All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Variancereduced Gradient Estimation Via Noisereuse In Online Evolution Strategies**arXiv ID:** 2304.12180 **Authors:** Oscar Li, James Harrison, Jascha Sohl-Dickstein, Virginia Smith, Luke Metz **Published:** 2023-04-21T17:53:05Z **Abstract:** Unrolled computation graphs are prevalent throughout machine learning but present challenges to automatic differentiation (AD) gradient estimation methods when their loss functions exhibit extreme local sensitivtiy, discontinuity, or blackbox characteristics. In such scenarios, online evolution strategies methods are a more capable ...Votes: 0GitHub stars: 3
- Video Game Level Design As A Multiagent Reinforcement Learning Problem**arXiv ID:** 2510.04862 **Authors:** Sam Earle, Zehua Jiang, Eugene Vinitsky, Julian Togelius **Published:** 2025-10-06T14:49:21Z **Abstract:** Procedural Content Generation via Reinforcement Learning (PCGRL) offers a method for training controllable level designer agents without the need for human datasets, using metrics that serve as proxies for level quality as rewards. Existing PCGRL research focuses on single generator agents, but are bottlenecked by the need to frequently recalculate h...Votes: 0GitHub stars: 3
- Vmavc A Deep Attentionbased Reinforcement Learning Algorithm For Modelbased Control**arXiv ID:** 1812.09968 **Authors:** Xingxing Liang, Qi Wang, Yanghe Feng, Zhong Liu, Jincai Huang **Published:** 2018-12-24T19:25:23Z **Abstract:** Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this paradigm to universal complex tasks. Among them, the low efficiency of data utilization in model-free reinforcemen...Votes: 0GitHub stars: 3
- War Workload Aware Rollouts Synchronous Agentic Reinforcement LearningSkill derived from arXiv:2607.17299 - WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement LearningVotes: 0GitHub stars: 3
- Wcog Vla Dual Level World Cognitive Autonomous DrivingWCog-VLA: dual-level World-Cognitive VLA framework bridging semantic world forecasting with generative world evolution for proactive autonomous driving. Features Game-theoretic Chain-of-Thought reasoning and Aligned Decoupled Diffusion Transformer. SOTA PDMS score of 92.9 on NAVSIM. Use when working with vision-language-action, autonomous-driving, world-cognition.Votes: 0GitHub stars: 3
- Webswarm Recursive Multi Agent Orchestration For Deep AndWebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search. Large language model (LLM)-based web search agents are transforming information seeking from simple factoid question answering into complex, deep-and-wide search and research-oriented tasks. A single ... Activation: agent, multi-agent, agentic, llm, orchestrationVotes: 0GitHub stars: 3
- What Does It Take To Detect An Ai Agent Minimal FeWhat Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under BrowserVotes: 0GitHub stars: 3
- Where Does Agent Reliability Come From A Cross BenDerived from arXiv:2607.17044 - Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise AgentVotes: 0GitHub stars: 3
- Winning Isnt Everything Enhancing Game Development With Intelligent Agents**arXiv ID:** 1903.10545 **Authors:** Yunqi Zhao, Igor Borovikov, Fernando de Mesentier Silva, Ahmad Beirami, Jason Rupert, Caedmon Somers, Jesse Harder, John Kolen, Jervis Pinto, Reza Pourabolghasem, James Pestrak, Harold Chaput, Mohsen Sardari, Long Lin, Sundeep Narravula, Navid Aghdaie, Kazi Zaman **Published:** 2019-03-25T18:39:04Z **Abstract:** Recently, there have been several high-profile achievements of agents learning to play games against humans and beat them. In this paper, we stud...Votes: 0GitHub stars: 3
- Workflow Aware Serving Layer AgenticA workflow-aware serving layer for agentic applications. Addresses the gap between model-serving engines and workflow orchestration for agentic AI workloads that form DAGs of LLM and tool calls with per-node model choices and quality operators. Activation: agentic serving, workflow-aware, LLM serving, DAG orchestration, quality operators, verifiers, agentic workload, serving infrastructure.Votes: 0GitHub stars: 3
