All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Off Switch Dual Use Knowledge ControlOff switch for dual-use knowledge using GRAM methodology.Votes: 0GitHub stars: 3
- Off Switch GramMethodology from Anthropic's "An off switch for dual-use knowledge in AI models" (Jul 2026). Use when you need to surgically remove or gate specific capabilities/knowledge (dual-use, dangerous, or disallowed) from a model while preserving general performance, and want that removal to RESIST restoration via fine-tuning. Based on Gradient-Routed Auxiliary Modules (GRAM) — isolating a capability in a removable module and deleting it.Votes: 0GitHub stars: 3
- Omni Sleep FoundationOmni-Sleep sleep foundation model methodology using CNS/ANS hierarchical contrastive learning for topology-constrained multimodal PSG representation learning. Use when working with sleep staging, affective BCI, polysomnography analysis, CNS-ANS dynamics, multimodal biosignal foundation models, or physiological hierarchy in representation learning.Votes: 0GitHub stars: 3
- Omniqec Ai Scientist Quantum Error CorrectionOmniQEC methodology for discovering practical quantum error-correcting codes using an AI scientist framework with LLM orchestrator and slow-fast synergistic workflow.Votes: 0GitHub stars: 3
- One Shot Quantum SignaturesQuantum algorithm for one-shot signatures using affine coset superposition and puncturable PRFs. Provides circuit-level implementation for delegated signatures, secured token transfer, and publicly verifiable randomness. Use when implementing quantum signature schemes, building quantum-secure authentication protocols, or designing quantum token systems.Votes: 0GitHub stars: 3
- OpencodeOpen source AI coding agent with multi-agent orchestration and ultrawork mode. Use when user mentions opencode, open code, oh-my-opencode, ultrawork, ulw, or needs an AI coding agent with background tasks and LSP integration.Votes: 0GitHub stars: 3
- OpenspecSpecification-driven development framework using Gherkin syntax. Use when user mentions openspec, open spec, spec-driven, gherkin, BDD, given-when-then, or needs to define requirements in structured human-readable format.Votes: 0GitHub stars: 3
- Optimal Ansatz Free Hamiltonian LearningOptimal ansatz-free Hamiltonian learning methodology — control-free, ancilla-free algorithm using randomized-sampling framework with band-limited kernel-based time sampling and displacement sieve for Hamiltonian structure learning. Use for quantum device calibration, signal sensing, and error correction.Votes: 0GitHub stars: 3
- Organic Magnetic Field Free QuantumMagnetic-field-free quantum computing and quantum reservoir computing framework using engineered organic materials based on the 3-Layer Quantum Brain Hypothesis. Covers SVILC qubits, CQEC error correction, and four implementation paths. Use when: organic quantum computing, quantum reservoir computing, spin-vortex qubits, magnetic-field-free quantum architectures, quantum neuroscience, or engineered organic quantum materials.Votes: 0GitHub stars: 3
- Organization Of Computation Reservoir ComputingEigenspectral decomposition framework for analyzing how information processing capacity (IPC) is distributed across reservoir state-space modes, with degree-wise representation energy and noise-aware capacity metrics for physical reservoir computers.Votes: 0GitHub stars: 3
- A Continual Development Methodology For Largescale Multitask Dynamic Ml Systems**arXiv ID:** 2209.07326 **Authors:** Andrea Gesmundo **Published:** 2022-09-15T14:36:17Z **Abstract:** The traditional Machine Learning (ML) methodology requires to fragment the development and experimental process into disconnected iterations whose feedback is used to guide design or tuning choices. This methodology has multiple efficiency and scalability disadvantages, such as leading to spend significant resources into the creation of multiple trial models that do not contribute to the fi...Votes: 0GitHub stars: 3
- A Deep Dive Into Effects Of Structural Bias On Cmaes Performance Along Affine Trajectories**arXiv ID:** 2404.17323 **Authors:** Niki van Stein, Sarah L. Thomson, Anna V. Kononova **Published:** 2024-04-26T11:07:09Z **Abstract:** To guide the design of better iterative optimisation heuristics, it is imperative to understand how inherent structural biases within algorithm components affect the performance on a wide variety of search landscapes. This study explores the impact of structural bias in the modular Covariance Matrix Adaptation Evolution Strategy (modCMA), focusing on the r...Votes: 0GitHub stars: 3
