All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Rogue Variable CognitionRogue Variable Theory (RVT) for quantum-compatible cognition modeling. Formalizes pre-event cognitive states as structured Rogue Variables embedded in graph Hilbert space via Mirrored Personal Graph (MPG). Includes Rosetta Stone Layer for cross-user latent space alignment. Use when: (1) modeling pre-decision cognitive states, (2) analyzing ambiguity and contextual tension in cognition, (3) building cross-user representation alignment systems, (4) implementing quantum-consistent information-th...Votes: 0GitHub stars: 3
- S2 Net Oscillatory Spiking SynchronizationSpiking-by-Synchronization Neural Network (S2-Net) methodology. Oscillatory SNN with time-delayed coordination for brain-inspired learning. Uses rhythmic timing as control mechanism for efficient information processing across neural decoding, signal processing, temporal binding and semantic reasoning.Votes: 0GitHub stars: 3
- Sa Hgnn Eeg Depression HyperbolicSample-Adaptive Hyperbolic Graph Neural Network (SA-HGNN) for EEG-based depression recognition. Combines sample-adaptive graph construction with hyperbolic graph convolution and attention pooling to capture hierarchical brain network structure in EEG signals.Votes: 0GitHub stars: 3
- Sa Hgnn Sample Adaptive Hyperbolic Eeg DepressionSample-Adaptive Hyperbolic Graph Neural Network for EEG-based depression recognition. Uses hyperbolic geometry to capture hierarchical brain network structure and personalized functional connectivity.Votes: 0GitHub stars: 3
- Sae Brain Language Interpretation使用稀疏自编码器(SAE)特征解释脑语言响应的编码框架。引入Augmented Sparse Encoding Models，结合LM稀疏特征和surprisal预测，实现可解释的脑信号解码Votes: 0GitHub stars: 3
- Sae Brain Llm Cortical TopographySparse Autoencoders (SAEs) bridge mechanistic interpretability with brain encoding models, decomposing LLMs into interpretable features that map onto cortical semantic topography. Use when analyzing brain-LLM alignment via SAE-discovered features, studying semantic feature organization in cortex, or evaluating how LLM internal representations correspond to neural responses across languages.Votes: 0GitHub stars: 3
- Sae Brain Llm TopographySparse Autoencoders (SAEs) bridge mechanistic interpretability with neural encoding models to map LLM features onto cortical semantic topography — decomposing GPT-2 XL and Llama-3.1-8B into 16K-32K interpretable features and showing semantic features dominate brain alignment (94% of peak encoding performance, r=0.285), validated across English/Chinese/French (arXiv: 2605.23035, CoNLL 2026).Votes: 0GitHub stars: 3
- Safety Critical Contextual Control RiemannianSafety-critical contextual control via online Riemannian optimization with world models — Penalized Predictive Control (PPC) framework for provably safe control using black-box simulators and score-based density estimation.Votes: 0GitHub stars: 3
- Saliency Aware Eeg DecodingSIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding for zero-shot EEG-to-image retrieval. Uses foreground segmentation, saliency prediction, Saliency-Aware Sampling (SAS), and foveated multi-view integration to overcome center-bias limitations in EEG-to-image retrieval. Trigger words: saliency-aware EEG decoding, SIMON, EEG-to-image retrieval, foveated view, multi-view neural decoding, Saliency-Aware Sampling, object-centric neural decoding, zero-shot EEG image, THINGS...Votes: 0GitHub stars: 3
- Same Brain Different Prediction How Preprocessing Choices Undermine Eeg Decoding Reliability**arXiv ID:** 2605.07212 **Authors:** Dengzhe Hou, Zihao Wu, Lingyu Jiang, Zirui Li, Fangzhou Lin, Kazunori D. Yamada **Published:** 2026-05-08T03:58:58Z **Abstract:** Electroencephalography (EEG) is a cornerstone of brain-computer interfaces and clinical neuroscience, yet deep learning models are typically trained and evaluated under a single, unreported preprocessing pipeline. We formalize preprocessing choices as a counterfactual intervention space and show that EEG predictions are surpris...Votes: 0GitHub stars: 3
