All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Spacetime Continuous Pde Forecasting Using Equivariant Neural Fields**arXiv ID:** 2406.06660 **Authors:** David M. Knigge, David R. Wessels, Riccardo Valperga, Samuele Papa, Jan-Jakob Sonke, Efstratios Gavves, Erik J. Bekkers **Published:** 2024-06-10T11:49:11Z **Abstract:** Recently, Conditional Neural Fields (NeFs) have emerged as a powerful modelling paradigm for PDEs, by learning solutions as flows in the latent space of the Conditional NeF. Although benefiting from favourable properties of NeFs such as grid-agnosticity and space-time-continuous dynamics ...Votes: 0GitHub stars: 3
- Spark Modular Spiking Neural Networks**arXiv ID:** 2602.02306 **Authors:** Mario Franco, Carlos Gershenson **Published:** 2026-02-02T16:36:58Z **Abstract:** Nowadays, neural networks act as a synonym for artificial intelligence. Present neural network models, although remarkably powerful, are inefficient both in terms of data and energy. Several alternative forms of neural networks have been proposed to address some of these problems. Specifically, spiking neural networks are suitable for efficient hardware implementations. Howe...Votes: 0GitHub stars: 3
- Sparse Neural Connectivity RecoveryCovariance-based method with Granger-causality refinement for recovering sparse neural connectivity from partial measurementsVotes: 0GitHub stars: 3
- Sparse Weight Decomposition Circuit ExtractionSparse Weight Decomposition (SWD) for efficient circuit extraction from pretrained transformers. Reparameterizes linear projections by factorizing weight matrices into two sparse factors with shared intermediate coordinates as circuit units.Votes: 0GitHub stars: 3
- Spatial Neighboring Scattering TransformSpatial Neighboring Scattering Transform (SNST) — a wavelet-scattering-based cross-channel amplitude-coupling measure for EEG connectivity that captures amplitude-envelope and cross-frequency coupling, robust to volume conduction where phase-sync fails. Use when building EEG/fNIRS functional connectivity pipelines, comparing against PLI/wPLI, or extracting inter-regional amplitude-domain dependence.Votes: 0GitHub stars: 3
- Specbox Speculative Sandbox SchedulingRuntime framework for speculative sandbox preallocation and scheduling in LLM agent serving environments to optimize resource utilization and reduce tail latency.Votes: 0GitHub stars: 3
- Spectral Anatomy Quantum KernelsSpectral entropy diagnostic S(K)/log n for quantum Gaussian process kernels. Unified framework showing dequantization and posterior pathologies governed by same quantity. Proves Cauchy-Schwarz tail bound on Nystrom error, variance-contraction identity, target-dependent optimal entropy. Verified on IBM Heron hardware. Activation: quantum Gaussian process, spectral entropy, quantum kernel diagnostic, Nystrom approximation, kernel Gram matrix, quantum dequantization, Bach degrees of freedomVotes: 0GitHub stars: 3
- Spectral Ot Functional AlignmentSpectralOT — a geometry-aware, spectral optimal-transport functional alignment method for fMRI that embeds cortical surface geometry (Laplace-Beltrami eigenmodes) into the alignment cost to regularize cross-subject alignment while preserving anatomical structure. Use when building population-level brain decoders, doing cross-subject fMRI alignment, or need a fast geometry-preserving alternative to Hyperalignment / Riemannian alignment. Trigger words: functional alignment, cross-subject decodi...Votes: 0GitHub stars: 3
- Spectral Phase Transitions Nn LearningSpectral phase transitions and trainability in neural network learning dynamics methodology. Formulates NN training as stochastic evolution of random matrix ensembles, showing BBP (Baik-Ben Arous-Péché) transitions during SGD where isolated eigenvalues detach from random bulk. Derives phase diagram of trainability governed by step size and initial weight variance. Links spectral analysis to representation formation, optimisation hyperparameters, and generalization. Use when: analyzing neural ...Votes: 0GitHub stars: 3
