Menu
Skills in this repository
SkillsMP has collected 4,114 skills from hiyenwong/ai_collection. Open a skill to review its source and details.
hiyenwong/ai_collectionShowing 40 of 4,114 collected skills.
Modern systems engineering design patterns extracted from April 2026 research papers. Covers physics-informed state space models for control systems, runtime security frameworks for multi-agent systems, and generative modeling for multi-agent coordination.…
Classification methodology for modular forms of rational weight satisfying the Kaneko-Zagier modular differential equation, using hypergeometric transformation and monodromy analysis.
模块化忆阻器模型：具有突触样可塑性和易失性记忆特性。通过可重构的忆阻器阵列实现类突触动力学，支持在线学习和自适应权重更新。适用于神经形态硬件、边缘学习设备、存内计算。
Source text: Chinese
Methodology for constructing and analyzing modular Nahm sums in number theory, including lift-dual operations and rank extensions
Distributed compilation of Shor's algorithm on modular atomic quantum processors. Methodology for large-scale integer factorization across multiple quantum modules with optimized inter-module communication and intra-module clock rates. Use when: compiling…
Module lattice security methodology for post-quantum cryptography. Covers unconditional verification of Weber's conjecture, Principal Ideal Problem solvability, Structured CVP Distance on the Log-Unit Lattice, Ring-LWE and Module-LWE security reductions, and…
MōLe-Λ methodology for learning coupled-cluster response states. Extends Molecular Orbital Learning (MōLe) to predict full CCSD response state by jointly learning T and Λ amplitudes from localized Hartree-Fock orbitals. Provides CC-quality energies, forces,…
Computational framework for analyzing vibronic relaxation channels in molecular spin qubits. Combines DFT, TD-DFT, and Redfield theory to predict T1 relaxation times and identify dominant decoherence pathways. Use when: analyzing molecular qubit coherence,…
Perceptogram: visual reconstruction framework from monkey neural activity — decoding perceived images from primate visual cortex recordings using deep generative models. Activation: monkey visual reconstruction, perceptogram, primate neuroscience, visual…
Disentangled motion control with causality reasoning for video generation. Use when: motion-controlled video generation, disentangled control systems, motion causality modeling, active-passive motion decomposition, camera-object motion separation,…
Moving MRI (mMRI) methodology for imaging during large-scale motion. Core idea: Move subject and scanner (magnet, gradients, RF coil) as a single unit to minimize relative motion, enabling neuroimaging during movement. Demonstrates cryogen-free…
MPC-RL integrated framework for autonomous driving in multi-agent scenarios. Combines Model Predictive Control's structured constraint handling with Deep Reinforcement Learning's adaptive behavior learning. Use for: autonomous vehicle control, multi-agent…
MQT Compiler Collection - Future-proof quantum-classical compilation framework built on MLIR. Supports complex optimizations and HPC integration. Activation: quantum compiler, MQT, quantum-classical compilation, MLIR quantum, quantum circuit optimization.
Spatiotemporal TDANN for modeling self-organized MT direction selectivity maps in the dorsal stream. Uses 3D ResNet with Momentum Contrast (MoCo) self-supervised learning and biological spatial loss to produce direction-selective pinwheel structures matching…
Multi-Timescale Conductance Spiking Networks (MTC-SNN) — gradient-trainable spiking neural networks where neural dynamics emerge from shaping the I-V curve via fast, slow, and ultra-slow conductances. Enables tonic, phasic, and bursting firing regimes within…
Multi-Timescale Conductance Spiking Networks (MTC-SN): A sparse, gradient-trainable SNN framework with rich firing dynamics for enhanced temporal processing. Uses fast/slow/ultra-slow conductances to shape I-V curves, enabling direct BPTT without surrogate…
Multi-task EEG analysis framework using Low-Rank Adaptation (LoRA) for efficient adaptation of pre-trained models to multiple downstream tasks. Addresses EEG signal heterogeneity and task conflicts through task-specific low-rank decomposition. Activation:…
多模态大语言模型预测小鼠社会优势行为的基准测试框架。MLLM分析原始行为视频预测优势等级。
Source text: Chinese
Multi-objective genetic algorithm (NSGA-III) optimisation of Izhikevich neuron-based recurrent spiking neural networks for simultaneously matching neural firing rates and network oscillation frequencies. Based on arXiv:2605.25224 (May 2026). Use when studying…
Multi-objective optimization methodology for quantum computing workflows, combining compilation strategy selection, noise suppression, and error-mitigation. Based on QBalance framework (arXiv: 2605.02966) and action-space engineering for RL-based circuit…
Multi-objective genetic algorithm (NSGA-III) optimisation of spiking neural networks (RSNNs) to match neural firing rates and oscillation frequencies for computational neuroscience modeling.