- Same Brain Different PredictionEEG decoding reliability methodology addressing preprocessing-induced prediction instability. Formalizes preprocessing choices as a counterfactual intervention space and demonstrates that preprocessing decisions significantly undermine model reliability across BCI paradigms. Use when: (1) designing EEG/MEG decoding studies, (2) evaluating model reliability, (3) comparing preprocessing pipelines, (4) building robust BCI systems, (5) writing methods sections for neuroimaging papers, (6) conduct...Votes: 0GitHub stars: 3
- Samga Subject Aware Multi Granularity Eeg ImageSubject-Aware Multi-Granularity Alignment (SAMGA) for zero-shot EEG-to-image retrieval. Enables cross-subject brain-computer interfaces with hierarchical neural representation alignment. Keywords: EEG, zero-shot retrieval, brain decoding, cross-subject, multi-granularity alignment.Votes: 0GitHub stars: 3
- Sandbox Digital Twin CpsSandbox-Enabled Digital Twin for Cyber-Physical Systems (CPS) - closed-loop validation framework that captures controller side-channels with simulated plant feedbackVotes: 0GitHub stars: 3
- Sbtg Neural Circuit InferenceScore-Block Time Graphs (SBTG) methodology for inferring lag-specific directed neural circuit interactions from population activity data. Uses denoising score models and cross-block score products to recover the Jacobian of transition maps under nonlinear dynamics. Based on arXiv:2605.02852 (Kinger et al., 2026).Votes: 0GitHub stars: 3
- Sbtg Neural Dynamics InferenceScore-Block Time Graphs (SBTG) methodology for inferring lag-specific directed neural circuit interactions from population activity data using denoising score models. Activates: neural circuit inference, diffusion score, SBTG, directed connectivity, calcium imaging circuit mapping, lag-specific interaction, Jacobian recovery, brain state transition, C. elegans neural circuit.Votes: 0GitHub stars: 3
- Sc Taupath Alzheimer Tau PropagationSC-TauPath 结构连接归因框架用于映射阿尔茨海默病 Tau 传播路径。结合网络扩散模型增强 MLP 与梯度×输入归因，生成多尺度路径图谱（骨干边、高流量路由、枢纽 ROI），验证 Braak 分期解剖学。Votes: 0GitHub stars: 3
- Scalable Learning In Structured Recurrent Spiking Neural Networks Without Backpropagation**arXiv ID:** 2605.00402 **Authors:** Bo Tang, Weiwei Xie **Published:** 2026-05-01T04:45:21Z **Abstract:** Spiking Neural Networks (SNNs) provide a promising framework for energy-efficient and biologically grounded computation; however, scalable learning in deep recurrent architectures with sparse connectivity remains a major challenge. In this work, we propose a structured multi-layer recurrent SNN architecture composed of locally dense recurrent layers augmented with sparse small-world lon...Votes: 0GitHub stars: 3
- Scalable Snn Without BackpropScalable learning in structured recurrent SNNs without backpropagation or surrogate gradients. Uses local plasticity, WTA teaching signals, and random broadcast alignment. Trigger words: SNN without backprop, local plasticity, structured recurrent SNN, WTA teaching signal, broadcast alignment.Votes: 0GitHub stars: 3
- Scaling Laws And Tradeoffs In Recurrent Networks Of Expressive Neurons**arXiv ID:** 2605.12049 **Authors:** Aaron Spieler, Georg Martius, Anna Levina **Published:** 2026-05-12T12:29:33Z **Abstract:** Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent biological constraints. Mainstream machine learning, by contrast, predominantly builds models from extremely simple units, a default inherited from early neural-network theory. We treat this as a normative architectural questi...Votes: 0GitHub stars: 3
- Scaling Optimal Channel PurificationScaling-optimal purification of noisy qubit unitary channels — methodology for constructing superchannels that purify noisy quantum operations back to original unitaries. Sequential strategies outperform parallel for finite uses; asymptotic optimal scaling via entanglement-assisted QEC. Use when: quantum channel purification, noise suppression protocols, superchannel design, quantum error correction with entanglement assistance, sequential vs parallel quantum strategies, or asymptotic noise s...Votes: 0GitHub stars: 3
- Schrodinger Equation Single NeuronsDerivation of emergent Schrödinger equation for single neurons through stochastic neural dynamics. Electrical noise in membranes produces quantum-like behavior. arXiv:2406.16991Votes: 0GitHub stars: 3
