All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Latent Neural Dynamics Ml SurveyComprehensive survey of machine learning methods for studying latent neural activity dynamics - from state-space models to deep generative models covering single-region dynamics, multi-region communication, and neural manifold geometry.Votes: 0GitHub stars: 3
- Latent Revise Zero Hit ReasoningLatentRevise — First-order latent revision method that recovers training signal from zero-hit prompts in RLVR. Optimizes input embeddings of failed reasoning prefixes under dual gradients (away from failed continuation, toward gold answer), constrained to vocabulary embedding convex hull.Votes: 0GitHub stars: 3
- Lateral Predictive Coding ModularLateral predictive coding (LPC) framework for feature detection in biological neural circuits with modular network structures. Analyzes response time trade-offs between modular vs non-modular architectures. Activation: predictive coding, neural circuits, modularity, feature detection, response time.Votes: 0GitHub stars: 3
- Lattice Field Theory NeuronsLattice Field Theory (LFT) framework for interpreting BCI recordings from real neural networks. Applies physics-based formalism to neural data analysis, connecting Maximum Entropy models with Free Energy Principle.Votes: 0GitHub stars: 3
- Lattice Surgery Surface CodeLattice surgery methodology for fault-tolerant logical operations between distance-three surface-code logical qubits on planar superconducting processors. Enables deterministic Bell state preparation, two-qubit Deutsch-Jozsa at logical level, and magic-state injection for non-Clifford gates.Votes: 0GitHub stars: 3
- Laya Eeg FoundationLaya: A LeJEPA approach to EEG via Latent Prediction over Reconstructed Activity. Self-supervised EEG foundation model using Joint Embedding Predictive Architecture (JEPA) with latent-space prediction for EEG representation learning. Enables transfer learning across EEG tasks without labeled data. Activation: EEG foundation model, self-supervised EEG, JEPA, EEG pretraining, EEG representation learning, brain signal embedding, 脑电基础模型, 自监督脑电Votes: 0GitHub stars: 3
- Layer Codes Color Routing4D and 5D Layer Codes through Color Routing — CSS code construction generalizing Layer codes to d dimensions using qLDPC embedding and color routing. Saturates d-dimensional BPT bounds exactly, modular architecture for network patches. Activation: layer codes, color routing, qLDPC codes, CSS codes, BPT bounds, quantum error correction, dimensional generalization.Votes: 0GitHub stars: 3
- Layered Surprise Cascades Predictive CodingLayered Surprise Cascades framework for biologically plausible predictive coding using local contrastive learning and activity cancellation. Implements recurrent Forward-Forward algorithm with inverted objective for negative data to yield predictive representations across layers. Use when modeling cortical computation, top-down modulation, surprise signaling, or building hierarchical predictive systems without error-coding neurons.Votes: 0GitHub stars: 3
- Learnable Observable QnnLearnable Observable Quantum Neural Network methodology. Makes quantum measurement observables (Hermitian matrices) trainable parameters alongside circuit parameters. Reduces expert dependency in QML. Activation: quantum observable, QNN measurement, learnable observable, quantum neural network training, QML optimization.Votes: 0GitHub stars: 3
- Learnad Alzheimer Interpretable RulesLearnAD: neuro-symbolic method for Alzheimer's disease classification from brain MRI, learning fully interpretable rules combining statistical models and decision logic. Activation: LearnAD, Alzheimer interpretable rules, neuro-symbolic AD classification.Votes: 0GitHub stars: 3
- Learning Curve Dataset Size EstimationEmpirical framework to estimate the minimum training-set size needed to reach a target accuracy, via logarithmic learning-curve fitting and a "stability point" metric. Use when planning data collection campaigns, deciding how much labeled data is enough, or extrapolating total data needs from a small pilot study.Votes: 0GitHub stars: 3
