All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Tribev2 Brain Foundation ModelTRIBE v2 tri-modal foundation model for in-situ fMRI brain-to-image decoding with synthetic data augmentation. Addresses low-data regime challenges in brain decoding.Votes: 0GitHub stars: 3
- Trophic Structure Seizure PropagationTrophic structure predicts seizure propagation.Votes: 0GitHub stars: 3
- Trp Narrative Comprehension EegTransition-Related Potentials (TRPs) methodology for analyzing narrative comprehension in continuous EEG recordings using deep neural networks to detect cinematic cuts and extract context-dependent brain responses.Votes: 0GitHub stars: 3
- Trustworthy Qml RoadmapTrustworthy Quantum Machine Learning roadmap covering reliability, robustness, and security in the NISQ era. Addresses QML-specific risks including probabilistic behavior, device noise, and hybrid pipeline vulnerabilities. Activation: trustworthy QML, quantum ML reliability, QML robustness, NISQ era quantum security, quantum ML safety.Votes: 0GitHub stars: 3
- Turbovla Real Time VlaTurboVLA architecture for real-time vision-language-action models achieving 32 Hz inference with <1 GB VRAM. Reformulates conventional V→L→A pathway as direct V+L→A mapping with lightweight bidirectional vision-language interaction. Use when building efficient robotic manipulation systems, real-time VLA policies, or low-resource embodied AI agents.Votes: 0GitHub stars: 3
- Turn Opd Turn Level BudgetingTurnOPD methodology for efficient on-policy distillation of long-horizon agents. Uses adaptive rollout-depth budgeting and progressive turn-normalized loss to address inefficiencies in vanilla agent OPD.Votes: 0GitHub stars: 3
- Tutorial On Answering Questions About Images With Deep Learning**arXiv ID:** 1610.01076 **Authors:** Mateusz Malinowski, Mario Fritz **Published:** 2016-10-04T16:29:28Z **Abstract:** Together with the development of more accurate methods in Computer Vision and Natural Language Understanding, holistic architectures that answer on questions about the content of real-world images have emerged. In this tutorial, we build a neural-based approach to answer questions about images. We base our tutorial on two datasets: (mostly on) DAQUAR, and (a bit on) VQA. Wit...Votes: 0GitHub stars: 3
- Two Branch Css Ldpc ConstructionMethodology for constructing regular CSS QLDPC (Quantum Low-Density Parity-Check) base matrices using a two-branch multiplicative-coset approach over finite fields. Use when: (1) designing quantum error-correcting codes, (2) constructing CSS codes from LDPC base matrices, (3) optimizing quantum code parameters for fault-tolerant computation, (4) implementing belief propagation decoding for quantum codes, (5) analyzing finite-length quantum code performance. Keywords: CSS LDPC, quantum error c...Votes: 0GitHub stars: 3
- Uncertainty Guided Hypergraph RefinementUncertainty-Guided Hypergraph Refinement (UGHR) methodology for medical image segmentation. Uses entropy-based uncertainty maps from coarse predictions to spatially guide targeted refinement in boundary/transition regions. Decouples foreground/background hyperedge prototypes to prevent noise propagation. Use when performing medical image segmentation with ambiguous boundaries, small lesions, or ill-defined edges.Votes: 0GitHub stars: 3
- Uncloneable Encryption MicrocryptUncloneable encryption methodology in microcrypt — boosting one-time secure uncloneable bits to many-time secure multi-bit uncloneable encryption. Reduces assumptions for existence of uncloneable indistinguishability in symmetric key encryption. Use when analyzing quantum encryption schemes, designing ciphertext cloning prevention protocols, or formalizing uncloneable indistinguishability in quantum cryptography. arXiv: 2605.27647Votes: 0GitHub stars: 3
- Understanding Predictive Coding As An Adaptive Trustregion Method**arXiv ID:** 2305.18188 **Authors:** Francesco Innocenti, Ryan Singh, Christopher L. Buckley **Published:** 2023-05-29T16:25:55Z **Abstract:** Predictive coding (PC) is a brain-inspired local learning algorithm that has recently been suggested to provide advantages over backpropagation (BP) in biologically relevant scenarios. While theoretical work has mainly focused on showing how PC can approximate BP in various limits, the putative benefits of "natural" PC are less understood. Here we dev...Votes: 0GitHub stars: 3