- Zerocost Proxies For Lightweight Nas**arXiv ID:** 2101.08134 **Authors:** Mohamed S. Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nicholas D. Lane **Published:** 2021-01-20T13:59:52Z **Abstract:** Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models need to be evaluated before choosing the best one. To reduce the computational power and time needed, a proxy task is often used for evaluating each model ...Votes: 0GitHub stars: 3
- Ztpm Agentic Cps SecurityZero Trust Policy Model (ZTPM) for Agentic Cyber-Physical Systems security enforcement at physical actuation boundaryVotes: 0GitHub stars: 3
- Multi Ensemble Mean Field OscillatorsMulti-ensemble mean-field reduction for networks of globally coupled phase oscillators with arbitrary (empirical) frequency distributions. Extends Ott-Antonsen to heterogeneity beyond Lorentzians. arXiv:2607.09516Votes: 0GitHub stars: 3
- Multi Matrix Quantum Mechanics Collective FieldsQuantum mechanics of bosonic multi-matrix Lagrangians in collective field framework, focusing on three matrix models with effective Hamiltonian derivation and vacuum stability analysis.Votes: 0GitHub stars: 3
- Multi Objective Optimisation Oscillatory SnnMulti-objective genetic algorithm (NSGA-III) optimisation of Izhikevich neuron-based recurrent spiking neural networks for simultaneously matching neural firing rates and network oscillation frequencies. Based on arXiv:2605.25224 (May 2026). Use when studying SNN parameter fitting, neural oscillations, genetic algorithm optimisation for spiking networks, or brain organoid modeling.Votes: 0GitHub stars: 3
- Multi Objective Quantum WorkflowMulti-objective optimization methodology for quantum computing workflows, combining compilation strategy selection, noise suppression, and error-mitigation. Based on QBalance framework (arXiv: 2605.02966) and action-space engineering for RL-based circuit routing. Use when: designing quantum compilation pipelines, optimizing NISQ device execution, selecting error-mitigation strategies, or formulating multi-objective quantum workflow problems.Votes: 0GitHub stars: 3
- Multi Objective Snn OscillationMulti-objective genetic algorithm (NSGA-III) optimisation of spiking neural networks (RSNNs) to match neural firing rates and oscillation frequencies for computational neuroscience modeling.Votes: 0GitHub stars: 3
- Multi Plasticity Snn Training多可塑性协同脉冲神经网络训练方法论。结合多种突触可塑性机制（STDP、奖励调制、赫布学习）协同训练SNN，自适应机制分配。适用于脉冲神经网络、神经形态计算、低功耗AI。触发词：脉冲神经网络、SNN、多可塑性、STDP、突触可塑性、spiking neural network、multi-plasticity。Votes: 0GitHub stars: 3
- Multi Plasticity Synergy SnnMulti-Plasticity Synergy for SNN TrainingVotes: 0GitHub stars: 3
- Multi Scale Hypergraph Brain ConnectivityMulti-scale hypergraph learning (MuHL) methodology for high-order brain connectivity analysis beyond pairwise GNNs. Accepted to ICML 2026. Use for: brain network analysis, neurodegenerative disease classification (Alzheimer's, Parkinson's), higher-order functional connectivity, hypergraph neural networks.Votes: 0GitHub stars: 3
- Multi Scale Info Geometry NeuralMulti-scale information geometry framework revealing the structure of mutual information in neural populations. A unique Riemannian representational geometry emerges from coarse-graining, extending Fisher information metric to capture encoding structure from fine to coarse stimulus distinctions. Use when researching neural population coding, information geometry, Fisher information in neuroscience, or neural representational geometry. Based on arXiv:2605.06304.Votes: 0GitHub stars: 3
