All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Raw Curve Quantum FingerprintsQuantum cloud platform authentication framework using multi-dimensional quantum fingerprints from raw measurement data. Constructs Mahalanobis-based fingerprints with drift early warning and adversarial detection to verify which physical device executes workloads, preventing hardware substitution attacks. Activation: quantum authentication, cloud verification, hardware fingerprinting, quantum cloud, device authentication, Mahalanobis distance, drift detection, adversarial detection, raw-curveVotes: 0GitHub stars: 3
- Rdnn Low Rank Manifolds Working MemoryRecurrent Divisive Normalization Network (RDNN) framework for continuous working memory with low-rank slow manifolds. Provides implementation guidance for stable continuous manifold learning in RNNs using divisive normalization to prevent state space shattering into discretized point attractors. Use when modeling continuous working memory, neural manifolds, or stable RNN dynamics.Votes: 0GitHub stars: 3
- React ComponentsExpert guidance for React component architecture, maintainability, and best practices. Use when building React components, reviewing component structure, optimizing component performance, or working with React hooks. Triggers on: react component, component architecture, react best practices, component size, react hooks.Votes: 0GitHub stars: 3
- Reasoning Models Chain Of Thought ControllabilityCoT-Control methodology for testing reasoning model control over internal reasoning. Finding - models struggle to control chains of thought, reinforcing monitorability as safety safeguard. Use when evaluating reasoning model safety or designing monitoring systems.Votes: 0GitHub stars: 3
- Reasonmaxxer Entropy Gated SelectionRL-free reasoning improvement via entropy-gated contrastive selection. Based on arXiv 2605.06241 showing RL's benefit is sparse policy selection at high-entropy decision points, not capability learning.Votes: 0GitHub stars: 3
- Reasonstl Nl To StlTool-augmented process-rewarded learning for Natural Language to Signal Temporal Logic (STL) translation in cyber-physical systems (CPS) specification. Use when: (1) translating natural language CPS requirements into STL formulas, (2) building NL-to-formal-specification pipelines for autonomous systems, robotics, or CPS verification, (3) designing tool-augmented LLM frameworks for formal methods, (4) implementing process-rewarded training for structured output generation, (5) creating benchma...Votes: 0GitHub stars: 3
- Reconstructing Backpropagation Noise Modulated NetworksUse when designing biologically plausible neural networks that need to implement backpropagation without weight transport. Provides a method to reconstruct gradients from forward-pass statistics using noise as a computational resource.Votes: 0GitHub stars: 3
- Recontext Evidence ReplayRecursive Evidence Replay as LLM Harness for Long-Context Reasoning. Training-free inference method that uses model-internal relevance signals to construct query-conditioned evidence pool and replays before final generation, improving long-context reasoning without training, external memory, or context pruning.Votes: 0GitHub stars: 3
- Recursive Evidence Replay ReasoningReContext framework — recursive evidence replay for long-context reasoning, mapping LLM attention to associative memory mechanisms from neuroscienceVotes: 0GitHub stars: 3
- Reinformed Dreamer Asymmetric World ModelReinforced Dreamer methodology for asymmetric reinforcement learning using latent guidance to improve world model representations and behaviors in model-based RL.Votes: 0GitHub stars: 3
- Reliability Testing For Natural Language Processing Systems**arXiv ID:** 2105.02590 **Authors:** Samson Tan, Shafiq Joty, Kathy Baxter, Araz Taeihagh, Gregory A. Bennett, Min-Yen Kan **Published:** 2021-05-06T11:24:58Z **Abstract:** Questions of fairness, robustness, and transparency are paramount to address before deploying NLP systems. Central to these concerns is the question of reliability: Can NLP systems reliably treat different demographics fairly and function correctly in diverse and noisy environments? To address this, we argue for the need ...Votes: 0GitHub stars: 3
