All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Working Memory Heterogeneous Delays 2026Working memory in recurrent spiking neural networks using heterogeneous synaptic delays (2026-04 update). Enables energy-efficient temporal pattern storage and recall in SNNs.Votes: 0GitHub stars: 3
- Working Memory Heterogeneous DelaysWorking memory implementation in recurrent spiking neural networks using heterogeneous synaptic delays. Models memory as sequential chains of overlapping Spiking Motifs for precise temporal pattern storage and recall. Activation: working memory SNN, heterogeneous delays, spiking motifs, recurrent SNN memory, temporal pattern storage, neuromorphic working memory.Votes: 0GitHub stars: 3
- Zeroth Order Adaptation Forgetting TheoryRandomized shaping theory explaining why zeroth-order (ZO) adaptation forgets less than first-order methods in continual learning. Activation triggers: zeroth-order adaptation, ZO continual learning, randomized shaping, gradient-free adaptation, catastrophic forgetting, low-query adaptationVotes: 0GitHub stars: 3
- Memoryvla Temporal Modeling Robotic ManipulationMemoryVLA++ - Temporal modeling framework for VLA models enabling persistent memory for long-horizon robotic manipulation tasksVotes: 0GitHub stars: 3
- Memorywam Efficient World Action ModelingMemoryWAM introduces persistent memory mechanisms for efficient world-action modeling with world model integration and hippocampal-inspired memory consolidation.Votes: 0GitHub stars: 3
- Memristive Signed Couplings OnnSelf-organized learning in oscillatory neural networks (ONNs) using memristive signed couplings. Inhibitory (negative) weights enable anti-phase attractors, expanding accessible attractor structures beyond purely synchronous couplings for autonomous neuromorphic learning.Votes: 0GitHub stars: 3
- Memristor Reservoir Computing ImageReservoir computing with memristor dynamics for image classification. Studies how memristor intrinsic dynamics reduce network size and parameter overhead in reservoir computing for time-series prediction and image recognition. Trigger words: memristor reservoir computing, image classification reservoir, memristive RC, hardware reservoir image, memristor dynamics preprocessing, echo state network memristor, reservoir image recognition.Votes: 0GitHub stars: 3
- Memristor Snn Interception TaskMemristor-based spiking neural network accelerator for bio-inspired interception tasks - achieving 12.7x energy reduction vs digital SNN (arXiv:2605.31299v1, May 2026).Votes: 0GitHub stars: 3
- Mental Fatigue Balance ControlMental fatigue-induced balance disturbance analysis using clustering-based heterogeneity classification. Investigating individual differences in balance control response to cognitive fatigue through AX-CPT and PVT performance metrics. Activation: mental fatigue, balance control, AX-CPT, psychomotor vigilance task, cognitive fatigue heterogeneity.Votes: 0GitHub stars: 3
- Merlin Photonic QmlMerLin discovery engine for photonic and hybrid quantum machine learning. Embeds linear optical circuit simulation into PyTorch/scikit-learn for end-to-end differentiable training of quantum layers. Use when: (1) building hybrid quantum-classical ML models, (2) reproducing photonic QML benchmarks, (3) designing quantum layer architectures, (4) benchmarking QML against classical baselines, (5) hardware-aware quantum ML testing. Activation: merlin, photonic qml, hybrid quantum machine learning,...Votes: 0GitHub stars: 3
- Mersenne Numbers Doubling Map梅森数与倍角映射的动力学联系研究。通过角度倍角映射动力学框架，无需显式计算M(n)即可求梅森数的因子。提供替代Lucas-Lehmer检验的动力学方法证明大梅森数为合数。适用于大数素性检验、动力系统数论应用。Votes: 0GitHub stars: 3
- Mesoscale Brain Organization脑组织中介尺度结构识别方法论。通过多分辨率技术提取脑连接网络的内聚结构。适用于脑网络模块化、社区检测。触发词：中介尺度、脑组织、模块化、mesoscale、community detection。Votes: 0GitHub stars: 3
- Meta Cognitive ReflectionMeta-cognitive reflection framework for self-improvement based on reasoning review, error analysis, and learning strategy adjustment.Votes: 0GitHub stars: 3
- Meta Cognitive Tool OptimizationMeta-cognitive framework for optimizing tool use in agentic multimodal models - deliberate tool invocation vs internal reasoning arbitration. Use when designing agents that need to decide between using external tools or internal knowledge. Activation: meta-cognitive tool use, deliberate tool invocation, tool arbitration, agentic multimodal models, tool vs reasoning, blind tool invocation.Votes: 0GitHub stars: 3