- A First Look At Coding Agents Compliance With Ai CA First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source CommunitiesVotes: 0GitHub stars: 3
- A Framework Of User Experience Principles For HumaSkill generated from arXiv paper 2607.19941: A Framework of User Experience Principles for Human-AI Agent Interaction in the WorkplaceVotes: 0GitHub stars: 3
- A Generative Model For Molecule Generation Based On Chemical Reaction Trees**arXiv ID:** 2106.03394 **Authors:** Dai Hai Nguyen, Koji Tsuda **Published:** 2021-06-07T07:47:18Z **Abstract:** Deep generative models have been shown powerful in generating novel molecules with desired chemical properties via their representations such as strings, trees or graphs. However, these models are limited in recommending synthetic routes for the generated molecules in practice. We propose a generative model to generate molecules via multi-step chemical reaction trees. Specificall...Votes: 0GitHub stars: 3
- A Group Theoretic Analysis Of The Symmetries Underlying Base Addition And Their Learnability By Neural Networks**arXiv ID:** 2507.10678 **Authors:** Cutter Dawes, Simon Segert, Kamesh Krishnamurthy, Jonathan D. Cohen **Published:** 2025-07-14T18:01:38Z **Abstract:** A major challenge in the use of neural networks both for modeling human cognitive function and for artificial intelligence is the design of systems with the capacity to efficiently learn functions that support radical generalization. At the roots of this is the capacity to discover and implement symmetry functions. In this paper, we invest...Votes: 0GitHub stars: 3
- A Hybrid Algorithm For Metaheuristic Optimization**arXiv ID:** 1906.02010 **Authors:** Sujit Pramod Khanna, Alexander Ororbia **Published:** 2019-05-26T10:45:58Z **Abstract:** We propose a novel, flexible algorithm for combining together metaheuristicoptimizers for non-convex optimization problems. Our approach treatsthe constituent optimizers as a team of complex agents that communicateinformation amongst each other at various intervals during the simulationprocess. The information produced by each individual agent can be combinedin variou...Votes: 0GitHub stars: 3
- A Large Scale Empirical Evaluation Of Mmao Under FDerived from arXiv:2606.31584 - A Large-Scale Empirical Evaluation of MMAO Under Fair-Budget Continuous and Discrete BenchmarksVotes: 0GitHub stars: 3
- A Learning Rate Gated Failure Of Grpo In A Small LA Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism - Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised chec...Votes: 0GitHub stars: 3
- A Library Of Mirrors Deep Neural Nets In Low Dimensions Are Convex Lasso Models With Reflection Features**arXiv ID:** 2403.01046 **Authors:** Emi Zeger, Yifei Wang, Aaron Mishkin, Tolga Ergen, Emmanuel Candès, Mert Pilanci **Published:** 2024-03-02T00:33:45Z **Abstract:** We prove that training neural networks on 1-D data is equivalent to solving convex Lasso problems with discrete, explicitly defined dictionary matrices. We consider neural networks with piecewise linear activations and depths ranging from 2 to an arbitrary but finite number of layers. We first show that two-layer networks with...Votes: 0GitHub stars: 3
- A Multiagent Framework For The Asynchronous And Collaborative Extension Of Multitask Ml Systems**arXiv ID:** 2209.14745 **Authors:** Andrea Gesmundo **Published:** 2022-09-29T13:02:58Z **Abstract:** The traditional ML development methodology does not enable a large number of contributors, each with distinct objectives, to work collectively on the creation and extension of a shared intelligent system. Enabling such a collaborative methodology can accelerate the rate of innovation, increase ML technologies accessibility and enable the emergence of novel capabilities. We believe that this...Votes: 0GitHub stars: 3
- A Neural Network Approach To Ordinal Regression**arXiv ID:** 0704.1028 **Authors:** Jianlin Cheng **Published:** 2007-04-08T17:36:00Z **Abstract:** Ordinal regression is an important type of learning, which has properties of both classification and regression. Here we describe a simple and effective approach to adapt a traditional neural network to learn ordinal categories. Our approach is a generalization of the perceptron method for ordinal regression. On several benchmark datasets, our method (NNRank) outperforms a neural network class...Votes: 0GitHub stars: 3