- Remember Me Refine Me ProceduralRemember Me, Refine Me - Procedural MemoryVotes: 0GitHub stars: 3
- Repulsive Cage Containment CpsDistributed containment of compromised CPS agents using repulsive cages — Stackelberg game framework for UAV swarm security via collision-avoidance exploitation. Use when: designing secure multi-agent systems, UAV swarm safety, cyber-physical security, distributed containment, adversarial agent mitigation.Votes: 0GitHub stars: 3
- Rescom Reconfigurable Snn AcceleratorReSCom可重构脉冲神经网络加速器，使用随机计算降低硬件复杂度。核心创新：乘法用随机算术，加法用精确定点，统一架构支持IF/LIF/Synaptic模型，运行时可权衡精度/延迟/能耗。MNIST上92.80%准确率，0.05mJ/image能效超越SOTA。触发词：可重构SNN加速器、随机计算SNN、神经形态FPGA、ReSCom。Votes: 0GitHub stars: 3
- Rescom Reconfigurable Snn Stochastic ComputingReSCom: A Reconfigurable Spiking Neural Network Accelerator Using Stochastic Computing. Neuromorphic hardware architecture for energy-efficient SNN inference with runtime accuracy-latency-energy trade-offs.Votes: 0GitHub stars: 3
- Rescom Reconfigurable Stochastic Computing SnnReSCom 是一种可重构 SNN 加速器，核心创新在于使用随机计算（Stochastic Computing）降低硬件复杂度，同时通过精度管理确保稳定推理。采用统一神经元设计支持多种神经元模型（IF/LIF/Synaptic），实现精度-延迟-能耗的动态权衡。Votes: 0GitHub stars: 3
- Research Api Fallback StrategyFallback strategies for automated research when external APIs fail. Use when: (1) arXiv/semantic scholar APIs return errors, (2) scheduled research jobs encounter connectivity issues, (3) need to pivot from live search to knowledge-based skill creation, (4) automated research pipelines need resilience against external service failures.Votes: 0GitHub stars: 3
- Research Literature KgBuild and analyze knowledge graphs from research literature. Automated pipeline: arxiv search → entity extraction → KG construction → vector embeddings → semantic search → skill pattern extraction. Use when user asks to analyze papers, build research knowledge bases, find related work, or extract reusable patterns from academic literature.Votes: 0GitHub stars: 3
- Research Paper Pattern ExtractorExtract reusable research skill patterns from knowledge graph paper analysis. Uses PageRank, Louvain, and vector search to identify important papers and research clusters, then distills patterns into new skills. Activation: extract research pattern, research skill extractor, 研究模式提炼, paper pattern analysis.Votes: 0GitHub stars: 3
- Research Skill ExtractorMeta-skill that extracts reusable skill patterns from research papers (arxiv), scientific workflows, and knowledge graph analysis. Activates when analyzing papers for skill patterns, creating skills from research methodologies, or mining patterns from scientific literature. Keywords: extract skill from paper, research skill mining, 论文技能提炼, paper to skill, arxiv skill extractor.Votes: 0GitHub stars: 3
- Reservoir Computation OrganizationAnalyze how information processing capacity is organized across reservoir state-space modes. Use SVD mode-task projection, degree-wise representation energy, and noise-aware capacity to design or diagnose echo-state networks and physical reservoirs.Votes: 0GitHub stars: 3
- Reservoir Computing Heterogeneous Magnetic MetamaterialsReservoir Computing with Heterogeneous Magnetic Metamaterials methodology — nanomagnetic reservoir computer based on heterogeneous array of interconnected magnetic nanorings with multi-channel planar Hall effect readout for enhanced computational expressivity.Votes: 0GitHub stars: 3
- Residual Conservative MpcResidual-Conservative MPC (RC-MPPI) framework — adaptive safety modulation for sampling-based model predictive control using prediction-execution residuals. Combines residual-dependent constraint tightening, adaptive safety-cost shaping, and residual-adaptive sampling. Use when designing safety-critical MPC systems with model uncertainty.Votes: 0GitHub stars: 3
- Resilient Output Containment CpsResilient output containment control for heterogeneous multi-agent systems under actuator cyber-attacks. Two-layer adaptive control architecture combining virtual-actuator reconfiguration with network-level adaptive protocols. Handles undisclosed leader dynamics, directed network topologies, and multiple attack types (state-correlated, input-correlated, exogenous). Use when designing fault-tolerant multi-agent coordination, resilient CPS control systems, or distributed containment tracking un...Votes: 0GitHub stars: 3
