All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Llm Self Correction Confidence Signals V2大型语言模型通过内部置信度信号检测和纠正自身错误的研究。基于决策神经科学二阶置信度模型和PANL token机制。Votes: 0GitHub stars: 3
- Llm Self Correction Confidence Signals大型语言模型通过内部置信度信号检测和纠正自身错误的研究。基于决策神经科学二阶置信度模型。Votes: 0GitHub stars: 3
- Llm Serving System Adaptive ArchitectureLLM服务系统自适应架构设计 - 自进化系统、解耦架构、冷启动优化、黑盒调度、能效优化的综合技能框架。激活词: llm serving, adaptive architecture, autopoiesis, lora serving, llm cold start, inference scheduling.Votes: 0GitHub stars: 3
- Llm Sysml AlignmentLLM-assisted semantic alignment methodology for SysML v2 model integration in collaborative MBSE. Use when working with cross-organizational system model integration, SysML v2 semantic alignment, or LLM-based MBSE workflows. Keywords: SysML, MBSE, LLM, semantic alignment, model integration, SysML v2.Votes: 0GitHub stars: 3
- Local Gradient Approximations RnnDynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks. Analytical framework comparing RFLO, tBPTT, and BPTT learning dynamics using dynamical systems theory. Key finding: RFLO solutions restricted to low-rank perturbations, with qualitatively distinct convergence behavior.Votes: 0GitHub stars: 3
- Logact Agentic ReliabilityLogAct - enabling agentic reliability via shared logs. Deconstructed state machine architecture for LLM agents with pre-execution validation, failure recovery, and semantic introspection. Activation: agent reliability, agentic system, shared log, agent failure recovery, LogAct.Votes: 0GitHub stars: 3
- Low Rank Rnn Learning DynamicsFramework for analyzing learning dynamics in low-rank RNNs via overlap space decomposition. Distinguishes loss-visible overlaps (determine activity/output/loss) from loss-invisible overlaps (encode training history). Enables understanding of why functionally equivalent networks learn differently. Activation: low-rank RNN learning, RNN overlap space, loss-visible invisible, RNN gradient descent dynamics, RNN learning theory, Ger Barak RNN.Votes: 0GitHub stars: 3
- Maximum Entropy Connectivity NetworksMaximum entropy principle for neural network connectivity — describe connectivity as a probability distribution over single-neuron weights, express task requirements as constraints, maximize Shannon entropy. From arXiv:2605.25607.Votes: 0GitHub stars: 3
- Maximum Entropy Network Structure FunctionMaximum entropy principle for neural network connectivity that reveals how task constraints shape neural population structure without dependence on training procedure. Use when analyzing neural connectivity patterns, studying structure-function relationships, or designing normative models of neural computation.Votes: 0GitHub stars: 3
- Memory Centric Agentic ResearchMemory-centric agentic system methodology for full scientific research lifecycle automation. Covers schema-governed research memory (SciMem), five-stage lifecycle execution (SciFlow), DAG-shaped multi-agent operators (SciDAG), and self-evolving feedback loops (SciEvolve). Use when designing autonomous research agents, building persistent AI research systems, implementing scientific workflow automation, or creating self-improving agent systems. Activation: memory-centric agent, agentic researc...Votes: 0GitHub stars: 3
- Memory Uncertainty Relation Recurrent NetworksMemory Uncertainty Relation in random recurrent networks: inequality bounding short-term memory from below as an uncertainty relation between memory capacity and state-space fluctuations. Defines harmonic memory as an analytically tractable lower bound achieved by optimal readout weights.Votes: 0GitHub stars: 3
- Meta Learning Biological PlasticityMeta-Learning Biologically Plausible Plasticity RulesVotes: 0GitHub stars: 3
- Meta Learning In Context Decoding V3Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding. Uses meta-learned in-context learning to decode brain signals across subjects without any subject-specific training. Supports visual decoding from fMRI/EEG signals with zero-shot generalization. Activation: meta-learning brain decoding, in-context learning, cross-subject, training-free decoding, zero-shot brain decoding, visual reconstruction, 元学习脑解码, 跨被试解码, 零样本解码Votes: 0GitHub stars: 3
- Mistake Gated Continual LearningMistake-gated learning for energy and memory efficient continual learning using neuromorphic hardware. Only neurons that "make mistakes" (prediction errors) are updated, reducing compute and memory. Achieves 10-100x energy reduction vs full backprop on MNIST/CIFAR benchmarks.Votes: 0GitHub stars: 3