- Score Broadcast Decorrelation Credit AssignmentScore Broadcast and Decorrelation (SBD)方法论 - 广播式信用分配的通用框架，为三因子学习规则提供理论基础。Error broadcast作为backpropagation的生物合理替代方案，适用于不同iable losses。Activation: SBD, score broadcast, credit assignment, three-factor learning, error broadcast, 生物可塑性.Votes: 0GitHub stars: 3
- Sd3mf Multimodal Brain NetworkSupervised Deep Multimodal Matrix Factorization (SD3MF) methodology for interpretable brain network analysis. Generalizes SNMTF from unsupervised single-graph clustering to supervised prediction over populations of multimodal graphs. Learns deep hierarchical factorizations with shared latent representations that align subjects across modalities via encoder-decoder formulation. Use when: analyzing multimodal connectome data, building interpretable brain network classifiers, performing supervis...Votes: 0GitHub stars: 3
- Sealkd Snn Knowledge DistillationSelective Alignment Knowledge Distillation (SeAl-KD) methodology for Spiking Neural Networks. Addresses the limitation of uniform timestep alignment in existing KD methods by selectively aligning class-level and temporal knowledge. Equalizes competing logits at erroneous timesteps, reweights temporal alignment based on confidence and inter-timestep similarity. Consistently improves over existing distillation methods on static image and neuromorphic event datasets. Activation: sealkd, selectiv...Votes: 0GitHub stars: 3
- Secretary Problem Continued FractionSecretary problem optimal stopping thresholds are exactly the convergents of 1/e via continued fractions. If p/q is a continued fraction convergent of 1/e with q at least 3, then for q applicants the optimal number to initially reject is p. Connects optimal stopping theory, continued fractions, and the mathematical constant e. Use when: optimal stopping problems, secretary problem analysis, continued fraction applications, 1/e thresholds, decision theory, sequential selection.Votes: 0GitHub stars: 3
- Seizure Suppression Hub StimulationSeizure Suppression via Brain Network Hub StimulationVotes: 0GitHub stars: 3
- Selective Alignment Kd SnnSelective Alignment Knowledge Distillation (SeAl-KD) methodology for Spiking Neural Networks. Addresses the performance gap between SNNs and ANNs by selectively aligning class-level and temporal knowledge during distillation. Unlike uniform alignment across all timesteps, SeAl-KD equalizes competing logits at erroneous timesteps and reweights temporal alignment based on confidence and inter-timestep similarity. Use when: improving SNN performance via knowledge distillation, temporal alignment...Votes: 0GitHub stars: 3
- Selective Alignment Knowledge Distillation SnnSelective Alignment Knowledge Distillation (SeAl-KD) for Spiking Neural Networks. Addresses the performance gap between SNNs and ANNs by recognizing that not all timesteps in SNN inference are equally important. Selectively aligns class-level and temporal knowledge by equalizing competing logits at erroneous timesteps and reweighting temporal alignment based on confidence and inter-timestep similarity. Use when training SNNs with knowledge distillation, optimizing temporal dynamics in spiking...Votes: 0GitHub stars: 3
- Self Correcting Quantum Memory 3dPassive self-correcting quantum memory in 3D — constructs a 3D Pauli stabilizer Hamiltonian encoding a qubit for exponential time at non-zero temperature via recursive transformations. Based on arXiv:2605.04951. Use when designing fault-tolerant quantum memories, analyzing thermal stability of topological codes, or building passive error correction schemes. Activation: self-correcting quantum memory, 3D stabilizer Hamiltonian, passive quantum error correction, thermal quantum memory, Pauli st...Votes: 0GitHub stars: 3
- Self Organized Criticality Brain Body ResonanceSelf-organized criticality methodology for conscious integration via brain-body resonance. Demonstrates that physiological signals actively support large-scale neural coordination. Uses 78ms brain-body resonance, raw EEG avalanche dynamics, and holographic information encoding. Activation: self-organized criticality, brain-body resonance, conscious integration, neural criticality, avalanche dynamics, holographic encoding.Votes: 0GitHub stars: 3