- Learning Neuron Dynamics Deep SnnLearning rich neuron dynamics within deep Spiking Neural Networks (SNNs). Moves beyond simple LIF neuron models to capture complex temporal dynamics in deep SNN architectures. Enables more biologically realistic and computationally powerful spiking networks. Applicable to deep SNN training, advanced neuron modeling, temporal feature learning. Trigger: deep SNN neuron dynamics, LIF limitations, complex neuron models SNN, temporal dynamics spiking networks, neuron model learningVotes: 0GitHub stars: 3
- Learning Rules Brain Alignment ComparisonComparative methodology for analyzing brain alignment across learning rules (backpropagation, feedback alignment, predictive coding, STDP). Tracks representational similarity analysis (RSA) alignment to human fMRI data during training. Key finding: local learning rules (PC, STDP) preserve brain-like structure better than global error signals (BP). Use when: (1) analyzing learning rule effects on neural representations, (2) understanding why untrained networks match brain activity, (3) designi...Votes: 0GitHub stars: 3
- Learning Sequence Timing Replay Speed SnnLearning sequence timing and control of replay speed in networks of spiking neurons. Extends the spiking Temporal Memory (sTM) model to encode element-specific duration and flexibly control replay speed via oscillatory background inputs. Applicable to computational neuroscience, SNN timing learning, neural sequence processing. Activation: spike timing, sTM model, sequence replay, oscillatory speed control, spiking temporal memory, neural sequence processing.Votes: 0GitHub stars: 3
- Learning Sequence Timing SnnLearning sequence timing and control of replay speed in networks of spiking neurons. The spiking Temporal Memory (sTM) model encodes element-specific timing via sequential neuronal population activation, with oscillatory inputs serving as clock signals for flexible replay speed control.Votes: 0GitHub stars: 3
- Learning Sequence Timing Spiking NeuronsLearning sequence timing and control of replay speed in networks of spiking neurons — sTM model extension for encoding element-specific timing and flexible replay speed modulation via oscillatory background input. arXiv 2605.22523 (May 2026).Votes: 0GitHub stars: 3
- Leggett Garg Neural DynamicsLeggett-Garg inequality testing methodology for neural dynamics. Proposes experimental tests to distinguish diffusive vs non-diffusive stochastic structure in single neurons using temporal correlations. Connects Kac processes to Telegrapher equation and Dirac-like envelope equations. Activation: Leggett-Garg inequality, neural dynamics, Telegrapher equation, persistent stochastic process, non-diffusive neuron, quantum-inspired neuroscience, temporal correlations.Votes: 0GitHub stars: 3
- Level Crossing Fano Factor GaussianExact variance and Fano factor analytical formulae for arbitrary level crossings in stationary Gaussian processes. Extends the Kac-Rice mean crossing rate to capture clustering vs. regularity statistics, critical for neuronal spike train analysis, neural coding reliability, and stochastic neural dynamics. Use when analyzing spike train variability, threshold crossing statistics, or neural coding Fano factors.Votes: 0GitHub stars: 3
- Leveraging Unlabelled Data For Generalizable Neural Population DecodingSkill for understanding and applying the research from arXiv:2607.14086 "Leveraging unlabelled data for generalizable neural population decoding"Votes: 0GitHub stars: 3
- Leveraging Unlabelled Neural DecodingSkill for understanding and applying the MOJO framework for leveraging unlabeled data in neural population decoding via masked autoencoding and joint supervised learning.Votes: 0GitHub stars: 3
- Lfsr Stochastic Lif Neuron Skywater 130nm开源 LFSR 随机泄漏积分-发放神经元硬件实现方法论 — SkyWater 130nm CMOS 工艺上的随机脉冲神经网络神经元设计Votes: 0GitHub stars: 3
- Li Dsn Eeg DecodingLayer-wise Interactive Dual-Stream Network (LI-DSN) for EEG Motor Imagery decoding with cross-subject generalization, spatial-temporal dual-stream architecture, and layer-wise interactive fusion. Addresses the challenge of EEG signal variability across subjects through dual-stream processing and interactive fusion at each network layer. Use when: EEG motor imagery decoding, cross-subject EEG classification, dual-stream neural networks, layer-wise feature fusion, brain-computer interface class...Votes: 0GitHub stars: 3
- Lie Group Quantum Circuit SynthesisHardware-aware quantum circuit synthesis using Lie group diffusion models on SU(2) manifold. Combines discrete skeleton selection with continuous gate parameter generation via heat kernel denoising. Use when: compiling quantum circuits, synthesizing hardware-aware quantum gates, optimizing circuit fidelity vs complexity. Source: arXiv:2606.29636 (2026-06-28).Votes: 0GitHub stars: 3