- Unifying Von Neumann Hpc Neuromorphic Ebbrains统一冯诺依曼HPC与神经形态计算的EBRAINS工作流框架 - 透明跨平台执行SNN，支持异构架构无缝切换。Votes: 0GitHub stars: 3
- Universally Robust Quantum ControlUniversal framework for noise-agnostic quantum control of open quantum systems. Achieves high-fidelity operations (>99%) without prior environmental noise characterization. Bridges theoretical control design with experimental constraints for fault-tolerant quantum technologies. Based on Ding et al. (npj Quantum Info 12, 22, 2026).Votes: 0GitHub stars: 3
- Unsupervised Object Keypoint Learning Using Local Spatial Predictability**arXiv ID:** 2011.12930 **Authors:** Anand Gopalakrishnan, Sjoerd van Steenkiste, Jürgen Schmidhuber **Published:** 2020-11-25T18:27:05Z **Abstract:** We propose PermaKey, a novel approach to representation learning based on object keypoints. It leverages the predictability of local image regions from spatial neighborhoods to identify salient regions that correspond to object parts, which are then converted to keypoints. Unlike prior approaches, it utilizes predictability to discover object ...Votes: 0GitHub stars: 3
- Updated Neuron Model AnnUpdating the standard neuron model in artificial neural networks - replacing the simplistic point neuron model with more realistic cortical cell representationsVotes: 0GitHub stars: 3
- Use Of Graph Neural Networks In Aiding Defensive Cyber Operations**arXiv ID:** 2401.05680 **Authors:** Shaswata Mitra, Trisha Chakraborty, Subash Neupane, Aritran Piplai, Sudip Mittal **Published:** 2024-01-11T05:56:29Z **Abstract:** In an increasingly interconnected world, where information is the lifeblood of modern society, regular cyber-attacks sabotage the confidentiality, integrity, and availability of digital systems and information. Additionally, cyber-attacks differ depending on the objective and evolve rapidly to disguise defensive systems. Howev...Votes: 0GitHub stars: 3
- Using Artificial Bee Colony Algorithm For Mlp Training On Earthquake Time Series Data Prediction**arXiv ID:** 1112.4628 **Authors:** Habib Shah, Rozaida Ghazali, Nazri Mohd Nawi **Published:** 2011-12-20T09:50:53Z **Abstract:** Nowadays, computer scientists have shown the interest in the study of social insect's behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm...Votes: 0GitHub stars: 3
- Vacuum Entanglement ExtractionVacuum entanglement extraction protocols from quantum field theory. Covers local operation protocols for harvesting entanglement from vacuum states and applications to distributed quantum computing and quantum networking. Use when: vacuum entanglement, entanglement harvesting, quantum field theory communication, distributed quantum computing, quantum networking, vacuum resource, QFT entanglement, local operations entanglement.Votes: 0GitHub stars: 3
- Variance Brain Foundation Models ForgotBrain foundation models (BFMs) lose third-order statistics (co-skewness) during pretraining - variance allocation problem where billion-parameter models predict cognition worse than linear FC. Solution: preserve co-skewness subspace. Activation: brain foundation model, variance allocation, co-skewness, third-order statistics, BFM pretraining, functional connectivity, cognitive prediction.Votes: 0GitHub stars: 3
- Variational Long Range EntanglingVariational quantum algorithms with sparse long-range entangling gates for neutral atoms and trapped ions (arXiv: 2607.07547)Votes: 0GitHub stars: 3
- Variational Quantum AlgorithmsVariational Quantum Algorithms methodology covering CVQE (Cascaded Variational Quantum Eigensolver), certified QNN training via QIBP, and resource-efficient quantum optimization. Use when designing variational quantum circuits, optimizing NISQ-era algorithms, implementing certified quantum machine learning, or applying quantum algorithms to combinatorial optimization problems. Covers VQE variants, quantum interval bound propagation, compact binary encoding for quantum optimization, and divide...Votes: 0GitHub stars: 3