多可塑性协同脉冲神经网络训练方法论。结合多种突触可塑性机制（STDP、奖励调制、赫布学习）协同训练SNN，自适应机制分配。适用于脉冲神经网络、神经形态计算、低功耗AI。触发词：脉冲神经网络、SNN、多可塑性、STDP、突触可塑性、spiking neural network、multi-plasticity。
Source text: Chinese
Multi-Plasticity Synergy for SNN Training
Source text: Chinese
Multi-scale hypergraph learning (MuHL) methodology for high-order brain connectivity analysis beyond pairwise GNNs. Accepted to ICML 2026. Use for: brain network analysis, neurodegenerative disease classification (Alzheimer's, Parkinson's), higher-order…
Multi-scale information geometry framework revealing the structure of mutual information in neural populations. A unique Riemannian representational geometry emerges from coarse-graining, extending Fisher information metric to capture encoding structure from…
Multi-scale information geometry framework for analyzing neural population codes. Extends Fisher information metric across stimulus coarse-graining scales to reveal mutual information structure. Use when analyzing: (1) neural population coding geometry, (2)…
Multi-source fMRI cognitive taskonomy framework using transfer learning across 23 HCP task states. Extends single-source to many-to-one task relations with Boolean Integer Programming for budget-constrained task allocation. Activation: fMRI taskonomy,…
Multi-Timescale Conductance Spiking Networks (MTC-SNN) methodology for energy-aware temporal processing. Introduces gradient-trainable spiking neurons using fast/slow/ultra-slow conductances to shape I-V curves, enabling direct backpropagation through time…
Multi-Timescale Conductance (MTC) Spiking Networks — gradient-trainable framework with rich firing dynamics for enhanced temporal processing. Conductance-based neuron model with fast/slow/ultra-slow timescales enables tonic, phasic, and bursting responses…
Multi-view O-Information framework for analyzing higher-order brain interactions in fMRI data. Combines O-information measures with information bottleneck principles for psychiatric diagnosis. Includes O-information computation, Gaussian approximation, and…
Multi-view O-Information framework for modeling higher-order brain interactions (HOIs) in fMRI data. Information-theoretic approach to psychiatric diagnosis using triadic and tetradic brain connectivity patterns. Keywords: O-information, higher-order…
Higher-order brain interaction analysis using O-information and Multi-View Information Bottleneck for fMRI-based psychiatric diagnosis. Decomposes multivariate neural interactions into redundant and synergistic components across multiple brain views for…
Game-theoretic framework extending Nash equilibrium to NeuroAI systems with internal computation. Multilevel Interactive Equilibrium (MIE) captures how neural learning dynamics, cognitive representations, and behavioral strategies mutually stabilize between…
多模态脑连接分析框架，整合fMRI、DTI和sMRI数据。使用可解释图神经网络，通过掩码策略差异加权神经连接，实现跨模态数据融合。支持认知功能预测和解剖特征发现。触发词：多模态融合、脑连接、fMRI、DTI、sMRI、图神经网络、功能连接、结构连接、multimodal fusion、brain connectivity、functional connectivity、structural connectivity。
Source text: Chinese
M3D-BFS: Multi-stage Dynamic Fusion Strategy for Sample-Adaptive Multi-Modal Brain Network Analysis. Combines Mixture-of-Experts (MoE) with multi-modal brain networks (structural and functional connectivity) through dynamic, sample-adaptive fusion. 3-stage…
Optimal multiparameter estimation for quantum systems using the unified Cramér-Rao bound framework. Use when: (1) estimating functions of multiple parameters in quantum Hamiltonians, (2) designing quantum sensing protocols, (3) analyzing precision limits for…
Multiplication-free spike-time learning algorithm for efficient on-chip SNN training on FPGA. Hardware-software co-design for low-power, event-driven neuromorphic computing. Keywords: SNN training, FPGA implementation, spike-time learning, neuromorphic…
Unified framework for multi-scale brain dynamics analysis combining criticality scaling, fixed point compositionality, and representation diagnostics. Integrates renormalization group methods, inhibition-dominated network theory, and EEG foundation model…
MV-BrainFM: Cross-view consistency learning for multi-view brain network foundation models. Activation: multi-view learning, brain networks, foundation models.
Multi-view Information Bottleneck framework for modeling higher-order interactions (HOIs) in resting-state fMRI for psychiatric diagnosis. Captures complex brain dynamics beyond pairwise connectivity without predefined hyperedges.