- Spectral Surgery Quantum State TransferSpectral surgery methodology for high-fidelity quantum state transfer in XX spin chains. Analytic construction that interpolates between Krawtchouc (perfect transfer) and homogeneous chains, capping coupling strengths while maintaining high transfer fidelity. (arXiv:2412.02321)Votes: 0GitHub stars: 3
- Spectral Theory Neuronal Population DynamicsSpectral theory framework for analyzing population density dynamics of spiking neurons with finite refractory time. Provides rigorous operator-theoretic methods for studying neuronal population stability, oscillatory modes, and transfer functions. Use when analyzing computational neuroscience models involving refractory periods, population dynamics, or spectral decomposition of neural systems.Votes: 0GitHub stars: 3
- Spectralot Functional AlignmentMethod for geometry-aware functional alignment of fMRI data using SpectralOT to improve cross-subject decoding by embedding cortical geometry into Laplace-Beltrami eigenmodes.Votes: 0GitHub stars: 3
- Specula Formal Specifications Model CheckingAutonomous agentic system for generating formal specifications and model checking of system code using LLM-based coding agents.Votes: 0GitHub stars: 3
- Spike Yolo Automotive PerceptionFirst comprehensive evaluation of SNNs for real-world automotive multi-object detection and tracking using SpikeYOLO transfer learning. Achieves mAP 0.937 (KITTI) and 0.771 (BDD100K MOT2020) for detection, HOTA 0.701/0.445 for tracking — competitive with conventional DL, with energy-efficient edge deployment. arXiv:2607.04921Votes: 0GitHub stars: 3
- Spikedecoder Snn Gpt ArchitectureSpikeDecoder is the first fully spiking neural network (SNN) implementation of the Transformer decoder architecture for natural language processing, achieving 87-93% theoretical energy reduction compared to ANN baselines.Votes: 0GitHub stars: 3
- Spikerestormer Unified Event ReasoningSpikeRestormer methodology for energy-efficient all-in-one image restoration using Spiking Neural Networks with unified event reasoning. Solves the challenge of applying SNNs to static images by generating internal spike events for degradation perception and restoration construction. Use when working with SNN-based image restoration, energy-efficient computer vision, or neuromorphic computing for static image processing.Votes: 0GitHub stars: 3
- Spiking Neural Network AnalysisAnalyze Spiking Neural Network (SNN) papers, extract technical patterns from knowledge graph, and identify reusable research methodologies for neuromorphic computing.Votes: 0GitHub stars: 3
- Spikingnav Robust Embodied NavigationSpikingNav framework for robust embodied navigation using spiking neural networks. Implements Spiking Sensing Encoder (SSE) and Spiking Policy Network (SPN) for energy-efficient, robust indoor navigation on neuromorphic hardware. Use when working with embodied AI agents, robotics navigation, spiking neural networks for real-world applications, or neuromorphic computing deployment.Votes: 0GitHub stars: 3
- Splitting Variational Quantum AlgorithmOperator-splitting variational quantum algorithm (sVQA) for simulating nonlinear quantum equations on quantum computers. Decomposes state-dependent nonlinear evolution into linear substeps (implementable as fixed unitaries) and nonlinear variational corrections (measurement-based). Use when: (1) simulating nonlinear differential equations on quantum hardware, (2) implementing nonlinear quantum dynamics via VQA, (3) handling state-dependent interactions that cannot be unitary, (4) designing op...Votes: 0GitHub stars: 3
- Squeezed State Quantum Randomness GenerationClosed-form Shannon-rate methodology for semi-device-independent quantum randomness generation using squeezed-coherent BPSK sources. Derives analytical bounds on certified randomness rates accounting for detector side information. Applicable to quantum key distribution, medical data security, and cryptographic systems. Activation: quantum randomness generation, squeezed state QRNG, semi-device-independent, BPSK quantum, certified randomness, Shannon rate quantumVotes: 0GitHub stars: 3