- Vehicle Lane Change Prediction Based On Knowledge Graph Embeddings And Bayesian Inference**arXiv ID:** 2312.06336 **Authors:** M. Manzour, A. Ballardini, R. Izquierdo, M. A. Sotelo **Published:** 2023-12-11T12:33:44Z **Abstract:** Prediction of vehicle lane change maneuvers has gained a lot of momentum in the last few years. Some recent works focus on predicting a vehicle's intention by predicting its trajectory first. This is not enough, as it ignores the context of the scene and the state of the surrounding vehicles (as they might be risky to the target vehicle). Other works as...Votes: 0GitHub stars: 3
- Verifiable Quantum AdvantageDesign and analysis of verifiable quantum algorithms that demonstrate quantum supremacy. Use when working on quantum algorithms with provable advantage, benchmarking quantum vs classical performance, designing quantum verification protocols, or analyzing quantum supremacy claims. Triggers: verifiable quantum advantage, quantum supremacy, quantum benchmarking, quantum verification, quantum echoes algorithm.Votes: 0GitHub stars: 3
- Verify Repair Repeat Or Stop Robust Stopping For NDerived from arXiv:2607.17641 - Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM AgentsVotes: 0GitHub stars: 3
- Vision Bottleneck V1Vision as looking and seeing through a bottleneck framework. Explains V1 as an information bottleneck that optimizes visual representation given retinal sampling constraints. Addresses why vision research progress is slower downstream than upstream of V1. Keywords: vision bottleneck, V1, primary visual cortex, information theory, visual representation, retinal sampling.Votes: 0GitHub stars: 3
- Vlm Transmon CalibrationSelf-specializing Vision-Language Model agent for physics-grounded transmon chip calibration. Uses zero-weight-update online adaptation via human-readable device notes, gradient-free strategy refinement with paired-snapshot accept gate, and physics-grounded simulation with realistic drift/wall-time/leakage. Activation: transmon calibration, quantum chip tuning, VLM calibration agent, gradient-free online adaptation, superconducting qubit calibration, 量子芯片校准Votes: 0GitHub stars: 3
- Vnvspec Requirements Vv SpecificationVNVSpec methodology for machine-readable verification and validation (V&V) specifications that bridge high-level systems-engineering requirements with low-level test results. Use when: (1) designing or auditing requirements-to-tests traceability for AI-enabled, cyber-physical, or safety-critical systems; (2) building executable V&V specs in CI; (3) mapping standards clauses (EU AI Act, ISO 21448, UL 4600) to automated evidence; (4) evaluating agent-generated code against decomposed requiremen...Votes: 0GitHub stars: 3
- Vocabulary Extension Initializer[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]Votes: 0GitHub stars: 3
- Von Neumann Quantum ControlInfinite-dimensional quantum controllability framework using von Neumann algebra techniques. Extends the finite-dimensional Lie algebra rank condition to bilinear quantum systems on infinite-dimensional Hilbert spaces by interpreting algebraic objects through affiliated operators. Use when: analyzing controllability of infinite-dimensional quantum systems, designing quantum control protocols for continuous-variable systems, generalizing Lie algebra rank conditions beyond finite dimensions, or...Votes: 0GitHub stars: 3
- Vqa Dynamic Portfolio OptimizationVQA methodology for dynamic portfolio optimization — sampling strategies (adaptive CVaR scheduling), optimizer scheduling (PSO+NFT hybrid), and hardware-aware ansatz design (data-guided colored layout, heavy-hex deep-chain layout). Activation: vqa portfolio, dynamic portfolio optimization, CVaR scheduling, hardware-aware ansatz, heavy-hex layout, PSO optimizer, quantum portfolio, 动态投资组合优化Votes: 0GitHub stars: 3