- Response Characterization For Auditing Cell Dynamics In Long Shortterm Memory Networks**arXiv ID:** 1809.03864 **Authors:** Ramin M. Hasani, Alexander Amini, Mathias Lechner, Felix Naser, Radu Grosu, Daniela Rus **Published:** 2018-09-11T13:27:36Z **Abstract:** In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked c...Votes: 0GitHub stars: 3
- Retain Or Consolidate Budget Dependent Operator SeDerived from arXiv:2607.17545 - Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent MemoryVotes: 0GitHub stars: 3
- Rethinking Self Evolution A Constrained ExploratioRethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill OverfVotes: 0GitHub stars: 3
- Rethinking Symbolic Regression Datasets And Benchmarks For Scientific Discovery**arXiv ID:** 2206.10540 **Authors:** Yoshitomo Matsubara, Naoya Chiba, Ryo Igarashi, Yoshitaka Ushiku **Published:** 2022-06-21T17:15:45Z **Abstract:** This paper revisits datasets and evaluation criteria for Symbolic Regression (SR), specifically focused on its potential for scientific discovery. Focused on a set of formulas used in the existing datasets based on Feynman Lectures on Physics, we recreate 120 datasets to discuss the performance of symbolic regression for scientific discovery ...Votes: 0GitHub stars: 3
- RevealReVealVotes: 0GitHub stars: 3
- Reward Valuation Vlm AnhedoniaCausal mechanism framework for anhedonia and reward valuation deficits in Vision-Language Models — mechanistic analysis linking VLM reward processing to Nucleus Accumbens dysfunction patterns from clinical depression research.Votes: 0GitHub stars: 3
- Rewardguided Iterative Refinement In Diffusion Models At Testtime With Applications To Protein And Dna Design**arXiv ID:** 2502.14944 **Authors:** Masatoshi Uehara, Xingyu Su, Yulai Zhao, Xiner Li, Aviv Regev, Shuiwang Ji, Sergey Levine, Tommaso Biancalani **Published:** 2025-02-20T17:48:45Z **Abstract:** To fully leverage the capabilities of diffusion models, we are often interested in optimizing downstream reward functions during inference. While numerous algorithms for reward-guided generation have been recently proposed due to their significance, current approaches predominantly focus on single-...Votes: 0GitHub stars: 3
- Ribbon Zx Calculus Gauge TheoryRibbon ZX calculus framework for gauge theory — extends ZX diagrammatic calculus to 2D Yang-Mills theory with compact gauge groups via Hopf Frobenius algebraic structure.Votes: 0GitHub stars: 3
- Riemannian Self Attention Eeg DecodingBures-Wasserstein metric-based Riemannian self-attention network for robust EEG decodingVotes: 0GitHub stars: 3
- Rl Ion Shuttling Trapped IonReinforcement learning for ion shuttling on trapped-ion quantum computers — RL-based optimization of ion transport in modular trapped-ion chips, achieving up to 36.3% reduction in shuttling operations.Votes: 0GitHub stars: 3
- Rl Qec ControlReinforcement Learning for Quantum Error Correction control methodology. Based on Google Quantum AI's Willow processor framework (arXiv:2511.08493). Use when: (1) designing RL-based calibration for quantum systems, (2) implementing continuous error correction without halting computation, (3) repurposing QEC syndrome measurements as RL learning signals, (4) stabilizing quantum operations against environmental drift, (5) optimizing surface code or color code performance. Keywords: quantum error...Votes: 0GitHub stars: 3
- Rl Tsch Dynamic ListeningReinforcement Learning-driven Adaptive Listening for TSCH NetworksVotes: 0GitHub stars: 3
- Robust Regret ControlFramework for distributionally robust regret optimization (DRRO) in stochastic control systems, combining robust control with regret minimization under uncertainty. Use when designing control systems with ambiguous disturbances, robust LQR, or optimizing control under unknown probability distributions.Votes: 0GitHub stars: 3