- Stark Units Sic OverlapsNumber-theoretic characterization of SIC-POVM overlap units via Stark units from ray class fields. Bridges algebraic number theory (Stark units, ray class fields, Shintani-Faddeev cocycle) with quantum information (SIC-POVM geometry, mutual scalar products). Activation: SIC-POVM overlaps, Stark units, ray class fields, Shintani-Faddeev cocycle, algebraic number theory quantum, SIC geometryVotes: 0GitHub stars: 3
- State Dependent Observation Noise Active InferenceState-Dependent Observation Noise methodology that reintroduces epistemic value in Linear-Gaussian Active Inference models. This skill provides the mathematical framework and implementation guidance for restoring curiosity-driven behavior in Gaussian agents by introducing state-dependent observation noise covariance R(x). Use when working with active inference, Bayesian filtering, dual control theory, or neural dynamics models where epistemic drive has been lost in standard linear-Gaussian fo...Votes: 0GitHub stars: 3
- Stationary Covariance Spectra Non Normal DynamicsFree probability framework for analyzing stationary covariance spectra in discrete-time non-normal random recurrent neural networks. Provides closed-form functional equations for eigenvalue distributions and critical regime behavior.Votes: 0GitHub stars: 3
- Stationary Covariance Spectra Non NormalFree-probability framework for deriving closed functional equations of stationary covariance spectra in discrete-time non-normal random recurrent dynamics, enabling analysis of tail eigenvalues in critical regime.Votes: 0GitHub stars: 3
- Statistical Quantum MeasurementStatistical interpretation framework unifying algebraic quantum mechanics and quantum probability theory — links observable algebras to measurement statistics for foundations of quantum physics. Use when: analyzing measurement procedures statistically, bridging algebraic and probabilistic formulations of quantum mechanics, studying quantum observables as statistical functionals, or developing measurement-based interpretations of quantum theory.Votes: 0GitHub stars: 3
- Statistical Validation In Cultural Adaptations Of Cognitive Tests A Multi Regional Systematic Review**arXiv ID:** 2504.13495 **Authors:** Miit Daga, Priyasha Mohanty, Ram Krishna, Swarna Priya RM **Published:** 2025-04-18T06:25:02Z **Abstract:** This systematic review discusses the methodological approaches and statistical confirmations of cross-cultural adaptations of cognitive evaluation tools used with different populations. The review considers six seminal studies on the methodology of cultural adaptation in Europe, Asia, Africa, and South America. The results indicate that proper adapt...Votes: 0GitHub stars: 3
- Statistically Significant Stopping Of Neural Network Training**arXiv ID:** 2103.01205 **Authors:** J. K. Terry, Mario Jayakumar, Kusal De Alwis **Published:** 2021-03-01T18:51:16Z **Abstract:** The general approach taken when training deep learning classifiers is to save the parameters after every few iterations, train until either a human observer or a simple metric-based heuristic decides the network isn't learning anymore, and then backtrack and pick the saved parameters with the best validation accuracy. Simple methods are used to determine if a ne...Votes: 0GitHub stars: 3
- Stdp Bernoulli Message PassingSTDP驱动的Bernoulli消息传递脉冲神经网络。使用脉冲时序依赖可塑性训练SNN实现贝叶斯推理的消息传递，支持因子图实现和不可靠信道信号传输。适用于神经形态计算、贝叶斯推理、编码理论。触发词：STDP消息传递、贝叶斯推理、脉冲神经网络、因子图、Bernoulli消息、spike-timing-dependent plasticity、Bayesian inference、message passing、factor graph。Votes: 0GitHub stars: 3
- Stein Variational Uncertainty MpcStein variational distributionally robust controller for nonlinear systems with latent parametric uncertainty. Uses particle-based approximation of task-dependent uncertainty distribution. Use when: (1) Designing MPC with parameter uncertainty, (2) Implementing uncertainty-adaptive model predictive control, (3) Building distributionally robust controllers for nonlinear systems, (4) Handling latent parametric uncertainty, (5) Developing particle-based uncertainty quantification methods.Votes: 0GitHub stars: 3
