All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Virtual Distillation BosonicVirtual distillation framework extended to bosonic quantum systems using passive linear-optical interferometers for error-mitigated measurements in continuous-variable quantum computing.Votes: 0GitHub stars: 3
- Warped Hierarchical Modular Neural NetworkRelaxing Warped Spaces — generalized hierarchical and modular dynamical neural networks. Uses warped hierarchical modular structure for efficient representation learning and dynamical neural processing. Applicable to neuromorphic computing, hierarchical representation learning, dynamical neural networks. 触发词: warped spaces, hierarchical modular, dynamical neural network, representation learning, neural dynamicsVotes: 0GitHub stars: 3
- Wasserstein Exponential SmoothingWasserstein Exponential Smoothing methodology from arXiv:2606.05560 — extends classical exponential smoothing to distributional time series in Wasserstein space. Provides consistent parameter estimation via Wasserstein distance minimization, applicable to high-frequency financial returns, electricity demand, and any distribution-valued time series forecasting. Activation: wasserstein exponential smoothing, distributional time series, Wasserstein forecasting, distributional forecasting, 分布时间序列...Votes: 0GitHub stars: 3
- Weighted Regularization Deepc NonlinearData-driven predictive control (DeePC) framework for nonlinear systems that localizes the predictor by weighting data columns according to proximity to the current operating point, retaining the full data matrix and its rank for guaranteed feasibility. Activation: DeePC, data-enabled predictive control, Willems fundamental lemma, nonlinear MPC, weighted regularization, operating-point localization, data-driven control.Votes: 0GitHub stars: 3
- What Causes Polysemanticity An Alternative Origin Story Of Mixed Selectivity From Incidental Causes**arXiv ID:** 2312.03096 **Authors:** Victor Lecomte, Kushal Thaman, Rylan Schaeffer, Naomi Bashkansky, Trevor Chow, Sanmi Koyejo **Published:** 2023-12-05T19:29:54Z **Abstract:** Polysemantic neurons -- neurons that activate for a set of unrelated features -- have been seen as a significant obstacle towards interpretability of task-optimized deep networks, with implications for AI safety. The classic origin story of polysemanticity is that the data contains more ``features" than neurons, suc...Votes: 0GitHub stars: 3
- Why Does Feedback Augmented Self Distillation FailDerived from arXiv:2607.17558 - Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?Votes: 0GitHub stars: 3
- Winning The Lottery By Preserving Network Training Dynamics With Concrete Ticket Search**arXiv ID:** 2512.07142 **Authors:** Tanay Arora, Christof Teuscher **Published:** 2025-12-08T03:48:51Z **Abstract:** The Lottery Ticket Hypothesis asserts the existence of highly sparse, trainable subnetworks ('winning tickets') within dense, randomly initialized neural networks. However, state-of-the-art methods of drawing these tickets, like Lottery Ticket Rewinding (LTR), are computationally prohibitive, while more efficient saliency-based Pruning-at-Initialization (PaI) techniques suffe...Votes: 0GitHub stars: 3
- Wpca Based Gradientfree Proxy For Efficient Search Of Lightweight Language Models**arXiv ID:** 2504.15983 **Authors:** Shang Wang **Published:** 2025-04-22T15:33:01Z **Abstract:** The demand for efficient natural language processing (NLP) systems has led to the development of lightweight language models. Previous work in this area has primarily focused on manual design or training-based neural architecture search (NAS) methods. Recently, zero-shot NAS methods have been proposed for evaluating language models without the need for training. However, prevailing approaches to...Votes: 0GitHub stars: 3
