power', # 或 'speed', 'accuracy'
)