- Stimulus Evoked Network Dynamics OrganoidsGraph-computational framework for analyzing stimulus-evoked propagation dynamics in human cortical organoids using HD-MEA recordings. Includes stimulus-conditioned functional graphs, graph-constrained dynamical models, biological message-passing principles, and longitudinal depression analysis.Votes: 0GitHub stars: 3
- Stl Parameter Synthesis NonlinearSynthesize parameters for nonlinear dynamical systems that robustly satisfy continuous-time Signal Temporal Logic (STL) specifications over uncertain initial conditions. Combines gradient-based optimization with set-based reachability verification for provable satisfaction guarantees. Activation: STL parameter synthesis, signal temporal robustness, formal methods control, reachability verification, nonlinear optimal control, interpretable constraints.Votes: 0GitHub stars: 3
- Stp Stabilizes Goal Conditioned DynamicsShort-Term Synaptic Plasticity (STP) stabilizes goal-conditioned dynamics in PFC-inspired reservoir model for multistep goal-directed action planning. Preserves action-relevant goal information under noise with 89.2% success rate vs 49.5% without STP. Activation: short-term synaptic plasticity, goal-conditioned dynamics, reservoir computing, PFC model, goal-directed planning, dynamic connectivity, facilitation-dominant STP.Votes: 0GitHub stars: 3
- Strain Controlled Topological QuantumControl and stabilize topological Majorana bound states using spatially nonuniform strain in superconductor-semiconductor heterostructures. Covers strain-tuned phase boundaries, disorder-induced psABS to MBS conversion, and position-dependent topological mass framework. Activation: strain-controlled quantum, Majorana bound states, topological quantum computing, Andreev bound states, superconductor-semiconductor heterostructure, Bogoliubov-de Gennes simulation.Votes: 0GitHub stars: 3
- Streamhoi Interaction Aware Temporal Memory AdaptaSkill generated from arXiv paper 2607.20174: StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video GenerationVotes: 0GitHub stars: 3
- Structagentharnesslong HorizondigitalagentswithuniResearch paper: StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure. Brief summary of key findings and contributions.Votes: 0GitHub stars: 3
- Structure Aware Variance Reduction HamiltonianStructure-aware variance reduction methodology for unbiased randomized Hamiltonian simulation. Combines classical variance reduction with randomized product-formula estimators to achieve 70-96% sampling cost reductions in tensor-network simulations. Use when implementing randomized Hamiltonian simulation, optimizing quantum circuit sampling, reducing Trotter discretization errors, or analyzing non-commutative Hamiltonian dynamics.Votes: 0GitHub stars: 3
- Stsbench DatasetA skill for understanding and using the STSBench dataset for modeling neuronal activity in the dorsal stream of primate visual cortex. Based on arXiv:2607.15631.Votes: 0GitHub stars: 3
- Stuart Landau Oscillator Reduction TheoryExact low-dimensional reduction theory for populations of Stuart–Landau oscillators, reducing N-oscillator systems to 3D or 7D systems while preserving amplitude-dependent collective dynamics like clustering and chaos.Votes: 0GitHub stars: 3
- Subjective Functions 251215948A skill for modeling subjective experiences as emergent properties of neural processes based on the mathematical framework of subjective functions. Use this skill when you need to bridge objective neural measurements with subjective reports, model endogenous objective functions, or study consciousness in biological and artificial systems.Votes: 0GitHub stars: 3
- Supertrust Foundational Alignment Mutual Trust Must Replace Permanent Control For Safe Superintelligence**arXiv ID:** 2407.20208 **Authors:** James M. Mazzu **Published:** 2024-07-29T17:39:52Z **Abstract:** It's widely expected that humanity will someday create AI systems vastly more intelligent than us, leading to the unsolved alignment problem of "how to control superintelligence." However, this commonly expressed problem is not only self-contradictory and likely unsolvable, but current strategies to ensure permanent control effectively guarantee that superintelligent AI will distrust humanit...Votes: 0GitHub stars: 3