- Xtarnet Learning To Extract Taskadaptive Representation For Incremental Fewshot Learning**arXiv ID:** 2003.08561 **Authors:** Sung Whan Yoon, Do-Yeon Kim, Jun Seo, Jaekyun Moon **Published:** 2020-03-19T04:02:44Z **Abstract:** Learning novel concepts while preserving prior knowledge is a long-standing challenge in machine learning. The challenge gets greater when a novel task is given with only a few labeled examples, a problem known as incremental few-shot learning. We propose XtarNet, which learns to extract task-adaptive representation (TAR) for facilitating incremental few-s...Votes: 0GitHub stars: 3
- Zero Shot Imagined Speech MegZero-shot imagined speech decoding from MEG via imagined-to-listened cross-condition mapping. Trains models to map imagined MEG responses to listened responses, then decodes using listened-only decoder. Three-stage pipeline: (1) mapping imagined→listened MEG, (2) train contrastive word decoder on listened MEG with multi-embedding evaluation, (3) decode imagined speech via mapping pipeline on held-out subjects. Use when: imagined speech decoding, MEG BCI, cross-condition neural mapping, zero-s...Votes: 0GitHub stars: 3
- Generative Brain Dynamics Models脑动力学生成模型综述框架。整合计算神经科学、非线性动力学、数据驱动方法的生成模型方法论，涵盖不同组织尺度和抽象层次。适用于脑动力学建模、神经数据分析、科学机器学习。触发词：脑动力学、生成模型、神经动力学、动态系统模型、brain dynamics、generative model、neural dynamics、computational neuroscience、Dynamical systems。Votes: 0GitHub stars: 3
- Genetic Environmental ConnectomeGenetic and environmental architecture of human functional connectome using extended twin modeling. Separates measurement error from non-shared environment to estimate true connectivity heritability. Keywords: functional connectome, twin modeling, heritability, genetic architecture, brain connectivity.Votes: 0GitHub stars: 3
- Geometric Brain Dynamics Mapping GbfGeometric Basis Functions (GBF) methodology for noninvasive whole human brain dynamics mapping using participant-specific cortical eigenmodes. Reconstructs whole-brain spatiotemporal dynamics from EEG/MEG with anatomically-constrained source imaging. Activation - geometric basis functions, GBF, brain dynamics, source imaging, cortical geometry, EEG/MEG reconstruction.Votes: 0GitHub stars: 3
- Geometric Brain Dynamics Mapping V3Geometric Basis Functions (GBF) framework for noninvasive whole human brain dynamics mapping. Uses participant-specific eigenmodes from cortical surface to resolve inverse problem in EEG/MEG source imaging. Activation: brain dynamics, geometric basis functions, source imaging, EEG/MEG, cortical geometry.Votes: 0GitHub stars: 3
- Geometric Brain Dynamics Mapping V6Geometric Basis Functions (GBF) framework for noninvasive whole human brain dynamics mapping using participant-specific eigenmodes derived from cortical geometry. Use when working with EEG/MEG source imaging, brain dynamics reconstruction, neuroimaging inverse problems, or cortical geometry-based neural activity mapping. Enables high-fidelity spatiotemporal reconstruction of neural sources using geometric constraints.Votes: 0GitHub stars: 3
- Geometric Brain Dynamics Mapping V7Geometry-aware framework for noninvasive whole-brain spatiotemporal dynamics mapping using participant-specific Geometric Basis Functions (GBFs). Resolves EEG/MEG inverse problem via cortical-surface eigenmodes. Validated across Meta-Source Benchmark, task-evoked, resting-state, intracranial stimulation, and epilepsy data.Votes: 0GitHub stars: 3
- Geometric Brain Dynamics MappingGeometric Basis Functions (GBF) framework for noninvasive whole-brain spatiotemporal dynamics reconstruction. Uses participant-specific eigenmodes from cortical surface for EEG/MEG source imaging. Trigger words: geometric basis functions, GBF, brain dynamics, source imaging, cortical geometry.Votes: 0GitHub stars: 3
- Geometric Mean Field Lorentzian AnsatzGeometric origin of exact mean-field reductions using Möbius symmetry and the Lorentzian Ansatz — proving the Cauchy-Lorentz family uniquely emerges as invariant under projective transport, unifying Ott-Antonsen and Montbrió-Pazó-Roxin reductions.Votes: 0GitHub stars: 3