- Multi Scale Information Geometry NeuralMulti-scale information geometry framework for analyzing neural population codes. Extends Fisher information metric across stimulus coarse-graining scales to reveal mutual information structure. Use when analyzing: (1) neural population coding geometry, (2) Fisher information limitations in neural data, (3) representational geometry from first principles, (4) mutual information estimation from neural responses, (5) diffusion model-based neural encoding analysis. Trigger: multi-scale Fisher, i...Votes: 0GitHub stars: 3
- Multi Source Fmri TaskonomyMulti-source fMRI cognitive taskonomy framework using transfer learning across 23 HCP task states. Extends single-source to many-to-one task relations with Boolean Integer Programming for budget-constrained task allocation. Activation: fMRI taskonomy, cognitive tasks, transfer learning, multi-source, HCP, BIP.Votes: 0GitHub stars: 3
- Multi Timescale Conductance SnnMulti-Timescale Conductance Spiking Networks (MTC-SNN) methodology for energy-aware temporal processing. Introduces gradient-trainable spiking neurons using fast/slow/ultra-slow conductances to shape I-V curves, enabling direct backpropagation through time (no surrogate gradients). Rich firing regimes (tonic, phasic, bursting) within single model. Outperforms LIF and AdLIF on Mackey-Glass time-series regression with substantially sparser activity. Activation: multi-timescale conductance, MTC-...Votes: 0GitHub stars: 3
- Multi Timescale Conductance Spiking NetworksMulti-Timescale Conductance (MTC) Spiking Networks — gradient-trainable framework with rich firing dynamics for enhanced temporal processing. Conductance-based neuron model with fast/slow/ultra-slow timescales enables tonic, phasic, and bursting responses within a single model. Trainable via standard BPTT without surrogate gradients. Activation: multi-timescale conductance, MTC spiking network, conductance-based neuron, spiking neural network regression, surrogate-free SNN training, I-V curve...Votes: 0GitHub stars: 3
- Multi View O Information Brain DynamicsMulti-view O-Information framework for analyzing higher-order brain interactions in fMRI data. Combines O-information measures with information bottleneck principles for psychiatric diagnosis. Includes O-information computation, Gaussian approximation, and Rényi entropy estimators. Activation: O-information brain, higher-order brain interactions, multi-view brain connectivity, O-information dynamics, brain synergy redundancy, psychiatric diagnosis fMRI.Votes: 0GitHub stars: 3
- Multi View O Information Brain HoiMulti-view O-Information framework for modeling higher-order brain interactions (HOIs) in fMRI data. Information-theoretic approach to psychiatric diagnosis using triadic and tetradic brain connectivity patterns. Keywords: O-information, higher-order interactions, fMRI analysis, information bottleneck, psychiatric diagnosis, hypergraphVotes: 0GitHub stars: 3
- Multi View O Information Brain NetworksHigher-order brain interaction analysis using O-information and Multi-View Information Bottleneck for fMRI-based psychiatric diagnosis. Decomposes multivariate neural interactions into redundant and synergistic components across multiple brain views for improved diagnostic classification. (arXiv:2604.17713, April 2026)Votes: 0GitHub stars: 3
- Multilevel Interactive Equilibrium NeuroaiGame-theoretic framework extending Nash equilibrium to NeuroAI systems with internal computation. Multilevel Interactive Equilibrium (MIE) captures how neural learning dynamics, cognitive representations, and behavioral strategies mutually stabilize between interacting agents. Activation: multilevel equilibrium, MIE, NeuroAI game theory, interactive equilibrium, bounded rationality, human-AI interaction equilibrium, computational psychiatry game theory.Votes: 0GitHub stars: 3
- Multimodal Brain Connectivity Gnn多模态脑连接分析框架，整合fMRI、DTI和sMRI数据。使用可解释图神经网络，通过掩码策略差异加权神经连接，实现跨模态数据融合。支持认知功能预测和解剖特征发现。触发词：多模态融合、脑连接、fMRI、DTI、sMRI、图神经网络、功能连接、结构连接、multimodal fusion、brain connectivity、functional connectivity、structural connectivity。Votes: 0GitHub stars: 3
