All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 16,459
- 686
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 8,761–8,784 of 16,459 skills
- Visual Semantic Decoding EcogVisual Semantic Decoding of Electrocorticography from Video Stimuli using End-to-End Deep Learning. Extract visual semantic categories from ECoG brain signals during video viewing using Transformer-based deep learning models. Use when working with ECoG neural decoding, brain-computer interfaces, or visual semantic classification from neural data.Votes: 0GitHub stars: 3
- O Vad Industrial Video Anomaly Detection Through ODerived from arXiv:2607.18142 - O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and ReasoningVotes: 0GitHub stars: 3
- Native Video Action Pretraining Generalizable Robot ControlLingBot-VA 2.0: video-action foundation model built from the ground up for robot embodiment. Semantic visual-action tokenizer, causal pretraining from scratch, sparse MoE backbone, asynchronous inference for real-time closed-loop control. Few-shot generalization across manipulation tasks. Activation: video-action model, robot control, pretraining, vision-language-action, generalizable manipulation.Votes: 0GitHub stars: 3
- Threshold Based Snn Event Driven Status UpdateThreshold-Based Spiking Neural Networks for Event-Driven Status Update Systems - lightweight RL approach using SNNs with explicit threshold policy representation for IoT status updates that jointly minimizes Age of Information (AoI) and transmission energy. Use when designing energy-efficient event-driven IoT systems, optimizing information freshness vs energy trade-offs, or implementing threshold policies with SNNs.Votes: 0GitHub stars: 3
- Threshold Based Snn Event Driven Status UpdateThreshold-Based Spiking Neural Networks for Event-Driven Status Update Systems - lightweight RL approach using SNNs with explicit threshold policy representation for IoT status updates that jointly minimizes Age of Information (AoI) and transmission energy. Use when designing energy-efficient event-driven IoT systems, optimizing information freshness vs energy trade-offs, or implementing threshold policies with SNNs.Votes: 0GitHub stars: 3
- Numa Balancing Spiking Network HpcNUMA balancing performance optimization for spiking network simulations on HPC systems. Identifies that automatic NUMA balancing can reduce energy efficiency by 30% in spiking network simulations and provides methodology for per-job NUMA balancing control to optimize performance and energy consumption.Votes: 0GitHub stars: 3
- Multi Objective Snn OscillationMulti-objective genetic algorithm (NSGA-III) optimization of Izhikevich neuron-based recurrent spiking neural networks for simultaneously fitting neural firing rates and network oscillation frequencies. Applicable to SNN parameter tuning, brain organoid modeling, and spiking neural network design.Votes: 0GitHub stars: 3
- Globally Optimal Snn TrainingGlobally optimal SNN training via parameter reconstruction. Convexifies parallel recurrent threshold networks (subsuming parallel SNNs) and uses parameter reconstruction to avoid surrogate gradient approximation errors. Use when training SNNs without surrogate gradients or seeking globally optimal solutions.Votes: 0GitHub stars: 3
- Current Injection Spiking Neural NetworkCurrent Injection Spiking Neural Network (CIS-Fuse) methodology for infrared and visible image fusion. Introduces the current injection spiking (CIS) operator that performs cross-modal fusion directly at the membrane-potential level, preserving subthreshold responses from both modalities before spike firing. Use when implementing energy-efficient multi-modal image fusion with spiking neural networks.Votes: 0GitHub stars: 3
- Cognisnn Random Graph ArchitectureCogniSNN: Enabling Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability with Random Graph Architectures in Spiking Neural NetworksVotes: 0GitHub stars: 3
- Spike Htr Spiking Neural TransformerSpike-HTR: Spiking Neural Transformer for Handwritten Text Recognition - hybrid spiking recognizer that controls both spiking steps and sequence positions processed by deep sequence mixer. Use when working with handwritten text recognition, spiking neural networks for computer vision, or computational efficiency in SNNs.Votes: 0GitHub stars: 3
