Menü
Skills in diesem Repository
SkillsMP hat 4.114 Skills aus hiyenwong/ai_collection gesammelt. Öffne einen Skill, um Quelle und Details zu prüfen.
hiyenwong/ai_collectionEs werden 40 von 4.114 gesammelten Skills angezeigt.
分布式优化控制架构用于逆变器接口虚拟电厂的大信号稳定性分析方法论。结合优化理论、控制理论、分布式系统设计，实现DER（分布式能源资源）的二次控制。Activation: distributed control, virtual power plant, VPP, inverter control, DER control, optimization-based control, large-signal stability.
Quellsprache: Chinesisch
Distributed Quantum Computing architecture and patterns. Apply when designing multi-QPU systems, quantum communication protocols, or scaling quantum computing beyond single device limitations.
Quellsprache: Englisch
系统工程学 + 量子计算融合模式。涵盖分布式量子计算架构、量子控制理论（H∞控制、反馈控制）、量子系统工程方法论。Activation: 分布式量子控制, quantum control systems, distributed quantum computing engineering, quantum systems engineering.
Quellsprache: Chinesisch
Design and analyze distributed quantum error correction (QEC) systems using bivariate bicycle (BB) codes in modular quantum computing architectures. Covers qLDPC code partitioning across multiple processors, star network topology for inter-processor…
Quellsprache: Englisch
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
Quellsprache: Englisch
Distribution-valued brain connectivity analysis using vector quantiles instead of scalar edge weights. Based on Mhanna, Achard, Petersen (2026, HAL). Use when building brain connectivity graphs from fMRI/EEG, improving connectome classification, or…
Quellsprache: Englisch
Dockerize Node.js pnpm workspace monorepos with native modules, multi-process runtime, and selective package builds. Triggers when containerizing Next.js/Express monorepos, writing Dockerfiles for pnpm workspaces, or handling better-sqlite3 native compilation…
Quellsprache: Englisch
Multi-objective optimization framework combining spatial relevance and functional discriminability for EEG channel selection in motor imagery BCIs
Quellsprache: Englisch
Doob-barrier-conditioned diffusion methodology that turns analog device noise into a continual-learning resource for neuromorphic hardware. Uses Doob h-transform to condition synaptic weight dynamics on never crossing memory-critical barriers, creating a…
Quellsprache: Englisch
dOPSD methodology for on-policy self-distillation in diffusion language models. Derives teacher privilege from student's own denoising trajectory rather than external labels, enabling reasoning improvement without tractable sequence likelihoods.
Quellsprache: Englisch
Dose-efficient quantum phase estimation methodology using sequential strategies in lossy optical interferometry for biological and medical imaging. Control-enhanced sequential strategies achieve superior quantum Fisher information per dose, approaching the…
Quellsprache: Englisch
Dynamic Rollout Editing (DRE) for reducing overthinking in RL-trained reasoning models. Training-time intervention that preserves verified prefixes and edits unnecessary continuation. Use when: (1) GRPO/RLVR training shows overthinking, (2) credit assignment…
Quellsprache: Englisch
梦境推理与世界行动模型：将梦境的认知重组机制应用于多模态推理，实现适应性推理策略切换。核心：Dreaming-when-Necessary机制、多模态推理适应性、长程任务规划。触发词：梦境推理、世界模型、行动规划、dreaming、多模态推理、adaptive reasoning、长程任务。
Quellsprache: Chinesisch
深度强化学习引导图神经网络脑网络分析方法论。结合DRL和GNN进行脑网络分析。适用于脑网络分类、疾病诊断。触发词：深度强化学习、图神经网络、脑网络、DRL-GNN。
Quellsprache: Chinesisch
Deep reinforcement learning for quantum optimal control. Combines DRL with quantum gate synthesis to achieve high-fidelity, high-speed quantum operations without prior heuristic ansatz. Use when: (1) Designing quantum optimal control protocols, (2) Applying…
Quellsprache: Englisch
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
Quellsprache: Englisch
Divergence Regularized Policy Optimization (DRPO) — smooth advantage-weighted quadratic regularizer replacing hard trust-region masks in LLM reinforcement learning. Use when optimizing LLM post-training with RL, improving upon GRPO/PPO/DPPO stability.
Quellsprache: Englisch
斑马鱼被盖微电路双轴归因方法论。基于斑马鱼视网膜被盖微电路的双轴功能归因（能量高效信息处理和鲁棒稳定）方法，将生物学电路组织转化为类脑神经网络架构设计。适用于脉冲神经网络、类脑架构设计、电路归因。触发词：dual-axis, 双轴归因, zebrafish tectal, microcircuit attribution, energy efficiency, robustness, ns_TIN, superficial_TIN
Quellsprache: Mehrsprachig
Dual-envelope constrained nonlinear MPC for autonomous drifting in distributed drive electric vehicles. Covers saddle point modeling, phase plane envelope construction, NMPC with envelope constraints, and extreme vehicle maneuver control. Use when working…
Quellsprache: Englisch
Dual Memory Pathway (DMP) neuromorphic network co-design methodology. Inspired by cortical fast-slow organization, combines explicit slow memory with fast spiking activity for long-timescale context. Applies to: neuromorphic computing, event-driven sensing,…
Quellsprache: Englisch
Dual-pathway architecture for provably robust learning-based control combining neural network feedforward estimation with conventional feedback correction. Use when designing learning-enabled control systems requiring both performance and robustness…
Quellsprache: Englisch
Dual-timescale memory mechanism in spiking neuron-astrocyte networks. Astrocytes provide slow-timescale modulation complementing fast spiking dynamics, enabling energy-efficient learning of environmental patterns and persistent memory traces.
