Menu
Skills in this repository
SkillsMP has collected 4,114 skills from hiyenwong/ai_collection. Open a skill to review its source and details.
hiyenwong/ai_collectionShowing 40 of 4,114 collected skills.
Safe deployment patterns for quantum control policies in cyber-physical systems. Covers Q-DASC discrepancy-attributed safe quantum control framework, Simplex architecture for quantum-classical switching, and certified safety layers for variational quantum…
Quantum Software Engineering (QSE) certification patterns - hybrid FPGA+AI frameworks for validating quantum device entanglement using CHSH inequality and LLM-guided optimization
Quantum software engineering practical patterns for FPGA-based quantum control systems with AI integration. Covers hardware-aware compilation, real-time feedback control, and fault-tolerant quantum computing workflows. Activation: quantum software…
Systems engineering methodology for quantum processor design. Integrates hardware architecture, control software, error correction, and resource management into a unified engineering framework. Covers scalability, reliability, and performance optimization for…
Comparative analysis and design framework for verifiable blind quantum computing (VBQC) client architectures. Covers emission-based, measurement-based, and rotation-based client designs with single-server, single-client protocols using measurement-based…
Risk-averse ensemble control methodology for control-affine systems with uncertainty — provides rigorous treatment beyond expectation-based optimization, with applications in quantum control and Neural ODE training.
Rubric-Guided GRPO for Constraint-Aware Quantum Circuit Synthesis. LLM-based quantum circuit generation optimized via Group Relative Policy Optimization with domain-grounded programmatic rubrics for T-gate reduction, hardware topology compliance, and unitary…
Safety-critical control framework for quantum systems with formal guarantees. Combines control barrier functions with quantum dynamics to ensure quantum states remain within safe operational regions during control operations.
Vectorized Quantum Control Processor (QCP) architecture using RISC-V Vector Extension with quantum-oriented extensions. Addresses up to 128 qubits per instruction with hardware-based halt-resume protocol within 80ns. Use when: designing quantum control…
Hierarchical Bayesian Statistical Learning (HBSL) model for individual statistical learning trajectories from EEG data. Models how individuals discover structure in sensory sequences, with applications to dyslexia research and cognitive development.…
Source text: Chinese
Multi-agent LLM physics-grounded digital twin simulator for cryogenic fault diagnosis in quantum computing infrastructure. Uses dilution refrigerator forward physics model with learned noise fingerprint + multi-agent LLM operations layer. Activation:…
AIGOR - modular, event-driven neuromorphic architecture for configurable SNN inference. Organizes neurons into timestep-synchronized processing cores with packet-switched communication, supporting multiple neuron models (LIF, HH, AH) and configurable…
Open-source hardware-aware simulation framework for mixed-signal SNNs enabling comparative analysis across neuron models (LIF, HH, AH), synapse types (floating-gate, ReRAM), and architectures. Reports accuracy with hardware metrics (area, power, quantization…
First-in-human quantum entanglement imaging using J-PET plastic scintillator scanner for PET + entanglement degree tomography. Exploits polarization correlations of annihilation photons for enhanced diagnostics. Use when building quantum-enhanced PET imaging…
Quantum imaging via kurtosis-difference weighted covariance for SPDC photon correlation detection - reduces acquisition time by 40x compared to standard covariance methods
DendriCL methodology for dendritic in-context learning in single-layer spiking neural networks. Demonstrates that a single dendritic compartment with online-LMS dynamics is sufficient for general-purpose ICL without attention, depth, or inference-time…
Multi-agent framework (MAST) for predicting which test cases require maintenance after production code changes. Uses agentic information fusion across code diffs, test history, and semantic analysis to identify tests needing updates. Activation: test…
Survey of agentic IoT architectures, applications, and challenges toward the Internet of Agents. Examines how AI integration transforms IoT from passive data collection to intelligent systems with anomaly detection, predictive maintenance, and optimization.…
An agentic divide-conquer-Combine copilot for causal discovery from high-dimensional data. Leverages massive prior knowledge to address causal identifiability issues in real-world settings where core assumptions are violated. Activation: CausalSteward, causal…