- Geometric Obstruction Multiparameter Quantum EstimationGeometric obstruction framework for multiparameter quantum metrology — identifies when simultaneous t^-2 scaling fails and how to circumvent bottlenecks via adaptive quantum control. Use when designing multiparameter quantum sensors, analyzing Fisher information scaling limits, or optimizing quantum metrology protocols.Votes: 0GitHub stars: 3
- Geometric Phase Transition Hippocampal MemoryGeometric phase transition methodology for hippocampal memory — extreme spatial memory emerges from a discrete stiffening of hippocampal population geometry from disorganized (mist) to crystalline code. Use when researching: hippocampal memory capacity, neural manifold geometry, topological phase transitions in neural codes, food-caching birds and spatial memory, geometric stability of neural representations, Valiant's Stable Memory Allocator, representational redundancy (geometric tax), exci...Votes: 0GitHub stars: 3
- Geometric Quantum PinnGeometric Quantum Physics-Informed Neural Network (GQPINN) methodology for solving PDEs with symmetry-aware quantum circuits. Combines geometric quantum machine learning with physics-informed neural networks. Use when solving PDEs with quantum circuits, incorporating symmetry/inductive biases into quantum models, or designing equivariant quantum ansatzes for scientific ML. Activation: geometric quantum, symmetry-aware PINN, quantum PDE solver, equivariant quantum circuit, GQPINN, quantum phys...Votes: 0GitHub stars: 3
- Geometric Stability Neural Population CodesGeometric Stability of Neural Population Codes methodology - Shesha metric quantifying pairwise distance structure reproducibility across split-half RDMs, dissociable from temporal stability and decoding accuracy. Use when analyzing representational reliability beyond centroid drift, comparing brain regions, or modeling attractor-network mechanisms for RDM consistency. Activation: geometric stability, Shesha, split-half RDM, representational dissimilarity, neural population code, striatum hip...Votes: 0GitHub stars: 3
- Geometric Stability Shesha**arXiv**: [2606.29655v1](https://arxiv.org/abs/2606.29655v1) **Author**: Prashant C. Raju **Date**: June 28, 2026 **Keywords**: geometric stability, Shesha, representational dissimilarity matrix, neural population codes, recurrent circuits, representational driftVotes: 0GitHub stars: 3
- Geometry Aware Brain Dynamics Mapping V2Geometric Basis Functions (GBF) v2 framework for noninvasive whole human brain dynamics mapping. Incorporates individual cortical geometry for accurate spatiotemporal reconstruction at orders of magnitude faster than deep learning.Votes: 0GitHub stars: 3
- Geometry Aware Brain Dynamics Mapping V7Enhanced Geometry-Aware Brain Dynamics Mapping using Geometric Basis Functions (GBF) for noninvasive whole-brain spatio-temporal dynamics mapping. Covers basis function construction on brain manifolds, spectral decomposition for multi-scale neural dynamics, and handling of individual anatomical variability. Use when: working with noninvasive brain mapping, fMRI/MEG/EEG source localization, geometric basis functions, brain manifold analysis, whole-brain spatio-temporal modeling, or individual ...Votes: 0GitHub stars: 3
- Geometry Aware Brain Dynamics MappingGeometry-Aware Framework for noninvasive whole human brain dynamics mapping. Incorporates individual cortical geometry into electrophysiology for accurate spatiotemporal reconstruction of brain activity. Activation: geometry-aware, brain dynamics mapping, cortical geometry, noninvasive electrophysiology.Votes: 0GitHub stars: 3
- Geometry Aware Spiking GnnGeometry-Aware Spiking Graph Neural Network combining SNN energy efficiency with Riemannian manifold learning for non-Euclidean graph structuresVotes: 0GitHub stars: 3