- Moe Optimal Transport RoutingMixture-of-Experts (MoE) routing using optimal transport for balanced expert utilization. Region-graph Sinkhorn routing for WSI classification and spatial data. Use when: MoE load balancing, expert routing optimization, spatial token assignment, entropic optimal transport, Sinkhorn iterations, MIL aggregation, computational pathology, region-to-expert assignment, capacity-constrained routing.Votes: 0GitHub stars: 3
- Momenta Multimodal Moe Misinformation DetectionMOMENTA — Mixture-of-Experts over multimodal embeddings with neural temporal aggregation for misinformation detection. Combines modality-specific MoE modules, bidirectional co-attention, discrepancy-aware branch, and attention-based temporal aggregation with drift/momentum encoding. Use when: multimodal misinformation detection, MoE for multimodal learning, temporal aggregation, cross-modal disagreement detection, fact-checking systems. Trigger: misinformation detection, multimodal MoE, cross...Votes: 0GitHub stars: 3
- Multi Agent Active Inference Digital TwinsMulti-agent digital twin framework using Active Inference for decentralized strategic decision-making. Features contextual inference and weighted message passing for coordination. Activation: active inference, multi-agent, digital twins, strategic decision-making, decentralized.Votes: 0GitHub stars: 3
- Multi Agent Clinical ReasoningMulti-agent framework for clinical reasoning and radiology AI. Use when designing multi-agent systems for medical diagnosis, radiology report generation, clinical decision support, or multi-modal medical reasoning. Triggers: multi-agent radiology, clinical reasoning agents, multi-agent medical AI, radiology report generation, clinical decision support agents.Votes: 0GitHub stars: 3
- Multi Agent Density ControlStochastic Density-Driven Optimal Control (D²OC) for multi-agent coverage and distribution matching. Uses Wasserstein distance as running cost with convergence guarantees for stochastic LTI systems. Use when designing decentralized multi-agent coverage, area coverage, distribution matching, or swarm control systems.Votes: 0GitHub stars: 3
- Multisensory Learning Engram RecruitmentMultisensory learning methodology that recruits visual neurons into olfactory memory engrams through cross-modal binding. Using Drosophila model to study how combining sensory modalities expands memory engrams and improves recall performance. Activation triggers: multisensory learning, memory engram, cross-modal binding, neural circuits, sensory integration.Votes: 0GitHub stars: 3
- Muon Ogd Spectral Orthogonal Gradient ProjectionMuon-OGD: Spectral-norm-aware orthogonal gradient projection for LLM continual learning. Integrates Muon optimizer's spectral-norm geometry with OGD's non-interference constraints. Activation triggers: Muon-OGD, spectral norm continual learning, orthogonal gradient projection LLM, Muon optimizer CL, Frobenius vs spectral norm CLVotes: 0GitHub stars: 3
- Near Policy DistillationMethodology for accelerating on-policy distillation via asynchronous generation and evaluation. Decouples generation from evaluation using a near-policy buffer, achieving 2-4x throughput gains without quality degradation.Votes: 0GitHub stars: 3
- Nerve Network Aware Bilinear Fc TokenizationNERVE: Network-Aware Representations of Brain Functional Connectivity via Bilinear Tokenization. Self-supervised learning framework for FC representation using network-aware bilinear tokenization in MAE. Partitions FC matrices into intra/inter-network connectivity blocks. Uses structured bilinear factorization to preserve network identity with linear parameter scaling. Evaluated on ABCD, PNC, CCNP cohorts for behavior prediction. Activation: nerve, network-aware fc tokenization, bilinear toke...Votes: 0GitHub stars: 3
- Network Attractors Delay PlasticityNetwork Attractors driven by Time-Delay Plasticity — framework for collective frequency selection and attractor formation via adaptive axonal delays (AADs), motivated by activity-dependent myelination in the brain. Uses delay-coupled phase oscillators on brain connectivity data. Activation: delay plasticity, adaptive axonal delay, network attractor, frequency selection, neural oscillation, myelination model, phase oscillator brain networkVotes: 0GitHub stars: 3
- Network Aware Iv RegressionNetwork-aware Instrumental Variable Regression for Causal Node Discovery and Estimation. Two-stage framework incorporating IVs and graph-fused regularization for sparse causal effects in network-structured exposures with latent confounding. Activation: network IV regression, causal node discovery, graph regularization, brain imaging causal inference.Votes: 0GitHub stars: 3