- Github Code ReviewReview code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with gh CLI or falls back to git + GitHub REST API via curl.Votes: 0GitHub stars: 3
- Smm Transformer Spiking MultimodalSMM Transformer methodology leveraging Spiking Neural Networks (SNNs) for multimodal tasks by integrating spiking mechanisms into transformer architectures to achieve energy efficiency while maintaining performance across diverse modalities.Votes: 0GitHub stars: 3
- Single Entity Spiking Neuron ModelsComprehensive survey of single-entity spiking neuron models — classification of biologically plausible neural systems including discrete and continuous analogs, membrane potential dynamics, and components affecting neural dynamics for accurate simulation of biological processes.Votes: 0GitHub stars: 3
- Hidden Tree Markov Networks Deep And Wide Learning For Structured Data**arXiv ID:** 1711.07784 **Authors:** Davide Bacciu **Published:** 2017-11-21T13:50:34Z **Abstract:** The paper introduces the Hidden Tree Markov Network (HTN), a neuro-probabilistic hybrid fusing the representation power of generative models for trees with the incremental and discriminative learning capabilities of neural networks. We put forward a modular architecture in which multiple generative models of limited complexity are trained to learn structural feature detectors whose outputs ar...Votes: 0GitHub stars: 3
- Runtime Monitoring Distributed Cps No Global ClockMonitor distributed CPS without global clock using STL.Votes: 0GitHub stars: 3
- Explainable Ai Xai SurveySkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Real Time Optimal Control Shallow Recurrent DecoderReal-time optimal control framework using SHallow REcurrent Decoder networks-based Reduced Order Modeling (SHRED-ROM) for high-dimensional and parametric dynamical systems. Enables synthesis of closed-loop controllers from limited state sensor readings with effective distributed control actions in new scenarios.Votes: 0GitHub stars: 3
- Subsystem Qec MetrologySubsystem quantum error correction methodology for noisy quantum metrology — uses subsystem stabilizer codes to achieve Heisenberg limit with simplified protocols. Covers syndrome-free protocols with single ancilla qubit, Floquet code protection for time-dependent metrological signals, and general conditions for subsystem codes in metrology. Use when: protecting quantum metrology from noise with minimal ancilla overhead, designing syndrome-free metrological protocols, implementing Floquet cod...Votes: 0GitHub stars: 3
- Scaling Laws Quantum StatesScaling laws methodology for Neural-Network Quantum States — power-law relations between loss, architecture size, and compute for characterizing the complexity of quantum many-body learning problems. Use when: analyzing NNQS complexity, benchmarking variational ansätze, transformer wave functions, frustrated quantum systems, scaling collapse in physics, variational quantum states.Votes: 0GitHub stars: 3
- Rl List Sequential Qldpc DecodingReinforcement learning-based list sequential belief propagation decoder for QLDPC codes — extends RL-S scheduling with list-based branch exploration for improved decoding convergence.Votes: 0GitHub stars: 3
- Quantum Stationary Point FindingQuantum comparison oracle methodology for finding stationary points of non-convex functions with quadratic speedup — O~(n/epsilon^1.5) quantum vs O~(n^2/epsilon^1.5) classical queries. ICML 2026 paper by Wang et al.Votes: 0GitHub stars: 3
- Quantum Ring AllreduceQuantum Ring All-Reduce methodology for distributed learning — reduces per-link communication by 2x using superdense coding, enables information-theoretically private aggregation via verified entanglement, and achieves exponential communication separation for sign-consistency auditing.Votes: 0GitHub stars: 3
- Quantum Ring Allreduce DistributedQuantum ring all-reduce protocol for distributed ML training — uses pre-shared entanglement and superdense coding for 2x communication reduction plus information-theoretic privacy guarantees. Covers composable ε-secure aggregation via verified entanglement and exponential separation in sign-consistency auditing.Votes: 0GitHub stars: 3