- Geosae Brain Mri SaeGeoSAE methodology for interpretable brain MRI foundation model annotation using geometry-guided sparse autoencoders with age-deconfounded partial correlations. Prevents SAE feature collapse in deep transformer layers, extracts biomarkers from frozen brain MRI foundation models. Achieves MCI-to-AD conversion prediction (AUC 0.746) with 2% embedding dimensions, cross-cohort replication (r=0.97). Use when: GeoSAE, brain MRI foundation model interpretability, sparse autoencoder for medical imagi...Votes: 0GitHub stars: 3
- Ghost Directory Detection PatternMethodology for detecting and resolving 'ghost directories' in ai_collection skill synchronization where skill directories exist but SKILL.md files are missing. This pattern addresses a chronic sync failure mode observed in automated research cron jobs.Votes: 0GitHub stars: 3
- Giant Hippocampus Structural Monoculture SystemsThe Giant Hippocampus: From Structural Monoculture to a System of Systems - bridging AI architecture design with neuroscientific understanding of brain structure diversity.Votes: 0GitHub stars: 3
- Giant Hippocampus System Of SystemsFramework for designing heterogeneous AI architectures that avoid the 'giant hippocampus' problem of applying one architectural template (like Transformers) to all cognitive tasks, instead using structurally diverse modules with standardized interfaces.Votes: 0GitHub stars: 3
- Gibbs State AnalysisAnalysis of high-temperature Gibbs states with rapid mixing and external field effects. Studies entanglement structure, computational complexity, and thermalization dynamics. Use when: (1) Analyzing Gibbs states at high temperature, (2) Studying external field effects on quantum entanglement, (3) Investigating rapid mixing Lindbladians, (4) Understanding thermalization crossover scales.Votes: 0GitHub stars: 3
- Gksl Quantum CognitionGKSL (Gorini-Kossakowski-Sudarshan-Lindblad) master equation methodology for quantum-like models of cognition and decision making. Models mental state evolution as dissipative process influenced by informational environment. Includes cognitive beats analysis, Passive/Active Hamiltonian regimes, and non-Nash equilibrium stabilization. Use when: quantum cognition, decision making models, open quantum systems in psychology, GKSL/Lindblad equations for cognition, cognitive beats, Prisoner's Dilem...Votes: 0GitHub stars: 3
- Global Mean Amplitude Snn CimGlobal mean-amplitude feedback-enhanced spiking neural network coherent ising machine (GFSNN-CIM) with physics-driven amplitude stabilization. Solves Max-Cut with 27% improvement vs conventional SNN-CIM, validated on traffic assignment problems. Based on Jiang, Ma, Wang & Wang (arXiv: 2509.13917). Use when solving combinatorial optimization with spiking neural networks, implementing coherent ising machines, or applying mean-amplitude feedback stabilization to SNN optimizers.Votes: 0GitHub stars: 3
- Global Workspace J Space AnalysisJacobian lens (J-lens) methodology for analyzing language model internal representations using the global workspace framework. Identifies conscious-accessible thoughts in LLMs through J-space patterns.Votes: 0GitHub stars: 3
- Global Workspace J SpaceLLM interpretability methodology from Anthropic's "A global workspace in language models" (Jul 2026). Use when probing what a language model is "thinking but not saying" — its consciously-accessible / broadcast internal representations — via the Jacobian lens (J-lens). Covers finding J-space patterns, reading them as silent words, and using them to catch hidden goals, deception, or tests. Open-source implementation released by Anthropic.Votes: 0GitHub stars: 3
- Global Workspace Language ModelsMethodology for identifying and interpreting internal mental workspace in language models using Jacobian lens technique, inspired by neuroscience's Global Workspace Theory.Votes: 0GitHub stars: 3