- Self Sustained Neuron PopulationModeling self-sustained neural activity in recurrent networks without external input. Hodgkin-Huxley neurons with STDP and stochasticity maintain autonomous sparse firing for 1800+ seconds after brief initialization. Use when studying autonomous brain dynamics, self-sustained activity, spontaneous neural reorganization, or biologically plausible network simulation.Votes: 0GitHub stars: 3
- Semantic Aligned Brain Network HypergraphsSABER framework for semantic-aligned brain network analysis via multi-scale hypergraphs. Actively integrates LLM-derived semantics into brain network prediction, combining global self-attention, multi-scale hypergraph construction, and decision-level semantic alignment for improved brain disease diagnosis. Use when building brain network classifiers, fMRI/EEG analysis pipelines, or LLM-brain integration systems.Votes: 0GitHub stars: 3
- Semi Device Independent Certification Nonlocality EntanglementSemi-device-independent certification methodology for nonlocality without entanglement (NLWE) using maximum-confidence discrimination. Proves global measurements outperform separable ones for ensembles of separable states, establishing NLWE through confidence-based state identification. Use when analyzing quantum state discrimination protocols, semi-device-independent quantum certification, maximum-confidence measurements, nonlocality without entanglement, or quantum communication security pr...Votes: 0GitHub stars: 3
- Semi Device Independent Nlwe CertificationSemi-device-independent certification methodology for nonlocality without entanglement (NLWE) using maximum-confidence discrimination of separable state ensembles.Votes: 0GitHub stars: 3
- Sensing Intelligence Trainable MetamaterialSensing Intelligence as a Trainable Metamaterial Property methodology. Optimize metamaterial body geometry via differentiable simulation to preprocess external stimuli, improving neural network sensing accuracy by up to 5x or reducing required sensors by 10x. Use when designing embodied sensing systems, neuromorphic perception pipelines, bio-inspired sensor optimization, or physical preprocessing for neural networks.Votes: 0GitHub stars: 3
- Sensorless Gaze Following HriNeuroscience-inspired framework for low-cost sensorless gaze following in Human-Robot Interaction. Uses computational models of human gaze perception to estimate where humans are looking without expensive eye-tracking hardware. Trigger words: sensorless gaze, gaze following, human-robot interaction, HRI, gaze estimation, neuroscience gaze, low-cost gaze tracking.Votes: 0GitHub stars: 3
- Sensorless Gaze FollowingNeuroscience framework for sensorless gaze-following in Human-Robot Interaction (HRI). Uses brain-inspired prediction mechanisms to estimate gaze targets without eye-tracking hardware.Votes: 0GitHub stars: 3
- Sensorless Gaze Hri FrameworkNeuroscience-inspired sensorless gaze-following framework for human-robot interaction. Uses perceptual illusions and brain's convexity assumptions to create gaze-following robots without cameras or sensors. Activation: sensorless gaze, perceptual gaze, cardboard robot, convexity prior, gaze-following HRI, low-cost robot gaze, perception neuroscience HRI.Votes: 0GitHub stars: 3
- Sfmc Infant Brain Stochastic ModulesStochastic module-based methodology for robust probabilistic measurement of structural-functional module consistency (SFMC) in brain networks. Accounts for inter-individual variability and reveals stronger developmental reorganization than conventional coupling approaches. Use for infant brain development analysis, structure-function coupling studies, and brain network module analysis.Votes: 0GitHub stars: 3
- Sgdm Eeg Visual CognitionStructure-Guided Diffusion Model (SGDM) for EEG-based visual cognition reconstruction. Leverages brain structural information to guide diffusion process for improved visual stimulus reconstruction from EEG. Keywords: EEG, diffusion model, visual reconstruction, brain structure, BCI.Votes: 0GitHub stars: 3
- Shared State ArchitecturePSI (Persistent Shared Interface): A shared-state architecture for coherent AI-generated instruments in personal AI agents. Addresses the problem of isolated AI tools by introducing a personal-context bus for cross-module reasoning and synchronized actions. Use when designing multi-agent systems, personal AI environments, tool orchestration, or building coherent AI software architectures.Votes: 0GitHub stars: 3