- Neuro Bursty Persistent NetworksBursty Persistent Brain Network (PBN) modeling methodology for neural dynamics with non-Markovian temporal structure. Combines renewal theory, state-dependent intensity functions, and stochastic simulations to model how neuronal avalanches transition between quiescent and active states.Votes: 0GitHub stars: 3
- Neuro Dendritic Balance LearningDendritic balance learning methodology for predictive processing in cortical circuits. Combines compartmental neuron models with predictive coding principles, using dendritic prediction errors to drive synaptic plasticity. Applies to spiking neural networks, predictive coding, dendritic computation, cortical learning algorithms.Votes: 0GitHub stars: 3
- Neuro Grounded Foundation Models[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.]Votes: 0GitHub stars: 3
- Neuro Sparse Deconvolved Predictive NetworkSparse Deconvolved Predictive Network methodology for neural dynamics modeling. Combines sparse coding, deconvolution of hemodynamic/synaptic responses, and predictive temporal modeling for extracting neural dynamics from observed signals. Applies to fMRI/EEG/Ca2+ imaging analysis, neural encoding, brain decoding.Votes: 0GitHub stars: 3
- Neurocybernetic Modeling Large ScaleIntegrative neurocybernetic modeling in the era of large-scale neuroscience. Closed-loop brain-body-environment models, nonlinear state-space, meta-dynamical extensions, knowledge distillation, connectomics-informed architectures. Trigger words: neurocybernetic modeling, closed-loop brain model, brain as controller, state-space neuroscience, large-scale neuroscience integration.Votes: 0GitHub stars: 3
- Nonlinear Rnn Fixed Connectivity SolutionAnalytical solution for large nonlinear recurrent neural networks at fixed connectivity. Calculates moments and response functions without synaptic weight averaging, linking connectivity to spontaneous activity and perturbation response. Trigger words: nonlinear RNN, fixed connectivity, moments, response functions, large N limit.Votes: 0GitHub stars: 3
- Nonlinear Rnn Linear EquivalenceLinear equivalence of nonlinear recurrent neural networks using two-site cavity method. Shows covariance matrix of large nonlinear RNNs takes same form as linear networks with mean-field order parameters. Activation: nonlinear RNN, linear equivalence, cavity method, mean-field analysis, covariance matrix.Votes: 0GitHub stars: 3
- Noracl Neurogenesis Continual LearningNORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning. Uses biologically-inspired neuronal growth to address the stability-plasticity dilemma without requiring oracle-sized architectures. Triggers: neurogenesis continual learning, adaptive network growth, NORACL, resource-adaptive CL, oracle-free architecture.Votes: 0GitHub stars: 3
- Normalizing Trajectory ModelsNormalizing Trajectory Models (NTM) methodology for few-step generative modeling with exact likelihood. Combines shallow invertible blocks within each denoising step with a deep parallel trajectory predictor, enabling end-to-end training and self-distillation for 4-step high-quality generation. Use when: normalizing trajectory, flow matching, few-step diffusion, trajectory modeling, exact likelihood, generative model distillation, self-distillation diffusion, invertible flow generation.Votes: 0GitHub stars: 3
- Pbkv Agent WorkflowPrediction-based KV-Cache management for efficient serving of dynamic agent workflows. Predicts future agent invocations to optimize cache eviction and prefetching.Votes: 0GitHub stars: 3
- Physical Foundation Models PfmPhysical Foundation Models (PFMs) — Fixed hardware implementations of large-scale neural networks where parameters are realized directly in physical substrate dynamics. Use when: designing specialized inference hardware, exploring optical/nanoelectronic neural implementations, analyzing energy efficiency of fixed-weight networks, considering trillion-parameter hardware inference. Triggers: physical neural network, fixed hardware inference, optical computing neural network, nanoelectronic AI, ...Votes: 0GitHub stars: 3
- Physical Foundation ModelsPhysical Foundation Models (PFMs): Fixed hardware implementations of large-scale neural networks realized directly in physical materials. Covers optical, nanoelectronic, and other physical platforms for trillion-parameter models. Activation: physical neural networks, optical computing, hardware AI, foundation model hardware.Votes: 0GitHub stars: 3
- Pinns Biomedical ModelingPhysics-informed Neural Networks (PINNs) for biomedical modeling and simulation. Use when working on physics-guided neural network approaches for hemodynamics, cardiovascular modeling, blood flow prediction, or inverse medical physics problems. Combines physical principles with neural networks for personalized medical predictions with minimal data requirements.Votes: 0GitHub stars: 3
