メニュー
このリポジトリの skills
SkillsMP は hiyenwong/ai_collection から 4,114 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
hiyenwong/ai_collection収集済み skill 4,114 件中 40 件を表示しています。
Empirical framework to estimate the minimum training-set size needed to reach a target accuracy, via logarithmic learning-curve fitting and a "stability point" metric. Use when planning data collection campaigns, deciding how much labeled data is enough, or…
原文の言語: 英語
Multi-ensemble mean-field reduction for networks of globally coupled phase oscillators with arbitrary (empirical) frequency distributions. Extends Ott-Antonsen to heterogeneity beyond Lorentzians. arXiv:2607.09516
原文の言語: 英語
Methodology for evaluating LLM capability to develop N-day exploits from public patches — measuring PoC generation, full exploit chain development, and patch-gap risk assessment.
原文の言語: 英語
Skill for applying the methods from the arXiv paper: Structured Fluctuations and the Information Dynamics of Self-Maintenance in Growing Neural Cellular Automata (arXiv:2607.12403). This skill provides a framework for analyzing internal fluctuations in neural…
原文の言語: 英語
Domain relevance filtering methodology for neuroscience paper selection in automated research workflows. Provides criteria for determining when arXiv papers are relevant to neuroscience, brain networks, neural dynamics, spiking neural networks, and…
原文の言語: 英語
Methodology 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,…
原文の言語: 英語
Parallel 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…
原文の言語: 英語
Topological time-series (TDA) framework for EEG analysis — sliding-window Takens delay embeddings + Vietoris-Rips filtrations to extract Dynamic Betti Curves, then topology-conditioned flow matching / rectified flow for neural signal synthesis and rare-event…
原文の言語: 英語
Parallel Tempering integration for Spiking Neural Network-based CSP solvers — overcoming local-minimum traps in stochastic SNN optimization. From arXiv:2607.08897 (Uludag et al., Jul 2026).
原文の言語: 英語
Self-adaptive anomaly detection for autonomous cyber-physical systems. Integrates RL-based detector selection, ensemble drift detection, and human-in-the-loop retraining with catastrophic forgetting prevention.
原文の言語: 英語
Framework for designing heterogeneous AI architectures that avoid the 'giant hippocampus' problem of applying one architectural template (like Transformers) to all cognitive tasks, instead using structurally diverse modules with standardized interfaces.
原文の言語: 英語
Visual 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…
原文の言語: 英語
Stereo 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…
原文の言語: 英語
Efficient Low-Rank and Sparse Attention Approximation (ELSAA) methodology for training Transformers with longer contexts while preserving both sharp token-level interactions and broad contextual mixing.
原文の言語: 英語
HeadCast methodology for efficient autoregressive video generation through training-free attention head classification and KV cache optimization.
原文の言語: 英語
Comparative methodology for language-specific versus cross-lingual knowledge graphs in implicit aspect identification for lower-resource languages, with task-specific fine-tuning strategies.
原文の言語: 英語
PoTRE (Poly-Topological Reasoning Ensembles) framework for complex reasoning through heterogeneous multi-agent architecture inspired by cognitive heterogeneity.
原文の言語: 英語
Skill derived from arXiv paper 2606.31584: A Large-Scale Empirical Evaluation of MMAO Under Fair-Budget Continuous and Discrete Benchmarks
原文の言語: 英語
Skill generated from arXiv paper 2607.19678: Reference-Free Evaluation of Reasoning in Open-Ended Question Answering
原文の言語: 英語
Recurring pipeline for fetching Anthropic research articles and turning reusable methodologies into ai_collection skills. Triggers on scheduled/cron Anthropic research fetches, "fetch anthropic research", extracting methods from anthropic.com/research, or…
原文の言語: 英語
Doob-barrier-conditioned diffusion methodology for turning analog neuromorphic hardware noise into a continual-learning resource — per-synapse consolidation via Doob h-transform creates noise-amplified restoring force that yields inverted-U noise-retention…
原文の言語: 英語
Data-driven predictive control (DeePC) framework for nonlinear systems that localizes the predictor by weighting data columns according to proximity to the current operating point, retaining the full data matrix and its rank for guaranteed feasibility.…
原文の言語: 英語
Skill generated from arXiv paper 2607.19865: DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations
原文の言語: 英語
Skill generated from arXiv paper 2607.20019: EvoDRC: A Self-Evolving Agentic Framework for Automated DRC Violation Repair
原文の言語: 英語
Skill generated from arXiv paper 2607.19837: Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents
原文の言語: 英語
Skill generated from arXiv paper 2607.19653: PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization
原文の言語: 英語
Single-stage shortcut-model trajectory planner for efficient offline model-based RL. Replaces two-stage consistency-distillation with one-stage step-size-conditioned shortcut models + feasibility-aware critic for fast one/few-step generative planning. Use…
原文の言語: 英語
Skill generated from arXiv paper 2607.19793: Silent Failures in Multimodal Agentic Search:A Diagnostic Taxonomy and Cross-Judge Evaluation
原文の言語: 英語
Skill generated from arXiv paper 2607.20255: The Ethics of Autonomous AI Agents for Offensive Security
原文の言語: 英語
Skill derived from arXiv paper 2607.11913: Towards Self-Evolving Agents: A Human-Inspired Adaptive Exploration-Exploitation Framework for Genetic Network Programming
原文の言語: 英語
SafeExplorer - drop-in PPO modification for RL with a deterministic recovery policy that prevents silent bias in on-policy updates. Uses score-function estimator only at safe timesteps, never evaluates recovery-policy density, so it stays valid where…
原文の言語: 英語
Skill generated from arXiv paper 2607.19894: Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
原文の言語: 英語
Topological time-series analysis methodology for dream-state EEG using Dynamic Betti curves, persistent homology, and topology-conditioned neural signal synthesis. arXiv:2607.09662
原文の言語: 英語
Skill generated from arXiv paper 2607.20268: PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
原文の言語: 英語
Concrete implementation recipe for dynamic neural manifold control on neuromorphic hardware (SpiNNaker 2), derived from arXiv 2607.07373. Covers rate→spike conversion, sparse circulant weight memory, three control knobs (gain/speed, additive current/shape,…
原文の言語: 英語
Skill generated from arXiv paper 2607.19941: A Framework of User Experience Principles for Human-AI Agent Interaction in the Workplace
原文の言語: 英語
Skill generated from arXiv paper 2607.20345: Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids
原文の言語: 英語
Skill generated from arXiv paper 2607.19985: Coordinating from Memory: Graph-Structured Experience Reuse for Multi-Agent Adaptation in Dynamic Manufacturing
原文の言語: 英語
Skill generated from arXiv paper 2607.19528: D3VL: Understanding Driving Scenes from 3D Time Series Data and Video with Language Models
原文の言語: 英語
Skill derived from arXiv paper 2606.29684: Evolutionary Hyperparameter Optimization to Find Lightweight CNN Models for Autonomous Steering
原文の言語: 英語