- Robustness Verification Of Deep Neural Networks Using Starbased Reachability Analysis With Variablelength Time Series Input**arXiv ID:** 2307.13907 **Authors:** Neelanjana Pal, Diego Manzanas Lopez, Taylor T Johnson **Published:** 2023-07-26T02:15:11Z **Abstract:** Data-driven, neural network (NN) based anomaly detection and predictive maintenance are emerging research areas. NN-based analytics of time-series data offer valuable insights into past behaviors and estimates of critical parameters like remaining useful life (RUL) of equipment and state-of-charge (SOC) of batteries. However, input time series data can...Votes: 0GitHub stars: 3
- Rosetta Stone Other Minds InferenceFramework for principled inference to other minds using structural approaches (Qualia Structure Paradigm and Integrated Information Theory) with Category Theory formalizationVotes: 0GitHub stars: 3
- Rrc Ranking Reward ConstructionRRC for ranking-based reward construction.Votes: 0GitHub stars: 3
- Rt Semamba Speech Enhancement MambaRT-SEMamba for real-time speech enhancement with Mamba.Votes: 0GitHub stars: 3
- Rt Shcua Real Time Self Hosted Computer Use AgentDerived from arXiv:2607.17951 - RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV ControlVotes: 0GitHub stars: 3
- Rulkov Neural Maps Cross CouplingNovel coupling methodology for Rulkov neural maps preserving chaos and generating strange attractorsVotes: 0GitHub stars: 3
- Safe Quantum MlSAFE Quantum Machine Learning methodology — variational quantum classifiers with amplitude encoding, learnable classical pre-encoding, and SAFE-AI reliability metrics (Cramer-von-Mises-based accuracy/robustness/explainability evaluation). For designing safety-critical quantum ML models.Votes: 0GitHub stars: 3
- Safeapt Safe Simulationtoreal Robot Learning Using Diverse Policies Learned In Simulation**arXiv ID:** 2201.13248 **Authors:** Rituraj Kaushik, Karol Arndt, Ville Kyrki **Published:** 2022-01-27T16:40:36Z **Abstract:** The framework of Simulation-to-real learning, i.e, learning policies in simulation and transferring those policies to the real world is one of the most promising approaches towards data-efficient learning in robotics. However, due to the inevitable reality gap between the simulation and the real world, a policy learned in the simulation may not always generate a sa...Votes: 0GitHub stars: 3
- Safety Liveness Control ContractsDesign layered control architectures (LCAs) using safety-liveness decomposition via heterogeneous assume-guarantee contracts. Use when: (1) designing hierarchical control systems with discrete planning + continuous execution, (2) enforcing safety constraints while achieving long-horizon objectives, (3) co-designing multi-layer controllers with formal guarantees, (4) building reference governor bridges between MPC planners and low-level controllers. Based on arXiv:2605.04222.Votes: 0GitHub stars: 3
- Sam Mt Realtime Multi Target VosDecouples VOS latency from target count for real-time multi-target video segmentation.Votes: 0GitHub stars: 3
- Same Dangerous Objective Opposite Advice Direct Exposure VersusSame Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent MediationVotes: 0GitHub stars: 3
- Samplebased Dynamic Hierarchical Transformer With Layer And Head Flexibility Via Contextual Bandit**arXiv ID:** 2312.03038 **Authors:** Fanfei Meng, Lele Zhang, Yu Chen, Yuxin Wang **Published:** 2023-12-05T15:04:11Z **Abstract:** Transformer requires a fixed number of layers and heads which makes them inflexible to the complexity of individual samples and expensive in training and inference. To address this, we propose a sample-based Dynamic Hierarchical Transformer (DHT) model whose layers and heads can be dynamically configured with single data samples via solving contextual bandit pro...Votes: 0GitHub stars: 3
- Sbb CodesSubsystem Bivariate Bicycle (SBB) codes methodology for quantum error correction. Reduces high-rate BB code stabilizer checks from weight-6+ to local weight-4 gauge measurements via CSS subsystem construction. Use when: (1) designing qLDPC codes with low-weight syndrome extraction, (2) implementing BB codes on hardware with limited connectivity, (3) analyzing topological properties of subsystem codes, (4) constructing finite-depth Clifford circuits for gauge qubit decoupling. Activation: sbb ...Votes: 0GitHub stars: 3