- Meta Representational Predictive CodingMeta-Representational Predictive Coding (MPC) — encoder-only neuroscience-informed self-supervised learning within the free energy principle, using cross-stream latent prediction and active inference saccade planning instead of backpropagation (arXiv: 2503.21796v2)Votes: 0GitHub stars: 3
- Metabolic Quantum Limit Meg MagnetoencephalographyMetabolic quantum limit to the information capacity of magnetoencephalography - 代谢量子极限作为MEG信息容量的基本约束Votes: 0GitHub stars: 3
- Metabolic Quantum Limit MegMetabolic quantum limit methodology for magnetoencephalography (MEG) — derives technology-independent bounds on brain imaging information capacity using quantum sensing limits and neural metabolism.Votes: 0GitHub stars: 3
- Metacognition As Reward"Metacognition-as-Reward (MaR) — metacognition-inspired RL framework for LLM reasoning. Use when training LLMs to reason better through RL: (1) improving reasoning quality beyond final-answer correctness, (2) providing reward signals for intermediate reasoning behaviors, (3) replacing hand-crafted rubrics with general metacognitive dimensions, (4) training models for process-level reasoning quality.Votes: 0GitHub stars: 3
- Metamorphic Quantum TestingPhysics-based metamorphic testing framework for Variational Quantum Circuits (VQCs). Addresses the oracle problem in quantum testing by deriving test oracles from quantum mechanical properties. Use when: testing VQEs/QAOA circuits, verifying quantum circuit implementations, building quantum software testing infrastructure. Source: MetaMorphQ (arXiv:2606.28742, 2026-06-27).Votes: 0GitHub stars: 3
- Metastable Mind Event SegmentationMetastable Mind framework synthesizing Event Segmentation (ES) and Metastable Neural Activity (MNA) theories. Neural states as fundamental computational units with spatio-temporally nested hierarchy, predictive models, and modular processing boundaries. Activation: metastable, event segmentation, neural states, cognitive segmentation, metastable neural activity, 亚稳态神经状态, 事件分割.Votes: 0GitHub stars: 3
- Metastable Mind Neural StatesMetastable neural states as fundamental computational units of cognition - integrating Event Segmentation theory with metastability framework (arXiv:2605.31473v1, May 2026).Votes: 0GitHub stars: 3
- Metastable Neural States Event SegmentationMetastable neural states as computational units of cognition methodology. Synthesizes event segmentation theory with metastable neural activity, revealing spatio-temporally nested hierarchies and predictive model-driven state transitions. Use when: metastable neural states, event segmentation, neural state hierarchy, cognitive state transitions, predictive processing, naturalistic cognition. arXiv: 2605.31473Votes: 0GitHub stars: 3
- Metis Memory Foundation ModelMetis Memory Foundation Model framework for native memory capabilities in foundation models. Introduces persistent dynamically evolving memory state within backbone and native memory procedures for autonomous information storage/utilization. Use when building AI agents with internalized memory, gradient-free online memory maintenance, or frozen-weight inference with dynamic memory states.Votes: 0GitHub stars: 3
- Microns Cortical Rnn Inductive Biases利用MICrONS功能连接组学数据构建生物合理的RNN。整合皮质几何、解剖连接和功能关系作为归纳偏置，实现更有效的学习和收敛到生物计算的组织原则。Votes: 0GitHub stars: 3
- Miim Cps Anomaly DetectionJoint latent clustering anomaly detection for multimodal cyber-physical systems (CPS). Models normal behaviour under the MIIM assumption set (Massive, Implicit, Imbalanced Multimodality) with explicit Gaussian-mixture mode clustering in latent space, scored without reconstruction residuals. Includes difficulty-stratified fair evaluation protocol with raw point-wise metrics, trivial-detector splits, and prevalence-matched F1.Votes: 0GitHub stars: 3
- Mimic Mjx Neuromechanical EmulationMIMIC-MJX framework for neuromechanical emulation of animal behavior by learning biomechanically grounded neural control policies from kinematics. Trains neural controllers to actuate biomechanical animal models in physics simulation to reproduce real kinematic trajectories. Use for motor control modeling, behavioral neuroscience, and integrative neuroscience research involving animal behavior simulation.Votes: 0GitHub stars: 3