- Vqe Active Space Drug BenchmarkSystematic benchmark methodology for active space selection in VQE-driven quantum drug discovery pipelines. Classifies molecule suitability for quantum computing using chemically grounded metrics, evaluates VQE across UCCSD and HEA ansatze with both simulation and QPU execution on drug-like molecules (lovastatin, oseltamivir, morphine).Votes: 0GitHub stars: 3
- Vqml Beyond Symmetry DesignBeyond-symmetry structural design patterns for variational quantum machine learning. Use when designing VQML ansatze that go beyond symmetry constraints, selecting parametrizations that balance expressivity and trainability within symmetry-preserving subspaces, or analyzing structural choices in quantum neural network architectures. Covers equivariant VQA design, symmetry-breaking regularization, and structural ansatz selection criteria.Votes: 0GitHub stars: 3
- War Workload Aware Rollouts For Synchronous AgentiDerived from arXiv:2607.17299 - WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement LearningVotes: 0GitHub stars: 3
- Watts Infrastructure For Openended Learning**arXiv ID:** 2204.13250 **Authors:** Aaron Dharna, Charlie Summers, Rohin Dasari, Julian Togelius, Amy K. Hoover **Published:** 2022-04-28T01:54:53Z **Abstract:** This paper proposes a framework called Watts for implementing, comparing, and recombining open-ended learning (OEL) algorithms. Motivated by modularity and algorithmic flexibility, Watts atomizes the components of OEL systems to promote the study of and direct comparisons between approaches. Examining implementations of three OEL a...Votes: 0GitHub stars: 3
- Web To Obsidian Fetcher MaintenanceMaintaining automated scripts that fetch web content and save to Obsidian notes. Covers deduplication strategies, Cloudflare-protected sites, index management, and common cron job pitfalls. Use when: (1) building or debugging automated content fetchers, (2) Obsidian note accumulation has duplicates, (3) web scraping fails due to Cloudflare/bot protection, (4) maintaining cron jobs that save content to Obsidian.Votes: 0GitHub stars: 3
- Weight Norm Criticality Loss SpikesWeight-norm Criticality framework for understanding loss spikes in neural network training induced by normalization and weight decay interactions. Use when analyzing training instability, criticality phenomena, or optimization dynamics in deep learning models with scale-invariant components.Votes: 0GitHub stars: 3
- What 81000 People Want From AiWhat 81,000 people want from AIVotes: 0GitHub stars: 3
- What Are Neural Networks Made Of**arXiv ID:** 1909.09588 **Authors:** Rene Schaub **Published:** 2019-08-25T21:59:26Z **Abstract:** The success of Deep Learning methods is not well understood, though various attempts at explaining it have been made, typically centered on properties of stochastic gradient descent. Even less clear is why certain neural network architectures perform better than others. We provide a potential opening with the hypothesis that neural network training is a form of Genetic Programming.Votes: 0GitHub stars: 3
- What Matters For Adversarial Imitation Learning**arXiv ID:** 2106.00672 **Authors:** Manu Orsini, Anton Raichuk, Léonard Hussenot, Damien Vincent, Robert Dadashi, Sertan Girgin, Matthieu Geist, Olivier Bachem, Olivier Pietquin, Marcin Andrychowicz **Published:** 2021-06-01T17:58:08Z **Abstract:** Adversarial imitation learning has become a popular framework for imitation in continuous control. Over the years, several variations of its components were proposed to enhance the performance of the learned policies as well as the sample complex...Votes: 0GitHub stars: 3
- When Fireflies Cluster Enhancing Automatic Clustering Via Centroidguided Firefly Optimization**arXiv ID:** 2605.18460 **Authors:** MKA Ariyaratne, Azwirman Gusrialdi, Yury Nikulin, Jaakko Peltonen **Published:** 2026-05-18T14:22:13Z **Abstract:** This work presents a novel variant of the Firefly Algorithm (FA) for data clustering, addressing limitations of traditional methods like K-Means that struggle with non-uniform cluster shapes, densities, and the need for pre-defining the number of clusters. The proposed algorithm introduces a centroid movement strategy and a multi-objective f...Votes: 0GitHub stars: 3
