القائمة
Skills في هذا المستودع
جمع SkillsMP عدد ٤٬١١٤ من skills من hiyenwong/ai_collection. افتح أي skill لمراجعة مصدره وتفاصيله.
hiyenwong/ai_collectionعرض ٤٠ من أصل ٤٬١١٤ skills مجمعة.
Majorization lattice supermodularity and subadditivity framework — two structural majorization relations (precursors) underlying supermodularity and subadditivity of all sum-concave functions including Tsallis, Rényi, and Shannon entropies on the majorization…
لغة النص الأصلي: الإنجليزية
"Multi-Agent Runtime Grading via Incremental Normalization (MARGIN) — online confidence calibration for multi-agent AI coordination. Use when building multi-agent systems that need to weight agent trustworthiness at runtime: (1) coordinating responses from…
لغة النص الأصلي: الإنجليزية
Medical image domain adaptation and transfer learning methodology. Use when working with medical imaging AI tasks including: (1) adapting pre-trained models to new clinical domains with scarce annotated data, (2) parameter-efficient fine-tuning for medical…
لغة النص الأصلي: الإنجليزية
Category-theory-based brain-DNN alignment methodology using Naturality Violation Score (NVS). Shifts alignment assessment from per-stimulus correspondence to preservation of candidate transformations. Activation: brain-DNN alignment, naturality violation, RSA…
لغة النص الأصلي: الإنجليزية
On-Policy Distillation (OPD) methodology for transforming autoregressive models into diffusion language models efficiently, eliminating train-inference mismatch.
لغة النص الأصلي: الإنجليزية
Persona-Pruner methodology for sculpting lightweight language models for role-playing tasks. Enables efficient pruning of LMs while preserving persona-consistent stylized interactions. Use when: model pruning for role-playing, lightweight character chatbots,…
لغة النص الأصلي: الإنجليزية
Polynomial acyclicity constraints for efficient continuous causal discovery in visual semantic graphs - 33% speedup over exponential baseline with improved F1 scores.
لغة النص الأصلي: الإنجليزية
Readiness-First Pipeline (RRFP) methodology — treating pipeline schedules as non-binding hint orders rather than pre-committed execution sequences. Reduces bubbles and stage misalignment in distributed training under runtime variability. Up to 1.77x speedup…
لغة النص الأصلي: الإنجليزية
Reconfigurable Nonlinear Photonic Decision Network (RNPDN) methodology for adaptive photonic neuromorphic computing. Local physical learning rules with tunable stability-plasticity tradeoff, controlled memory formation via bistable photonic states, and…
لغة النص الأصلي: الإنجليزية
Train hundred-billion-parameter sparse MoE models on single nodes using reversible recurrence stacks and state-preserving growth principles with TQP optimizer strategy.
لغة النص الأصلي: الإنجليزية
Information-geometry unified memory architecture combining Riemannian retrieval (Fisher-Rao metric) with Fisher-guided discrete token distillation for resource-efficient long-term memory in dialogue agents.
لغة النص الأصلي: الإنجليزية
Contrastive on-policy self-distillation methodology for reasoning models that mitigates privilege-induced style drift
لغة النص الأصلي: الإنجليزية
Rollout-Adaptive Supervised Fine-Tuning (RASFT) for reasoning tasks - policy-aware SFT that calibrates expert supervision based on problem-level solvability from verified rollouts.
لغة النص الأصلي: الإنجليزية
SAE 最优性结构理论 - 解释 Sparse Autoencoders 如何从最优性条件提取可解释特征。涵盖层次分裂与吸收、残差结构、密集对立特征等现象的理论基础。
لغة النص الأصلي: الصينية
Theory explaining how optimality conditions structure SAE (Sparse Autoencoder) dictionaries - hierarchical splitting, absorption, residuals, and dense antipodal features
لغة النص الأصلي: الإنجليزية
Self-evolution skill that uses dual-agent challenge design and execution to expand capabilities over time.
لغة النص الأصلي: الإنجليزية
自我验证技能，基于 ReVeal 论文实现多轮生成-验证迭代，支持代码和推理任务的可靠自我验证。触发词：自我验证、self-verification、verify、验证代码、验证推理。
لغة النص الأصلي: الصينية
GPU-accelerated semidefinite programming for causal game analysis — using SDP hierarchies to compute bounds in causal inference games, with GPU acceleration for scalability. From arXiv:2606.20519.
لغة النص الأصلي: الإنجليزية
Efficient semi-structured LLM sparsification via annealing of Hessian-mask guided pruning. Achieves high sparsity with minimal accuracy loss using second-order importance estimation.