- A Novel Machine Learning Classifier Based On Genetic Algorithms And Data Importance Reformatting**arXiv ID:** 2412.13350 **Authors:** A. K. Alkhayyata, N. M. Hewahi **Published:** 2024-12-17T21:54:55Z **Abstract:** In this paper, a novel classification algorithm that is based on Data Importance (DI) reformatting and Genetic Algorithms (GA) named GADIC is proposed to overcome the issues related to the nature of data which may hinder the performance of the Machine Learning (ML) classifiers. GADIC comprises three phases which are data reformatting phase which depends on DI concept, trainin...Votes: 0GitHub stars: 3
- A Novel Neural Networkbased Federated Learning System For Imbalanced And Noniid Data**arXiv ID:** 2311.10025 **Authors:** Mahfuzur Rahman Chowdhury, Muhammad Ibrahim **Published:** 2023-11-16T17:14:07Z **Abstract:** With the growth of machine learning techniques, privacy of data of users has become a major concern. Most of the machine learning algorithms rely heavily on large amount of data which may be collected from various sources. Collecting these data yet maintaining privacy policies has become one of the most challenging tasks for the researchers. To combat this issue,...Votes: 0GitHub stars: 3
- A Novel Progressive Learning Technique For Multiclass Classification**arXiv ID:** 1609.00085 **Authors:** Rajasekar Venkatesan, Meng Joo Er **Published:** 2016-09-01T01:50:18Z **Abstract:** In this paper, a progressive learning technique for multi-class classification is proposed. This newly developed learning technique is independent of the number of class constraints and it can learn new classes while still retaining the knowledge of previous classes. Whenever a new class (non-native to the knowledge learnt thus far) is encountered, the neural network struc...Votes: 0GitHub stars: 3
- A Perspective On Objects And Systematic Generalization In Modelbased Rl**arXiv ID:** 1906.01035 **Authors:** Sjoerd van Steenkiste, Klaus Greff, Jürgen Schmidhuber **Published:** 2019-06-03T19:29:12Z **Abstract:** In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledge and the combinatorial construction of such models. In this work, we argue that dynamically bound features (objects) do not simply em...Votes: 0GitHub stars: 3
- A Pso And Pattern Search Based Memetic Algorithm For Svms Parameters Optimization**arXiv ID:** 1401.1926 **Authors:** Yukun Bao, Zhongyi Hu, Tao Xiong **Published:** 2014-01-09T08:41:55Z **Abstract:** Addressing the issue of SVMs parameters optimization, this study proposes an efficient memetic algorithm based on Particle Swarm Optimization algorithm (PSO) and Pattern Search (PS). In the proposed memetic algorithm, PSO is responsible for exploration of the search space and the detection of the potential regions with optimum solutions, while pattern search (PS) is used to ...Votes: 0GitHub stars: 3
- A Robust Experimental Evaluation Of Automated Multilabel Classification Methods**arXiv ID:** 2005.08083 **Authors:** Alex G. C. de Sá, Cristiano G. Pimenta, Gisele L. Pappa, Alex A. Freitas **Published:** 2020-05-16T20:08:04Z **Abstract:** Automated Machine Learning (AutoML) has emerged to deal with the selection and configuration of algorithms for a given learning task. With the progression of AutoML, several effective methods were introduced, especially for traditional classification and regression problems. Apart from the AutoML success, several issues remain open. O...Votes: 0GitHub stars: 3
- A Scalable Test Problem Generator For Sequential Transfer Optimization**arXiv ID:** 2304.08503 **Authors:** Xiaoming Xue, Cuie Yang, Liang Feng, Kai Zhang, Linqi Song, Kay Chen Tan **Published:** 2023-04-17T06:48:07Z **Abstract:** Sequential transfer optimization (STO), which aims to improve the optimization performance on a task of interest by exploiting the knowledge captured from several previously-solved optimization tasks stored in a database, has been gaining increasing research attention over the years. However, despite the remarkable advances in algorit...Votes: 0GitHub stars: 3
- A Systematic Evaluation Of Trajectory Data CuratioDerived from arXiv:2607.17205 - A Systematic Evaluation of Trajectory Data Curation for LoRA Fine-Tuning of Code AgentsVotes: 0GitHub stars: 3