- When Shippers Become Algorithms Candidate ExposureSkill generated from arXiv paper 2607.19967: When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight MarketsVotes: 0GitHub stars: 3
- When To Smell In StereoStereo olfaction utility analysis framework - determines when dual nostril 'stereo' olfaction provides advantages over single nostril 'mono' olfaction based on odor concentration gradients and spatial correlation length scales. Use when analyzing animal olfactory navigation, odor trail tracking, or surface-based olfactory search strategies.Votes: 0GitHub stars: 3
- Why Classic Transformers Are Shallow And How To Make Them Go Deep**arXiv ID:** 2312.06182 **Authors:** Yueyao Yu, Yin Zhang **Published:** 2023-12-11T07:49:16Z **Abstract:** Since its introduction in 2017, Transformer has emerged as the leading neural network architecture, catalyzing revolutionary advancements in many AI disciplines. The key innovation in Transformer is a Self-Attention (SA) mechanism designed to capture contextual information. However, extending the original Transformer design to models of greater depth has proven exceedingly challenging,...Votes: 0GitHub stars: 3
- Why Does Ctc Result In Peaky Behavior**arXiv ID:** 2105.14849 **Authors:** Albert Zeyer, Ralf Schlüter, Hermann Ney **Published:** 2021-05-31T10:03:14Z **Abstract:** The peaky behavior of CTC models is well known experimentally. However, an understanding about why peaky behavior occurs is missing, and whether this is a good property. We provide a formal analysis of the peaky behavior and gradient descent convergence properties of the CTC loss and related training criteria. Our analysis provides a deep understanding why peaky beh...Votes: 0GitHub stars: 3
- Wigner Function ReconstructionWigner function reconstruction methodology for continuous-variable quantum system characterization. Combines provably efficient regression for sparse states (binomial codes, cat states) with deep learning for general states (GKP). Use when: (1) characterizing CV quantum systems, (2) reconstructing Wigner functions from sparse measurements, (3) identifying error processes in QEC cycles, (4) phase-space tomography, (5) reducing measurement overhead in quantum state characterization. Trigger wor...Votes: 0GitHub stars: 3
- Wind Solar Csfs Feature SelectionSkill for applying Cluster-based Sequential Feature Selection (CSFS) to improve feature selection in wind and solar power prediction tasks. Use when working with renewable energy prediction datasets that have many environmental variables and need efficient, model-agnostic feature selection.Votes: 0GitHub stars: 3
- Worldcuparena Fine Grained Evaluation Of LanguageDerived from arXiv:2607.18084 - WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football ForecastingVotes: 0GitHub stars: 3
- Zero Shot Quantum NasZero-shot Quantum Neural Architecture Search methodology for VQA circuit optimization without classical search loop. Use when: (1) designing variational quantum circuits, (2) optimizing quantum architecture without expensive search, (3) reducing classical overhead in VQA, (4) NISQ-era algorithm design, (5) quantum machine learning circuit selection.Votes: 0GitHub stars: 3
- Zhusuan A Library For Bayesian Deep Learning**arXiv ID:** 1709.05870 **Authors:** Jiaxin Shi, Jianfei Chen, Jun Zhu, Shengyang Sun, Yucen Luo, Yihong Gu, Yuhao Zhou **Published:** 2017-09-18T11:30:08Z **Abstract:** In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks a...Votes: 0GitHub stars: 3
- Parallel Tempering Snn CspParallel tempering (replica exchange) integrated into a stochastic Spiking Neural Network (SNN) solver for Constraint Satisfaction Problems (CSPs). Multiple replica networks run at different inverse temperatures and periodically exchange temperatures (not states), letting replicas cross energy barriers unreachable by fixed-temperature dynamics. First integration of PT into an SNN-based CSP solver; concentrated gains on hard SATLIB uf20-91 instances. Use when building or improving stochastic S...Votes: 0GitHub stars: 3