Orchestrating mathematical reasoning agents with fact-graph memory. Addresses scaling and orchestration challenges for LLM-based mathematical reasoning agents by coordinating parallel proof attempts using a shared fact-graph memory structure. Activation:…
Pre-registered experiment on small economies of frontier LLM agents (Claude Opus 4.8), testing information-theoretic capacity regions for wealth growth under market coupling and mean-field residual attractor dynamics. Activation: LLM agent economies,…
Studies whether social structure (role, audience, relational context) changes what LLM agents express publicly, without explicit objectives in prompts. LLM agents will increasingly act in socially structured settings where what is advantageous or costly to…
Institutional AI platform (LLMoxie) with three-tiered architecture supporting multi-cloud and on-premise inference, LiteLLM/MLflow control plane for authentication, budgeting, PII masking, and observability, and an application augmentation layer for AI coding…
MCP-enabled agentic AI architecture for autonomous control of vendor-agnostic IPoDWDM networks. Demonstrates live end-to-end lifecycle multi-layer automation and closed-loop control using GNPy and telemetry, validated on a real testbed. Activation: MCP,…
Return-preserving communication unlearning for efficient multi-agent coordination under bandwidth constraints. Enables MARL agents to selectively forget inter-agent communications while preserving coordination returns, addressing the trade-off between…
LLM-based agents for automating business process execution using organizational memory. General-purpose LLMs lack organization-specific knowledge; this work extracts and structures organizational knowledge from human-oriented artifacts to enable reliable…
Benchmarking contextual integrity in multi-user agentic systems. As LLM agents evolve into shared organizational infrastructure, new privacy risks emerge from inter-agent messages, shared memory, and cross-user information exposure. Activation: contextual…
Conflict-aware replicated memory contract for multi-agent systems. Agent systems accumulate conflicting observations across branches, retries, and replicas. StateFuse builds a conflict-preserving memory layer on standard version control principles, avoiding…
A 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:…
Physics-grounded digital twin + multi-agent LLM methodology for fault diagnosis in critical infrastructure. Uses a forward physics model with learned noise fingerprint to drive LLM agents for diagnostic tasks. Trigger words: fault diagnosis, digital twin,…
Anthropic's discovery of emergent mental workspace (J-space) in Claude using Jacobian lens technique. Interpretability method for detecting hidden reasoning, misalignment, and enabling counterfactual reflection training for AI safety.
In-context learning methodology for antigen-specific antibody affinity ranking in computational immunology
Low-depth quantum simulation of non-Markovian dynamics using trajectory mixing — trades entangling gates for statistical mixture of independent pure state trajectories to reduce circuit depth on NISQ hardware. Activation: non-Markovian simulation, trajectory…
Scalable Perturbation Learning for Online Self-Supervised Echo State Networks - orthogonal decomposition reduces perturbation dimension from reservoir to input dimension, enabling scalable hardware-compatible online learning
Maximum entropy path ensemble embedding for manifold learning and dimensionality reduction
AI-assisted formal verification methodology for quantum information theory using Lean 4 theorem prover
Quantum reservoir computing methodology using metrologically useful state preparation via unitary operations to enhance predictive performance on chaotic systems. Combines classical autoencoders with quantum metrology techniques in QRC pipelines.
Hilbert-Schmidt Speed (HSS) contractivity analysis for quantum channels — proves HSS contracts under unital CPTP maps, enabling non-Markovianity detection and discrimination of unital vs non-unital Markovian dynamics. Activation: hilbert schmidt speed,…
Neuromorphic Silicon Neuron Controller for Adaptive Deep Brain Stimulation in Parkinson's Disease - CMOS-implemented SiLIF-DBS controller achieving 5.85%/uW beta suppression efficiency with 75% power reduction vs open-loop
Logarithmic negativity as exact entanglement cost methodology — proving logarithmic negativity equals the exact entanglement cost for typical quantum states. Use when analyzing quantum entanglement quantification, entanglement cost computation, quantum…