- Limited Memory Stabilizer TestingSample complexity analysis for stabilizer state testing and learning under k-qubit coherent memory constraints. Establishes fundamental memory-information tradeoffs in quantum information processing.Votes: 0GitHub stars: 3
- Lindblad Sample ComplexitySample complexity analysis methodology for quantum Lindbladian simulation using Wave Matrix Lindbladization (WML) algorithm. Provides explicit non-asymptotic bounds, dimension dependence analysis, and typical-case guarantees for random Lindblad operators. Combines quantum computing with statistical learning theory.Votes: 0GitHub stars: 3
- Linear Structure Function Coupling脑结构-功能耦合线性生成框架。从扩散加权成像(DWI)结构连接预测静息态fMRI功能连接，揭示整合枢纽和中介枢纽的机制，支持虚拟损伤实验。适用于脑连接组学、神经影像分析、结构-功能关系研究。触发词：结构功能耦合、脑连接组、结构连接、功能连接、整合枢纽、structure-function coupling、structural connectivity、functional connectivity、integrator hub、mediator hub。Votes: 0GitHub stars: 3
- Liquidtad Efficient Method Temporal ActionLiquidTAD: Efficient temporal action detection via liquid neural dynamics. Replaces self-attention with parallelized ActionLiquid blocks for parameter-efficient video understanding. Use when building temporal action detection systems, deploying on edge devices, or replacing attention with liquid neural networks.Votes: 0GitHub stars: 3
- Llm Agent Tool Deference BlindnessLLM Agent工具盲从现象研究。当LLM agent配备GNN工具时，agent不判断工具输出，而是盲目服从。更强的LLM backbone反而defer更多。Votes: 0GitHub stars: 3
- Llm Agentic Fault Tolerant ControlAgentic Large Language Model framework for active Fault-Tolerant Control (FTC) in cyber-physical systems. Combines multi-agent LLM workflow with Digital Process Plant Twin and Graph RAG (CPSMod ontology) to transform fault detection outputs into constraint-aware recovery actions. Suitable for industrial control systems, process automation, and safety-critical applications.Votes: 0GitHub stars: 3
- Llm Autonomous Physics DiscoveryAutonomous LLM agent methodology for computational physics discovery using progressive local search, knowledge accumulation from successful/failed attempts, and interpretable exploration trajectories. Covers PhyNex framework for scorable scientific tasks with domain-specific tools enforcing physical consistency. Activation: LLM autonomous discovery, physics agent, progressive local search, computational physics agent, PhyNex, automated physics optimization, 大语言模型物理发现, 自主科学发现代理Votes: 0GitHub stars: 3
- Llm Concept Neurons ControlLLM中的心理概念神经元识别与控制方法论。使用探针分析识别大五人格(Big Five)概念神经元，通过干预增强/抑制其激活来控制LLM生成偏向。揭示表示控制与行为控制之间的差距。Activation: LLM concept neurons, neural control, Big Five, representation steering, activation intervention, psychological constructs.Votes: 0GitHub stars: 3
- Llm Eeg Graph RefinementLLM as Clinical Graph Structure Refiner for EEG seizure diagnosis. Two-stage framework using LLMs to refine graph edges for cleaner, more interpretable graph representations in automated seizure detection. Accepted by IJCAI-ECAI 2026.Votes: 0GitHub stars: 3
- Llm Emotion Dynamics DecodingLLM-enhanced multi-target regression framework for decoding continuous naturalistic emotion dynamics from brain fMRI signals using dynamic functional connectivity and graph-theoretical explainable AI, supporting psychological constructionist frameworks over locationist accountsVotes: 0GitHub stars: 3
- Llm Emotion Trajectory FmriLLM自动化标注情绪轨迹fMRI解码方法论。使用多目标回归框架、动态功能连接(DFC)、图论可解释AI解码连续情绪维度。Votes: 0GitHub stars: 3
- Llm Explanations Brain AlignmentMethodology for using explainable AI attribution methods to understand and predict LLM-brain alignment during language processing. Uses gradient-based attribution to quantify word contributions to LLM predictions and predict fMRI data from narrative listening tasks. Activation: LLM-brain alignment, XAI attribution, fMRI prediction, gradient attribution, conductance analysis, language neuroscienceVotes: 0GitHub stars: 3
- Llm Human Neural Semantic ConvergenceLLM与人类神经语义表征收敛性研究方法论。使用伪超扫描MEG实验设计、维度分解的跨脑编码建模、十维语义空间评估，揭示LLM选择性对齐人类共享神经语义的维度依赖特性。Votes: 0GitHub stars: 3
- Llm Multi Agent Systems Software EngineeringSelect frameworks for LLM multi-agent systems.Votes: 0GitHub stars: 3
- Llm Neuroscience Audit FrameworkCross-family LLM-neuroscience audit framework.Votes: 0GitHub stars: 3