- Sharpness Aware Surrogate Snn TrainingSAST methodology improving SNN generalization through sharpness-aware minimization with surrogate gradients. Activation: sharpness-aware training, surrogate gradient, SNN generalization.Votes: 0GitHub stars: 3
- Sheaf Consistency MbseSheaf-theoretic framework for multi-view consistency in model-based systems engineering (MBSE). Uses presheaves on architectural sites to certify global design consistency via pairwise interface checks. Provides a formal mathematical criterion for when local engineering views (electrical, thermal, mechanical, software) determine a coherent global design. Use when: (1) analyzing multi-domain CPS architecture consistency, (2) formalizing MBSE verification, (3) building design space composition ...Votes: 0GitHub stars: 3
- Shunting Inhibition Dendritic Credit AssignmentShunting inhibition and dendritic branching mechanisms for local credit assignment in biological neurons - conductance-based models showing how E/I synapses reshape credit-signal geometry under restricted feedbackVotes: 0GitHub stars: 3
- Signal Transform UnificationUnify signal transforms (DFT, DCT, wavelet, KLT, etc.) under representation-theoretic principles via the Algebraic Diversity framework. Covers matched group discovery, Peter-Weyl theorem applications, covariance-invariant transforms, and applications to MIMO, GNNs, transformers, and quantum informatics. Activation: signal transform theory, matched group discovery, Algebraic Diversity, DFT unification, representation theory signal processing, Peter-Weyl transform, covariance eigenbasis.Votes: 0GitHub stars: 3
- Simon Saliency Neural DecodingSIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding for zero-shot EEG-to-image retrieval. Uses saliency-aware sampling and foveated views to overcome center-bias limitations. Trigger words: SIMON neural decoding, EEG-to-image retrieval, saliency-aware EEG, foveated neural decoding, zero-shot EEG image, object-centric neural decoding, multi-view EEG.Votes: 0GitHub stars: 3
- Simulation Of Neural Responses To Classical Music Using Organoid Intelligence Methods**arXiv ID:** 2407.18413 **Authors:** Daniel Szelogowski **Published:** 2024-07-25T22:11:30Z **Abstract:** Music is a complex auditory stimulus capable of eliciting significant changes in brain activity, influencing cognitive processes such as memory, attention, and emotional regulation. However, the underlying mechanisms of music-induced cognitive processes remain largely unknown. Organoid intelligence and deep learning models show promise for simulating and analyzing these neural responses ...Votes: 0GitHub stars: 3
- Single Entity Spiking Neuron Models SurveyComprehensive survey of single-entity spiking neuron models - mathematical modeling approaches for biologically plausible neural systems including discrete/continuous models, membrane potential dynamics, and various neural componentsVotes: 0GitHub stars: 3
- Single Entity Spiking Neuron SurveyComprehensive survey of single-entity spiking neuron models covering mathematical formulations, biological plausibility, and computational trade-offs. Covers integrate-and-fire variants (LIF, EIF, Izhikevich, AdEx), Hodgkin-Huxley models, FitzHugh-Nagumo, Morris-Lecar, and discrete/continuous analogs for membrane potential dynamics. Activation: spiking neuron model, neuron model survey, LIF, EIF, Izhikevich, AdEx, Hodgkin-Huxley, FitzHugh-Nagumo, Morris-Lecar, membrane potential, biologically...Votes: 0GitHub stars: 3
- Sleep Like PlasticitySleep-inspired homeostatic regularization for stabilizing spike-timing-dependent plasticity (STDP) in spiking neural networks. Uses sleep-like phases with modified dynamics to consolidate learning, prevent weight runaway, and improve generalization. Bio-inspired approach mimicking sleep-dependent memory consolidation in biological brains. Use for SNN training stability, continual learning, and bio-inspired regularization. Activation: sleep regularization SNN, homeostatic plasticity, sleep-lik...Votes: 0GitHub stars: 3