Quellsprache: Englisch
Spiking Neuron-Astrocyte Network (SNAN) combining STDP-based long-term memory with astrocytic calcium-mediated short-term suppression for efficient navigation. Introduces Topological-Context Memory as a dual-timescale working memory mechanism that reduces…
Quellsprache: Englisch
Dual-timescale memory mechanism in spiking neuron-astrocyte networks (SNAN). Combines STDP-based long-term memory with astrocytic short-term suppression for efficient navigation and working memory. Activation: dual timescale memory, SNAN, spiking neuron…
Quellsprache: Englisch
Dual-timescale memory mechanism in spiking neuron-astrocyte networks for efficient navigation. Models complementary learning systems: long-term memory via astrocytic regulation + short-term suppression via spike-frequency adaptation. Use for neuromorphic…
Quellsprache: Englisch
Dynamic Gated Neuron (DGN) - Biologically plausible gating mechanism for Spiking Neural Networks via dynamic membrane conductance modulation. Enables selective input filtering and adaptive noise suppression. Activation triggers: dynamic gated neuron, DGN, SNN…
Quellsprache: Englisch
Gaussian-equivalent process methodology for analyzing nonlinear noise in recurrent neural circuits using Ornstein-Uhlenbeck noise matching and lognormal moment closure. Activation: mean field, nonlinear noise, recurrent networks, OU process.
Quellsprache: Englisch
Dynamic neural manifolds methodology for flexible closed-loop control on neuromorphic hardware (SpiNNaker 2). Sensory-modulated heterogeneous inhibition drives subspace rotations for behavior switching.
Quellsprache: Englisch
Model dynamic path trajectories in brain functional connectivity to capture temporal evolution of connections between functional communities. Based on arXiv 2510.24025 NeuroPathNet.
Quellsprache: Englisch
Dynamic Pauli Constraints methodology for quantum circuit design - software-oriented model motivated by near-term hardware constraints
Quellsprache: Englisch
A Dynamical Blueprint for Brain State Organization methodology — framework for understanding dynamic organization of brain states through attractor dynamics and neural population trajectories
Quellsprache: Englisch
Continual learning framework preserving plasticity via dynamical isometry - Neural Tangent Kernel analysis showing layer-wise Jacobian singular values near 1 prevents plasticity loss, with isometry-promoting regularization and dormant ReLU reactivation…
Quellsprache: Englisch
Dynamical quantum optimal transport (QOT) methodology based on Benamou-Brenier formulation for computing geodesics between positive semidefinite matrices. Use when: computing quantum state transport distances, solving quantum chemistry problems via optimal…
Quellsprache: Englisch
DYSCO (Dynamics via Contrastive Learning) - 多视角对比学习从噪声观测中提取潜在动力学系统。通过独立噪声视角分离信号与噪声，恢复潜在轨迹和支配动力学方程。
Quellsprache: Englisch
DYSCO (Dynamics via Contrastive Learning) methodology for extracting governing equations from latent dynamics via multi-view temporal contrastive learning. Identifies latent dynamical systems from noisy high-dimensional measurements and recovers symbolic…
Quellsprache: Englisch
In-ear EEG monitoring platform methodology for simultaneous EEG sensing and auditory stimulation. Covers personalized IEEM device design, closed-loop neuromodulation, and in-ear electrode validation.
Quellsprache: Englisch
EEG-based visual attention decoding methodology addressing the eccentricity confound. Uses spatial attention tasks with controlled stimulus eccentricity and phase-scrambling controls to demonstrate that decodable EEG signals reflect genuine attention…
Quellsprache: Englisch
Eccentricity confound analysis for EEG-based visual attention decoding during natural video viewing. Methodological framework for separating true neural attention from stimulus and eye movement artifacts. Keywords: visual attention, EEG, eye movements,…
Quellsprache: Englisch
Cross-layer device-circuit-system co-design framework for leveraging non-equilibrium ECRAM dynamics as computational resources for short-term plasticity in neuromorphic circuits. ECRAM devices naturally exhibit volatile ionic dynamics that produce transient…
Quellsprache: Englisch
Cross-layer device-circuit-system co-design framework for implementing short-term plasticity (STP) in neuromorphic hardware using non-equilibrium ECRAM dynamics. Transforms volatile ionic dynamics from device artifacts into computational resources. Use when…
Quellsprache: Englisch