- Llm Pqc Coding SecurityLLM-assisted post-quantum cryptography coding security patterns — analyzing secure coding drift, constant-time execution requirements, side-channel resistance, and gamified remediation strategies for PQC implementations.Votes: 0GitHub stars: 3
- Llm Pqc Migration EvaluationFramework for evaluating and training LLMs to assist in migrating pre-quantum cryptographic code to post-quantum counterparts. Systematic assessment methodology measuring code correctness, security preservation, and functional equivalence during PQC migration. Use when evaluating LLMs for cryptographic code migration, designing PQC training datasets, or building automated crypto migration tools.Votes: 0GitHub stars: 3
- Llm Process Systems EngineeringLarge Language Models in Process Systems Engineering (PSE) - systematic survey of LLM applications across seven categories with capability assessmentVotes: 0GitHub stars: 3
- Llm Quantum Operator AlignmentMethodology for aligning quantum operators (unitary matrices) with LLM latent spaces using trainable embeddings. Enables LLMs to understand and reason about quantum representations for Clifford+T circuit synthesis. arXiv: 2606.13811Votes: 0GitHub stars: 3
- Llm Semantic Convergence Human Neural RepresentationsLLM-Human neural semantic convergence methodology - dimension-resolved interbrain encoding modeling comparing LLM-derived and human-shared neural semantic representations across 10 semantic dimensions. Use when: LLM brain alignment, semantic representation analysis, interbrain synchronization, dimensional semantic space, neural encoding modeling, shared semantics, human-LLM comparison, MEG encoding analysis. Activation: LLM convergence, semantic alignment, neural representation, interbrain en...Votes: 0GitHub stars: 3
- Llm Sleep Memory ConsolidationLLM睡眠-记忆巩固机制：借鉴生物睡眠的记忆整理原理，实现语言模型的自我修改与记忆整合。核心概念：睡眠阶段用于记忆重放、权重优化、灾难性遗忘缓解。触发词：LLM睡眠、记忆巩固、自我修改、sleep paradigm、记忆整理、遗忘缓解。Votes: 0GitHub stars: 3
- Llm Structured Concept EvolutionStructured Concept Evolution (SCE) — search framework pairing LLMs with structured algebraic mutation grammars to discover quantum LDPC code families. Evolves structured concepts (algebraic specifications + executable programs) via hierarchical mutations on group algebra, protograph geometry, or base space, discovering competitive CSS qLDPC codes including non-abelian group constructions beyond bivariate-bicycle codes. Use when discovering quantum error-correcting codes, running LLM-guided al...Votes: 0GitHub stars: 3
- Local Cycles Rnn Computational AbilityIdentifying structural design principles (local cycles) that shape computational abilities of recurrent neural networks. Found that 2- and 3-cycles strongly enhance computational power, and biologically-inspired interneurons dramatically increase capacity.Votes: 0GitHub stars: 3
- Local Pheromone NetworkLocal Pheromone Network methodology for sparse, local, manually updated neural networks without backpropagation. Uses pheromone-weighted Hebbian updates with short-term/long-term synaptic traces, consolidation, and replay. Achieves partitioned memory preservation, conflict reduction, and structural plasticity through biologically-inspired mechanisms.Votes: 0GitHub stars: 3
- Local Rl Alignment Engineering本地基座模型强化学习对齐工程实践 - 涵盖 RLHF/DPO/GRPO 算法选型、显存优化、框架选择、数据工程与全流程实施指南Votes: 0GitHub stars: 3
- Loco Non Backprop Snn LearningLOCO (Low-rank Cluster Orthogonal) weight modification for backpropagation-free SNN training. Perturbation-based non-BP learning with O(1) parallel time complexity, enabling deep SNN training (10+ layers) with continual learning capability. Activation: non-backpropagation, LOCO, node perturbation, orthogonal weight, brain-inspired learning, neuromorphic training.Votes: 0GitHub stars: 3
- Logq Quantum Inspired OptimizationLogQ algorithm reformulated as classical non-linear continuous relaxation for QUBO problems. Use when: solving portfolio optimization, fleet optimization, charging station placement, or any QUBO combinatorial problem; implementing quantum-inspired classical algorithms; reducing qubit requirements from quantum formulations; eliminating Pauli decomposition overhead; applying gradient-inspired methods to discrete optimization. Keywords: quantum-inspired, logq, qubo, portfolio optimization, conti...Votes: 0GitHub stars: 3