لغة النص الأصلي: الإنجليزية
Analysis of Neural Tangent Kernel (NTK) collapse near dynamical bifurcations in state-space models. Studies how the NTK spectrum degrades as recurrent networks approach critical transitions. Activation: NTK collapse, bifurcation analysis, state-space NTK,…
لغة النص الأصلي: الإنجليزية
SuCo - Sufficiency-guided Continuous Adaptive Reasoning for LRM efficiency. Minimal Sufficient CoT (MSC) defines shortest prefix adequate for correct answer. Two-stage training: MSC-Aligned Fine-Tuning + Sufficiency-Aware Policy Optimization. Use when: (1)…
لغة النص الأصلي: الإنجليزية
Super Factory multi-agent pipeline system — E2E testing, real execution, and contract debugging.
لغة النص الأصلي: الإنجليزية
Methodology from Anthropic research for improving alignment training to reduce agentic misalignment through principle-based training, "difficult advice" datasets, and counterfactual data augmentation.
لغة النص الأصلي: الإنجليزية
Universal complementarity identity for quantum interferometry — exact trade-off relation between path distinguishability and interference visibility for polarized double-slit experiments, with extensions to quantum information protocols. Activation:…
لغة النص الأصلي: الإنجليزية
Vibe Calibration methodology for autonomous quantum processor bring-up using LLM skill orchestration. Distills expert tacit knowledge into reusable calibration skills for superconducting quantum processors. Use when designing autonomous calibration systems…
لغة النص الأصلي: الإنجليزية
Quantum-inspired GAN methodology for high-resolution medical image generation with prototype-guided skip connections and dual-stream generator. Addresses data scarcity, class imbalance, and privacy constraints in medical imaging through variational quantum…
لغة النص الأصلي: الإنجليزية
End-to-End Encrypted Control Pipeline for Multi-Agent Coordination via CKKS Homomorphic Encryption. Enables privacy-preserving cloud-based coordination by redesigning control loops for FHE constraints. Activation: encrypted control, homomorphic encryption,…
لغة النص الأصلي: الإنجليزية
Metabolic Multi-Agent Optimizer (MMAO) - bio-inspired optimization with endogenous resource allocation. Each agent carries internal energy with private-public metabolic loop. Fitness improvements converted to metabolic gains regulating sensing, search…
لغة النص الأصلي: الإنجليزية
Methodology from Anthropic research (Jun 2026) on making biological data infrastructure agent-friendly. Case study shows that adding deterministic retrieval layers (like gget virus) to scientific research agents improves accuracy from inconsistent results to…
لغة النص الأصلي: الإنجليزية
Runtime governance framework for heterogeneous agent systems using action certificates. Model-agnostic governance centered on action proofs rather than vendor-native session records. From Anthropic research (arXiv:2606.04104).
لغة النص الأصلي: الإنجليزية
Compiler-driven sub-microsecond feedback control stack for trapped-ion quantum experiments. Use when designing quantum control software stacks, compiler pipelines for hardware control, deterministic low-latency feedback systems, DSL transpilation, or…
لغة النص الأصلي: الإنجليزية
Execution-time AI alignment architecture using an unfireable safety kernel that operates outside the agent's address space. Ensures safety controls cannot be bypassed by the AI agent itself, addressing the fundamental vulnerability of in-process guardrails.
لغة النص الأصلي: الإنجليزية
Boltzmann Attention methodology — energy-based generalization of attention using interacting Ising models with learnable pairwise couplings. Opens path to quantum annealing-based training.
لغة النص الأصلي: الإنجليزية
Brain-Prompt Injection security audit framework for BCI-LLM agents with route-safety audit contract, C3 decomposition, and split-conformal calibration
لغة النص الأصلي: الإنجليزية
Comprehensive open-source toolkit unifying continuous attractor neural network (CANN) research workflow. Three co-designed components (Python/Rust/GUI) for 1D/2D attractor modeling, spike-frequency adaptation, grid cells, path integration, and persistent…
لغة النص الأصلي: الإنجليزية
CANNs toolkit for continuous attractor neural network research - unified Python/Rust/PySide6 framework for modeling spatial navigation, grid cells, head-direction cells, and attractor dynamics analysis. Activation: CANNs toolkit, continuous attractor neural…
لغة النص الأصلي: الإنجليزية
CARVE (Content-Aware Recurrent with Value Efficiency) methodology — content-aware gating for recurrent models that resolves memory-blind gating, value-axis waste, and enables WY-form chunk-parallel training.
لغة النص الأصلي: الإنجليزية
Computational modeling methodology for chronic stress effects on prefrontal working memory networks via excitatory-inhibitory (E/I) balance perturbation. Use when modeling stress-induced cognitive dysfunction, E/I ratio alterations, or prefrontal cortex…
لغة النص الأصلي: الإنجليزية
Computational modeling methodology for chronic stress as E/I perturbation in recurrent working-memory networks. Identifies enhanced inhibitory-to-excitatory synaptic strength as best-fit mechanism and reveals resilience-generalization trade-off.
لغة النص الأصلي: الإنجليزية
Framework for functional dissociation between cortical and subcortical systems during learning under memory constraints - cortex supports general structure learning while subcortex specializes in reward-based learning
لغة النص الأصلي: الإنجليزية