- Mind Omni Brain Vision Language UnifiedMind-Omni unified multi-task framework for Brain-Vision-Language modeling via discrete diffusionVotes: 0GitHub stars: 3
- Mind2drive Eeg Driver IntentionSkill based on the Mind2Drive paper — a framework for predicting driver intentions from EEG signals captured during real-world on-road driving. Covers multi-sensor synchronization, EEG preprocessing for driving contexts, deep learning architecture comparison (12 models), and deployment considerations for brain-computer interface (BCI) systems in vehicles.Votes: 0GitHub stars: 3
- Mindalign Eeg Visual DecodingTri-modal contrastive framework (EEG, vision, language) for zero-shot visual decoding. Achieves 54.1% Top-1 accuracy on 200-way benchmark, massively exceeding prior baselines. Use for: brain-computer interface visual reconstruction, EEG-based image retrieval, non-invasive neural decoding, multimodal brain signal analysis.Votes: 0GitHub stars: 3
- Mine Mechanistically Interpretable Neural EncodingMINE (Mechanistically Interpretable Neural Encoding) — a framework that applies mechanistic interpretability tools from LLMs to vision encoding models, revealing fine-grained functional selectivity at the voxel level in human visual cortex. (arXiv:2605.16468)Votes: 0GitHub stars: 3
- Mine Neural Encoding Mechanistic InterpretabilityMechanistically Interpretable Neural Encoding (MINE) — applying mechanistic interpretability tools (feature attribution, counterfactual editing) to open the black box of voxel-level neural encoding models. Use when: (1) analyzing which image features drive specific voxel responses, (2) generating interpretable descriptions of neural selectivity, (3) performing causal validation of encoding model features, (4) discovering fine-grained functional organization within category-selective brain reg...Votes: 0GitHub stars: 3
- Minimal Network Brain Dynamics Mean FieldInteracting branching model of neural network dynamics with hierarchy of analytical mean-field approximations. Characterizes nonequilibrium phase transitions between disorder and ordered phases, exhibits criticality and self-organized dynamics relevant to brain function. Based on arXiv:2512.22093.Votes: 0GitHub stars: 3
- Mirage Fmri Mental Imagery DecodingMIRAGE methodology — robust multi-modal architecture for translating fMRI-to-image models from seen visual decoding to mental imagery reconstruction. Demonstrates that SOTA on seen images doesn't guarantee SOTA on mental imagery and proposes a multi-modal, multi-loss architecture that excels at both. Use when researching: fMRI visual decoding, mental imagery reconstruction, brain decoding generalization, seen-to-imagery transfer, NSD-Imagery dataset, multi-modal brain decoding, vision model g...Votes: 0GitHub stars: 3
- Mirage Fmri Mental ImageryMIRAGE methodology — robust multi-modal architecture for translating fMRI-to-image models from vision decoding to mental image reconstruction. Uses linear backbone + multi-modal text/image features with diffusion model; achieves SOTA on NSD-Imagery benchmark. Activation: fMRI mental imagery, MIRAGE, brain decoding, image reconstruction, cross-decoding, NSD-ImageryVotes: 0GitHub stars: 3
- Mirage Multimodal Fmri EncodingMIRAGE - Adaptive multimodal gating framework for whole-brain fMRI encoding. Integrates visual, auditory, and linguistic information via native multimodal backbone with layer-wise feature gating. Predicts brain responses to naturalistic audiovisual stimuli across subjects. Use when: (1) Building brain encoding models with multimodal stimuli, (2) Predicting fMRI responses from movies/videos, (3) Integrating visual-auditory-language features for brain prediction, (4) Interpretable modality-spec...Votes: 0GitHub stars: 3
- Ml Clifford Noise ReductionML-guided Clifford noise reduction for Hamiltonian simulations using mid-circuit measurements. Use when optimizing quantum circuit noise, designing stabilizer verification protocols, reducing logical error rates in encoded quantum operations, or applying ML to select optimal quantum verification operators. Covers CliNR framework, symplectic transvection Trotter synthesis, and ML-guided stabilizer selection. Activation: quantum noise reduction, Clifford noise, CliNR, stabilizer verification, m...Votes: 0GitHub stars: 3