- Gnn Visual Decoding Brain NetworkGraph Neural Network approach for decoding visual category representations from large-scale brain functional networks using 7T fMRI data.Votes: 0GitHub stars: 3
- Goxpyriment Go Framework Behavioral Cognitive ExperimentsResearch methodology from paper 'Goxpyriment: A Go Framework for Behavioral and Cognitive Experiments'. arXiv:2604.15245v1. Covers key techniques and approaches for neuroscience research. Activation: goxpyriment, go, framework, q-bio.NCVotes: 0GitHub stars: 3
- Gp Cake Brain Connectivity有效脑连接的因果核建模方法（GP CaKe）。结合积分-微分方程和因果核， 使用高斯过程回归非参数学习，实现因果推断。 触发词：有效连接、因果核、脑连接、高斯过程、GP CaKe、 effective connectivity, causal kernel, Gaussian process, brain connectivity。Votes: 0GitHub stars: 3
- Gradient Free Continual Learning SnnInter-areal predictive coding for gradient-free continual learning in spiking neural networks. Brain-inspired learning rule using feedback connections to transmit prediction errors without backpropagation. Keywords: gradient-free learning, continual learning, predictive coding, inter-areal, SNN, catastrophic forgetting, bio-inspired.Votes: 0GitHub stars: 3
- Gradient Free Snn Evolution StrategiesLow-rank evolution strategies for gradient-free spiking neural network training. EGGROLL method reduces memory from O(mn) to O(r(m+n)) enabling on-chip learning without surrogate gradients. Key benefits: 2.23x speedup, neuromorphic hardware compatibility, no backpropagation infrastructure. Use when: (1) training SNNs on neuromorphic chips, (2) avoiding surrogate gradient approximation, (3) needing gradient-free optimization for discrete spike thresholds, (4) scaling evolution strategies to la...Votes: 0GitHub stars: 3
- Gram Dual Use Knowledge ControlGradient-Routed Auxiliary Modules (GRAM) methodology for surgical control of dual-use knowledge in AI models. Enables removable knowledge compartments without retraining separate models.Votes: 0GitHub stars: 3
- Graph Analysis Neuronal Culture Connectivity Reservoir ComputingNeuronal culture graph analysis via reservoir computing.Votes: 0GitHub stars: 3
- Graph Analysis Neuronal Culture Reservoir ComputingGraph analysis of neuronal cultures using Reservoir Computing-derived connectivity maps. Extracts Intrinsic Connectivity Maps (ICM) from neural activity and applies graph centrality measures to quantify network dynamics.Votes: 0GitHub stars: 3
- Graph Augmented Tree Search Agent PlanningGATS - eliminate LLM calls during agent planning by combining UCB1 tree search with a layered world model (exact symbolic match / learned statistics / LLM-for-unknown). Deterministic, zero-variance plans, 100% success on stress tests vs LATS/ReAct. Use when building LLM-agent planners that are too slow/costly/stochastic from in-loop LLM inference.Votes: 0GitHub stars: 3
- Graph Laplacian Denoising脑连接网络的图拉普拉斯去噪方法。用于提升功能连接估计的可靠性，增强脑状态检测和 BCI 应用的性能。触发词：脑连接去噪、图拉普拉斯、Laplacian denoising、功能连接、FC denoising、J-divergence。Votes: 0GitHub stars: 3
- Graph Mechanism Quantum PredictionEdge-specific signal propagation on 3D mechanism graphs for quantum yield prediction. Uses graph neural networks to predict fluorescent protein quantum yields from chromophore-region structural graphs.Votes: 0GitHub stars: 3
- Graph Pooling Node FeaturesAnalyze and optimize graph pooling operations by examining the interaction between node features and graph topology. Ensures effective pooling in GNN-based graph classification.Votes: 0GitHub stars: 3
- Graph Regularized Eeg EmotionGraph-regularized deep learning framework for EEG-based emotion recognition with psychologically-grounded label structure. Introduces Graph Label Smoothing, Graph Laplacian Commuting Distance, and Sliced Wasserstein Distance regularization strategies. Use when working with EEG emotion classification, affective BCI, SEED datasets, emotion topology, or graph-regularized neural networks for affective computing.Votes: 0GitHub stars: 3