- Supervised Training Rapidly Degrades Early VisualDerived from arXiv:2605.30556 - Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning RulesVotes: 0GitHub stars: 3
- Surrogate Gradient Snn TrainingSurrogate Gradient Learning for Spiking Neural Networks - comprehensive training framework using differentiable surrogate functions to overcome the non-differentiability of spike functions. Includes multiple surrogate gradient types (fast-sigmoid, exponential, arctan, erf), temporal batch normalization, neuron normalization, and advanced training strategies for deep SNNs. Activation: surrogate gradient SNN, differentiable spike, spiking neural network training, SNN backpropagation, time surro...Votes: 0GitHub stars: 3
- Survey On Neural Routing Solvers**arXiv ID:** 2602.21761 **Authors:** Yunpeng Ba, Xi Lin, Changliang Zhou, Ruihao Zheng, Zhenkun Wang, Xinyan Liang, Zhichao Lu, Jianyong Sun, Yuhua Qian, Qingfu Zhang **Published:** 2026-02-25T10:24:43Z **Abstract:** Neural routing solvers (NRSs) that leverage deep learning to tackle vehicle routing problems have demonstrated notable potential for practical applications. By learning implicit heuristic rules from data, NRSs replace the handcrafted counterparts in classic heuristic frameworks,...Votes: 0GitHub stars: 3
- Surviving By Serving SbsSurviving by Serving (SBS) principle for self-organization in complex adaptive systems - components persist when their outputs are utilized by others, prolonged non-utilization promotes adaptation. Minimal multi-agent model where agents transform shared resources with local utilization feedback, spontaneously forming functional networks with core-periphery structure. Use for self-organization, multi-agent resource networks, functional emergence, pre-adaptive search. Activation: self-organizat...Votes: 0GitHub stars: 3
- Symmetrybased Representations For Artificial And Biological General Intelligence**arXiv ID:** 2203.09250 **Authors:** Irina Higgins, Sébastien Racanière, Danilo Rezende **Published:** 2022-03-17T11:18:34Z **Abstract:** Biological intelligence is remarkable in its ability to produce complex behaviour in many diverse situations through data efficient, generalisable and transferable skill acquisition. It is believed that learning "good" sensory representations is important for enabling this, however there is little agreement as to what a good representation should look like...Votes: 0GitHub stars: 3
- Synaptic Clustering Covariance DiscriminationSynaptic clustering methodology for learning covariance structure discrimination using Dendrinet architecture with hierarchical dendritic segments and sparse conductance-based synapses. Use when analyzing functional synapse clusters (FSCs), dendritic nonlinearities, synaptic structural plasticity, or covariance classification tasks in computational neuroscience.Votes: 0GitHub stars: 3
- Synaptic Clustering Learning Covariance DiscriminationSynaptic clustering methodology for learning covariance structure discrimination using Dendrinet architecture with hierarchical dendritic segments and sparse conductance-based synapses. Use when analyzing how functional synapse clusters (FSCs) emerge from learning to support computation of covariance structure in neural networks.Votes: 0GitHub stars: 3
- Synaptic Delays Oscillatory Ei NetworksSynaptic delays in oscillatory E-I networks.Votes: 0GitHub stars: 3
- Synaptic Motifs Heterogeneous DynamicsMean-field theory bridging microscale synaptic motifs to macroscale heterogeneous population dynamics in neural networksVotes: 0GitHub stars: 3
- Synaptic Motifs Mean Field DynamicsMean-field theory linking microscale synaptic motifs to macroscopic heterogeneous population dynamics in neural networks. Use when studying synaptic-resolution connectomics, second-order motifs, random RNNs with cell types, or heterogeneous population dynamics.Votes: 0GitHub stars: 3