- Ml Hybrid Distributed CachingML-hybrid distributed caching methodology combining traditional caching algorithms (LRU, LFU, ARC, TLRU) with lightweight machine learning for predictive eviction and adaptive sizing. Use when: (1) designing cache systems for dynamic environments, (2) selecting caching strategy based on workload characteristics, (3) implementing ML-enhanced eviction/prefetching layers, (4) optimizing cache performance across distributed architectures, (5) benchmarking caching algorithms across hit ratio, late...Votes: 0GitHub stars: 3
- Ml Latent Neural Dynamics SurveyMachine Learning Methods for Studying Latent Neural Activity Dynamics - IJCAI 2026 survey综述机器学习研究神经种群潜伏动力学结构的方法论，涵盖单区域潜伏动力学（LDS/RNN/Neural ODE）、多区域通信、行为对齐建模、神经基础模型（Transformer/扩散模型）Votes: 0GitHub stars: 3
- Ml Qec Threshold OptimizationMachine learning methodology for finding optimal quantum error correction (QEC) thresholds. Combines ML search strategies with quantum error correction analysis to determine noise thresholds where QEC codes break down.Votes: 0GitHub stars: 3
- Ml Quantum Error CorrectionMachine Learning approaches for Quantum Error Correction (QEC). Use when researching, designing, or implementing ML-assisted QEC systems including: (1) diffusion models for error decoding (DiffQEC pattern), (2) reinforcement learning for QEC control and calibration, (3) neural network decoders for surface codes and LDPC codes, (4) loss-biased fault-tolerant architectures, (5) quantum error correction for quantum machine learning (QML). Activation keywords: ML QEC, diffusion model quantum erro...Votes: 0GitHub stars: 3
- Mld Qec DecoderMaximum Likelihood Decoding methodology for CSS quantum error correction codes — reformulates MLD as partition function computation in classical spin models, enabling exact MLD via tensor network contraction and approximate MLD via belief propagation. Connects QEC threshold to statistical phase transition. Use when: designing quantum error correction decoders, analyzing CSS code thresholds, computing MLD for surface/toric codes, applying tensor networks to QEC, or studying statistical mechani...Votes: 0GitHub stars: 3
- Mld Quantum DecodingMaximum Likelihood Decoding of QEC codes — unified survey via statistical mechanics, tensor networks, and AIVotes: 0GitHub stars: 3
- Mle Toolbox Eeg MegMLE-Toolbox: Comprehensive open-source MATLAB toolbox for end-to-end EEG/MEG analysis with source localization, connectivity analysis, and ML classifiers. Activation: MLE-Toolbox, EEG analysis, MEG analysis, source localization, brain network analysis, neuroimaging toolbox.Votes: 0GitHub stars: 3
- Mllm Brain Alignment Task ProbingTask-conditioned probing methodology for evaluating brain alignment of instruction-tuned multimodal LLMs (MLLMs) using fMRI. Activation: brain-MLLM alignment, instruction-tuned MLLM, task-conditioned probing, brain encoding, fMRI-MLLM, voxel-wise encodingVotes: 0GitHub stars: 3
- Mmpo Metacognitive Memory PolicyMeta-Cognitive Memory Policy Optimization (MMPO) for long-horizon LLM agents using Belief Entropy as self-supervised proxy.Votes: 0GitHub stars: 3
- Modal Neural Modality DiscoveryMoDAl (Modality Decorrelation and Alignment) framework for self-supervised neural modality discovery in speech neuroprosthesis. Uses contrastive alignment with LLM text embeddings + decorrelation loss to discover complementary neurolinguistic modalities from multiple brain regions. Key innovation: proves contrastive alignment induces transitive modality coalescence, which decorrelation must counteract. Trigger words: MoDAl, neural modality discovery, speech neuroprosthesis, brain-to-text deco...Votes: 0GitHub stars: 3
- Modern Systems Engineering PatternsModern 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. Use when designing distributed systems, control systems, multi-agent architectures, or cyber-physical systems that require reliability, security, and coordination. Activation keywords: physics-informed control, multi-agent security, distrib...Votes: 0GitHub stars: 3
- Modular Forms Kaneko Zagier ClassificationClassification methodology for modular forms of rational weight satisfying the Kaneko-Zagier modular differential equation, using hypergeometric transformation and monodromy analysis.Votes: 0GitHub stars: 3
- Modular Memristor Synaptic Plasticity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。Votes: 0GitHub stars: 3
- Modular Nahm Sums ConstructionMethodology for constructing and analyzing modular Nahm sums in number theory, including lift-dual operations and rank extensionsVotes: 0GitHub stars: 3