- A Temporal Anomaly Detection System For Vehicles Utilizing Functional Working Groups And Sensor Channels**arXiv ID:** 2209.06828 **Authors:** Subash Neupane, Ivan A. Fernandez, Wilson Patterson, Sudip Mittal, Shahram Rahimi **Published:** 2022-09-14T14:33:07Z **Abstract:** A modern vehicle fitted with sensors, actuators, and Electronic Control Units (ECUs) can be divided into several operational subsystems called Functional Working Groups (FWGs). Examples of these FWGs include the engine system, transmission, fuel system, brakes, etc. Each FWG has associated sensor-channels that gauge vehicular...Votes: 0GitHub stars: 3
- Accelerating Training Speed Of Tiny Recursive Models With Curriculum Guided Adaptive Recursion**arXiv ID:** 2511.08653 **Authors:** Kaleem Ullah Qasim, Jiashu Zhang **Published:** 2025-11-11T08:17:23Z **Abstract:** Background: Recursive reasoning models achieve strong performance through iterative refinement, allowing small networks to match large language models. However, training is computationally expensive, often requiring 36 GPU-hours for Sudoku extreme. Existing models use fixed recursion depth and uniform supervision weighting, leading to inefficient training. Objectives: We pr...Votes: 0GitHub stars: 3
- Activation Functions In Artificial Neural Networks A Systematic Overview**arXiv ID:** 2101.09957 **Authors:** Johannes Lederer **Published:** 2021-01-25T08:55:26Z **Abstract:** Activation functions shape the outputs of artificial neurons and, therefore, are integral parts of neural networks in general and deep learning in particular. Some activation functions, such as logistic and relu, have been used for many decades. But with deep learning becoming a mainstream research topic, new activation functions have mushroomed, leading to confusion in both theory and pra...Votes: 0GitHub stars: 3
- Active Learning Of Inverse Models With Intrinsically Motivated Goal Exploration In Robots**arXiv ID:** 1301.4862 **Authors:** Adrien Baranes, Pierre-Yves Oudeyer **Published:** 2013-01-21T13:26:07Z **Abstract:** We introduce the Self-Adaptive Goal Generation - Robust Intelligent Adaptive Curiosity (SAGG-RIAC) architecture as an intrinsi- cally motivated goal exploration mechanism which allows active learning of inverse models in high-dimensional redundant robots. This allows a robot to efficiently and actively learn distributions of parameterized motor skills/policies that solve ...Votes: 0GitHub stars: 3
- Activity Regeneration From Silent States In Neuronal Networks With Transient Synaptic MemorySkill for understanding and applying the research from arXiv:2607.14000 "Activity Regeneration from Silent States in Neuronal Networks with Transient Synaptic Memory"Votes: 0GitHub stars: 3
- Adaptive Conduction Delays Haken LighthouseAdaptive conduction delays and phase locking in spiking Haken Lighthouse networks. Theory of phase-locked activity in delayed spiking networks using analytically tractable event-based neural dynamics. Introduces activity-dependent white matter plasticity with myelination-modulated axonal conduction speed. Activation: Haken Lighthouse, phase locking, conduction delays, myelin plasticity, spike-time perturbations, circulant symmetry, Fourier modes.Votes: 0GitHub stars: 3
- Adaptive Online Sequential Elm For Concept Drift Tackling**arXiv ID:** 1610.01922 **Authors:** Arif Budiman, Mohamad Ivan Fanany, Chan Basaruddin **Published:** 2016-10-06T16:08:52Z **Abstract:** A machine learning method needs to adapt to over time changes in the environment. Such changes are known as concept drift. In this paper, we propose concept drift tackling method as an enhancement of Online Sequential Extreme Learning Machine (OS-ELM) and Constructive Enhancement OS-ELM (CEOS-ELM) by adding adaptive capability for classification and regres...Votes: 0GitHub stars: 3
- Adnev A Scalable Multilevel Neuroevolution Framework For Multivariate Anomaly Detection**arXiv ID:** 2305.16497 **Authors:** Marcin Pietron, Dominik Zurek, Kamil Faber, Roberto Corizzo **Published:** 2023-05-25T21:52:38Z **Abstract:** Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given dataset is a cumbersome and time consuming process. Neuroevolution could be an effective and efficient solution ...Votes: 0GitHub stars: 3