- Multimodal Brain Network M3d BfsM3D-BFS: Multi-stage Dynamic Fusion Strategy for Sample-Adaptive Multi-Modal Brain Network Analysis. Combines Mixture-of-Experts (MoE) with multi-modal brain networks (structural and functional connectivity) through dynamic, sample-adaptive fusion. 3-stage training: uni-modal encoders, MoE expert pretraining, and full model finetuning with multi-modal disentanglement loss. Activation: multi-modal brain network, M3D-BFS, dynamic fusion, mixture-of-experts brain, sample-adaptive fusion, SC-FC f...Votes: 0GitHub stars: 3
- Multiparameter Hamiltonian EstimationOptimal multiparameter estimation for quantum systems using the unified Cramér-Rao bound framework. Use when: (1) estimating functions of multiple parameters in quantum Hamiltonians, (2) designing quantum sensing protocols, (3) analyzing precision limits for non-commuting generators, (4) optimizing quantum metrology with multiple parameters. Based on arXiv:2605.04136.Votes: 0GitHub stars: 3
- Multiplication Free Spike Time FpgaMultiplication-free spike-time learning algorithm for efficient on-chip SNN training on FPGA. Hardware-software co-design for low-power, event-driven neuromorphic computing. Keywords: SNN training, FPGA implementation, spike-time learning, neuromorphic hardware, edge AIVotes: 0GitHub stars: 3
- Multiscale Brain Dynamics AnalysisUnified framework for multi-scale brain dynamics analysis combining criticality scaling, fixed point compositionality, and representation diagnostics. Integrates renormalization group methods, inhibition-dominated network theory, and EEG foundation model audit protocols.Votes: 0GitHub stars: 3
- Multiview Brain Network Foundation ModelMV-BrainFM: Cross-view consistency learning for multi-view brain network foundation models. Activation: multi-view learning, brain networks, foundation models.Votes: 0GitHub stars: 3
- Multiview Information Bottleneck Brain HoiMulti-view Information Bottleneck framework for modeling higher-order interactions (HOIs) in resting-state fMRI for psychiatric diagnosis. Captures complex brain dynamics beyond pairwise connectivity without predefined hyperedges.Votes: 0GitHub stars: 3
- Music Perception Brain Network音乐感知脑网络建模方法论。使用FitzHugh-Nagumo模型和经验脑连接数据研究听觉刺激对神经网络动力学的影响，分析同步与频率/振幅的关系。触发词：音乐感知、脑网络、听觉刺激、神经同步、FitzHugh-Nagumo、gamma同步、music perception、brain network、auditory stimulus。Votes: 0GitHub stars: 3
- Mzeqas Zero Shot Quantum NasZero-shot quantum neural architecture search methodology using QNTK convergence and MCTS for VQA circuit design. Eliminates repeated training costs. Activation: quantum NAS, neural architecture search, zero-shot, VQA, MCTS, 量子架构搜索.Votes: 0GitHub stars: 3
- N Day Exploit AssessmentMethodology for evaluating LLM capability to develop N-day exploits from public patches — measuring PoC generation, full exploit chain development, and patch-gap risk assessment.Votes: 0GitHub stars: 3
- Naimark Qnn Measurement CircuitsQuantum measurement circuit design comparing Naimark extension, hybrid Naimark-QNN, and fully QNN measurements for state discrimination. Use when: quantum measurement implementation, POVM circuits, minimum-error measurement, maximum-confidence measurement, quantum neural network measurements, Naimark extension circuits. Activation: naimark measurement, quantum measurement circuit, QNN measurement, POVM circuit, minimum-error measurement, maximum-confidence measurement, 量子测量电路Votes: 0GitHub stars: 3
- Native Active Perception ReasoningNative active perception methodology for omni-modal understanding using POMDP-based Observation-Thought-Action cycle, Agentic Supervised Fine-Tuning (ASFT), and TAURA turn-level credit assignment.Votes: 0GitHub stars: 3
