Menú
Skills en este repositorio
SkillsMP ha recopilado 4114 skills de hiyenwong/ai_collection. Abre una skill para revisar su origen y sus detalles.
hiyenwong/ai_collectionMostrando 40 de 4114 skills recopiladas.
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…
Idioma del texto original: inglés
"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…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
On-Policy Distillation (OPD) methodology for transforming autoregressive models into diffusion language models efficiently, eliminating train-inference mismatch.
Idioma del texto original: inglés
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,…
Idioma del texto original: inglés
Polynomial acyclicity constraints for efficient continuous causal discovery in visual semantic graphs - 33% speedup over exponential baseline with improved F1 scores.
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
Train hundred-billion-parameter sparse MoE models on single nodes using reversible recurrence stacks and state-preserving growth principles with TQP optimizer strategy.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Contrastive on-policy self-distillation methodology for reasoning models that mitigates privilege-induced style drift
Idioma del texto original: inglés
Rollout-Adaptive Supervised Fine-Tuning (RASFT) for reasoning tasks - policy-aware SFT that calibrates expert supervision based on problem-level solvability from verified rollouts.
Idioma del texto original: inglés
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。
Idioma del texto original: chino
Theory explaining how optimality conditions structure SAE (Sparse Autoencoder) dictionaries - hierarchical splitting, absorption, residuals, and dense antipodal features
Idioma del texto original: inglés
Self-evolution skill that uses dual-agent challenge design and execution to expand capabilities over time.
Idioma del texto original: inglés
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。
Idioma del texto original: chino
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.
Idioma del texto original: inglés
Efficient semi-structured LLM sparsification via annealing of Hessian-mask guided pruning. Achieves high sparsity with minimal accuracy loss using second-order importance estimation.
Idioma del texto original: inglés
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,…
Idioma del texto original: inglés
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)…
Idioma del texto original: inglés
Super Factory multi-agent pipeline system — E2E testing, real execution, and contract debugging.
Idioma del texto original: inglés
Methodology from Anthropic research for improving alignment training to reduce agentic misalignment through principle-based training, "difficult advice" datasets, and counterfactual data augmentation.
Idioma del texto original: inglés
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:…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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,…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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).
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Boltzmann Attention methodology — energy-based generalization of attention using interacting Ising models with learnable pairwise couplings. Opens path to quantum annealing-based training.
Idioma del texto original: inglés
Brain-Prompt Injection security audit framework for BCI-LLM agents with route-safety audit contract, C3 decomposition, and split-conformal calibration
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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
Idioma del texto original: inglés