- Pinns Medical Modeling[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.]Votes: 0GitHub stars: 3
- Plant Model Mismatch MpcModel Predictive Control under plant-model mismatch - stability and suboptimality guarantees. Handles model uncertainty in control systems. Activation: MPC, model mismatch, robust control, plant-model mismatch, uncertainty in control systems.Votes: 0GitHub stars: 3
- Plasticity Network FrameworkNetwork-based operationalization of plasticity as the ratio between system size and connectivity strength. Links structure to dynamical regimes (plastic vs rigid). Use for: complex systems analysis, brain plasticity quantification, neural network rigidity, ecosystem resilience, state space accessibility.Votes: 0GitHub stars: 3
- Plasticity Prediction Deep Continual LearningTheoretical framework for predicting plasticity in deep continual learning — understanding why neural networks lose their ability to adapt after training on previous tasks (loss of plasticity). Activation triggers: loss of plasticity, plasticity prediction, continual learning theory, network adaptability, neural network plasticityVotes: 0GitHub stars: 3
- Poisson Gradient EstimationSystematic comparison of Poisson gradient estimation methods (EAT vs GSM) for latent variable models in computational neuroscience. Activation: poisson gradient, EAT method, Gumbel-SoftMax, spike train inference.Votes: 0GitHub stars: 3
- Polystep Gradient Free TrainingGradient-free neural network training via Optimal Transport geometry (PolyStep optimizer). Based on arXiv:2605.01928 (Le, 2026). Use when training non-differentiable models including hard-LIF spiking neurons, quantized networks, discrete routing, or blackbox simulators. Replaces backpropagation and surrogate gradients with forward-pass-only optimization. Activation: polystep optimizer, gradient-free training, non-differentiable network, hard-LIF training, optimal transport optimizer, surrogat...Votes: 0GitHub stars: 3
- Polystep Optimal Transport TrainingGradient-free optimization for non-differentiable networks using optimal transport (PolyStep). Trains spiking neurons, quantized layers, discrete routing without surrogate gradients. Activation: polystep, optimal transport training, gradient-free optimizer, non-differentiable networks, spiking training without backprop.Votes: 0GitHub stars: 3
- Preisach Attention Hysteretic MemoryPreisach Attention Layer (PAL) — a novel sequence modeling architecture that replaces softmax attention with the classical Preisach hysteresis operator from mathematical physics. Uses binary relay operators with learned thresholds and a stack of local extrema as internal state. Achieves Turing-completeness at O(1) depth via two-stack PDA simulation. Activation: attention, hysteresis, sequence modeling, episodic memory, transformer alternative, rate-independent computationVotes: 0GitHub stars: 3
- Prompt OptimizationUniversal prompt optimization skill that applies systematic techniques to improve prompt quality, clarity, and effectiveness for any AI agent.Votes: 0GitHub stars: 3
- Qcnn Parallel Feature Fusion MedicalParallel multi-circuit quantum feature fusion methodology for medical image classification. Use when: (1) building hybrid quantum-classical CNN architectures for biomedical image classification, (2) comparing quantum vs classical models with statistical rigor (Wilcoxon signed-rank test, Cohen's d effect size), (3) designing parallel quantum encoding circuits (amplitude + angle encoding simultaneously), (4) parameter-matched fairness evaluation for QML vs classical baselines. Covers QCNN archi...Votes: 0GitHub stars: 3
- Qpinn Portfolio OptimizationQuantum Physics-Informed Neural Networks (QPINN) for portfolio optimization PDEs — uses parameterized quantum circuits with tensor rank decomposition to solve financial PDEs with 80x fewer parameters and higher accuracy than classical PINNs. Use when: solving financial PDEs for portfolio optimization, Merton problem, quantum-inspired PINNs, tensor rank decomposition for quantum circuits, parameter-efficient quantum PDE solvers.Votes: 0GitHub stars: 3
- Quasi Equivariant MetanetworksQuasi-equivariant metanetworks for weight-space learning. Use for designing neural architectures that operate on pretrained model parameters, implementing equivariant and quasi-equivariant transformations that respect architectural symmetries while maintaining expressivity. Applicable to feedforward, convolutional, and transformer networks.Votes: 0GitHub stars: 3