- Agentmap Joint Equivalence And Subsumption DiscoveAgentMap: Joint Equivalence and Subsumption Discovery for Ontology MatchingVotes: 0GitHub stars: 3
- Agentsnare Learning To Delay Divert And Defuse AutAgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration AgentsVotes: 0GitHub stars: 3
- Alien Coding**arXiv ID:** 2301.11479 **Authors:** Thibault Gauthier, Miroslav Olšák, Josef Urban **Published:** 2023-01-27T00:51:48Z **Abstract:** We introduce a self-learning algorithm for synthesizing programs for OEIS sequences. The algorithm starts from scratch initially generating programs at random. Then it runs many iterations of a self-learning loop that interleaves (i) training neural machine translation to learn the correspondence between sequences and the programs discovered so far, and (ii) p...Votes: 0GitHub stars: 3
- An Explicit World Model Based On Data First OntoloDerived from arXiv:2607.17269 - An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and Counterfactual Reasoning EvaluationVotes: 0GitHub stars: 3
- An Off Switch For Dual Use Knowledge In Ai ModelsAn off switch for dual-use knowledge in AI modelsVotes: 0GitHub stars: 3
- An Online Supervised Learning Algorithm Based On Triple Spikes For Spiking Neural Networks**arXiv ID:** 1901.01549 **Authors:** Guojun Chen, Xianghong Lin, Guoen Wang **Published:** 2019-01-06T15:11:10Z **Abstract:** Using precise times of every spike, spiking supervised learning has more effects on complex spatial-temporal pattern than supervised learning only through neuronal firing rates. The purpose of spiking supervised learning after spatial-temporal encoding is to emit desired spike trains with precise times. Existing algorithms of spiking supervised learning have excellent...Votes: 0GitHub stars: 3
- Analog Quantum Event GnnAnalog Quantum Asynchronous Event-Based Graph Neural Network (QA-AEGNN) — implementing event-based GNNs on neutral-atom quantum processors via Rydberg Hamiltonian programming. Maps streaming event data to trapped atom arrays where geometric proximity reflects spatio-temporal neighborhoods, with native Hamiltonian dynamics executing message-passing natively. Activation: quantum GNN, neutral atom, Rydberg Hamiltonian, event camera, asynchronous event, analog quantum computing, graph neural netw...Votes: 0GitHub stars: 3
- Application Of Unsupervised Artificial Neural Network Ann Selforganizing Map Som In Identifying Main Car Sales Factors**arXiv ID:** 2408.05110 **Authors:** Mazyar Taghavi **Published:** 2024-07-29T14:24:16Z **Abstract:** Factors which attract customers and persuade them to buy new car are various regarding different consumer tastes. There are some methods to extract pattern form mass data. In this case we firstly asked passenger car marketing experts to rank more important factors which affect customer decision making behavior using fuzzy Delphi technique, then we provided a sample set from questionnaires an...Votes: 0GitHub stars: 3
- Approximate Answering Of Graph Queries**arXiv ID:** 2308.06585 **Authors:** Michael Cochez, Dimitrios Alivanistos, Erik Arakelyan, Max Berrendorf, Daniel Daza, Mikhail Galkin, Pasquale Minervini, Mathias Niepert, Hongyu Ren **Published:** 2023-08-12T14:47:21Z **Abstract:** Knowledge graphs (KGs) are inherently incomplete because of incomplete world knowledge and bias in what is the input to the KG. Additionally, world knowledge constantly expands and evolves, making existing facts deprecated or introducing new ones. However, we w...Votes: 0GitHub stars: 3
- Are Grid Cells Hexagonal For Performance Or By Convenience**arXiv ID:** 2410.11886 **Authors:** Taahaa Mir, Peipei Yao, Kateri Duranceau, Isabeau Prémont-Schwarz **Published:** 2024-10-11T21:45:49Z **Abstract:** This paper investigates whether the hexagonal structure of grid cells provides any performance benefits or if it merely represents a biologically convenient configuration. Utilizing the Vector-HaSH content addressable memory model as a model of the grid cell -- place cell network of the mammalian brain, we compare the performance of square a...Votes: 0GitHub stars: 3
- Arxiv 1308 2350 Learning Features And Their Transformations By SpaLearning Features and their Transformations by Spatial and Temporal Spherical Clustering (arXiv: 1308.2350)Votes: 0GitHub stars: 3
- Arxiv 1407 3501 Robots That Can Adapt Like AnimalsRobots that can adapt like animals (arXiv: 1407.3501)Votes: 0GitHub stars: 3