- Natural Language AutoencodersMethodology from Anthropic research for converting LLM activations into human-readable natural language text using a reconstruction-based training loop with Activation Verbalizer and Activation Reconstructor.Votes: 0GitHub stars: 3
- Naturalistic Computational Cognitive ScienceFramework for building generalizable cognitive science models using naturalistic experimental paradigms and AI integration. Argues that naturalistic stimuli/tasks elicit distinct neural and behavioral patterns not captured by controlled experiments. Use when: designing ecologically valid neuroscience experiments, integrating AI models with cognitive science, naturalistic fMRI/behavioral studies, computational cognitive modeling, generalization of neural findings. Triggered by: naturalistic co...Votes: 0GitHub stars: 3
- Nbox Memristor Visuotactile SnnSelf-oscillating NbOx memristor neuron for ultra-low-latency visuotactile perception. NbOx devices leverage intrinsic Mott metal-insulator transition and parasitic capacitance for simultaneous TTFS (time-to-first-spike) + rate encoding with 260 ns first-spike latency. Use when: neuromorphic hardware design, memristive spiking neurons, tactile/visual sensor fusion, embodied intelligence hardware, low-latency spike encoding circuits.Votes: 0GitHub stars: 3
- Neocortex Error Driven Predictive LearningNeocortex learning framework via error-driven predictive learning with temporal derivatives, corticothalamic circuits, and competitive kinase synaptic plasticity. Three-criteria account of neocortex learning: computational, algorithmic, and implementational. Activation: neocortex learning, predictive coding, error-driven learning, corticothalamic circuits, synaptic plasticity, temporal derivatives.Votes: 0GitHub stars: 3
- Neocortex Learning Error Driven PredictiveNeocortex learning framework via error-driven predictive learning using temporal derivatives, corticothalamic circuits, and competitive kinase synaptic plasticity. Activation: neocortex learning, cortical learning, predictive learning, thalamocortical, kinase plasticity, error-driven learning.Votes: 0GitHub stars: 3
- Neocortex Learning Predictive Error DrivenNeocortex learning framework via error-driven predictive learning using temporal derivatives, corticothalamic circuits, and competitive kinase synaptic plasticity. Implemented in Axon spiking neural simulation framework. Activation: neocortex learning, predictive coding, error-driven learning, temporal derivatives, corticothalamic circuits, kinase plasticity, spiking neurons, Axon framework, competitive learningVotes: 0GitHub stars: 3
- Nerve Brain Fc TokenizationNERVE (Network-Aware Representations of Brain Functional Connectivity via Bilinear Tokenization) - self-supervised learning framework for brain functional connectivity (FC) representation learning. Redefines FC matrix tokenization by partitioning into intra/inter-network connectivity blocks, using structured bilinear factorization for heterogeneous patch sizes. Use when: building brain network ML models, self-supervised fMRI/FC representation learning, masked autoencoder for brain data, brain...Votes: 0GitHub stars: 3
- Nerve Fc Bilinear TokenizationNERVE: Network-Aware Bilinear Tokenization for Brain Functional Connectivity representation learning. Self-supervised learning framework that redefines FC tokenization via structured bilinear factorization, aligning with large-scale brain network organization. Activation: NERVE, brain FC tokenization, functional connectivity representation, bilinear tokenization, network-aware MAE, brain network MAE.Votes: 0GitHub stars: 3
- Network Quantum Sensing CertificationCertification methodology for network quantum sensing — resolving the tension between quantum metrology and cryptography for distributed sensor networks. Framework for certifying security and precision guarantees simultaneously in noisy, insecure quantum networks.Votes: 0GitHub stars: 3