Menu
Skills neste repositório
O SkillsMP coletou 4.114 skills de hiyenwong/ai_collection. Abra uma skill para revisar a origem e os detalhes.
hiyenwong/ai_collectionMostrando 40 de 4.114 skills coletadas.
Symmetry-Protected Lyapunov Neutral Modes in Equivariant Recurrent Networks. Theoretical framework for when continuous attractors (zero Lyapunov exponents) are guaranteed by symmetry rather than tuning. Activation: equivariant rnn, symmetry-protected modes,…
Idioma do texto original: inglês
DeepStack methodology for design space exploration (DSE) in system-hardware co-design. Scalable and accurate performance modeling for distributed 3D-stacked AI systems. Use when performing early-stage system design optimization, hardware-software co-design,…
Idioma do texto original: inglês
Automated threat modeling and security verification for cyber-physical systems (CPS) and AI-enabled systems. Use when: (1) Designing security architecture for CPS/IoT systems, (2) Performing automated threat modeling from system architecture models (SysML,…
Idioma do texto original: inglês
Tensor Network Feature Engineering methodology for multi-class neurological disorder prediction from MRI data. Uses tensor network decompositions to extract high-dimensional features from sparse medical imaging. Activation: tensor network MRI, neurological…
Idioma do texto original: inglês
Framework for implementing Test-Time Training (TTT) - updating model weights during inference to adapt to continuous information streams. Use when designing adaptive AI systems, online learning for LLMs, breaking static train-deploy paradigm, or handling…
Idioma do texto original: inglês
Perceptual misalignment of texture representations in convolutional neural networks — finds no connection between CNN Brain-Score and alignment with human texture perception, suggesting texture perception involves mechanisms distinct from object recognition…
Idioma do texto original: inglês
Thermodynamic Networks methodology for autonomous physics-based computation using non-equilibrium steady states. Identifies Negative Differential Conductance (NDC) as the critical property for computational expressivity. Applies to quantum dot networks,…
Idioma do texto original: inglês
"Training-free looped transformers — inference-time technique that loops a contiguous mid-stack block of layers in a frozen pretrained LLM to improve reasoning without fine-tuning. Use when: (1) improving a frozen LLM's reasoning at inference time, (2)…
Idioma do texto original: inglês
Multi-Modal Graph Neural Network with Transformer-Guided Adaptive Diffusion for Preclinical Alzheimer Classification. Combines diffusion kernel (short-range) + multi-head attention (long-range) for brain network analysis. Activation: Alzheimer, preclinical…
Idioma do texto original: inglês
Use prototype-based readout layers for transformer encoders to replace pooling methods (mean pooling, class token). Avoid information collapse with learned compression mechanism. Activation: prototype readout, transformer output layer, collapse-free…
Idioma do texto original: inglês
Multi-Stage Warm-Start Deep Learning Framework for Unit Commitment. Transformer-based architecture for predicting generator commitment schedules with deterministic post-processing for physical feasibility, warm-start strategy for MILP solver, and…
Idioma do texto original: inglês
End-to-end pipeline for large-scale portfolio selection with cardinality constraints using trapped-ion quantum computers. Use when: executing portfolio optimization on trapped-ion QPU hardware; solving QUBO subproblems via BF-DCQO; decomposing large…
Idioma do texto original: inglês
TRIBE v2 tri-modal foundation model methodology for in-silico neuroscience. Uses video/audio/language embeddings to predict whole-brain fMRI across 720 subjects.
Idioma do texto original: inglês
TRIBE v2 tri-modal foundation model methodology for in-silico neuroscience. Uses video, audio, and language modalities to predict human brain activity across naturalistic and experimental conditions. Supersedes linear encoding models with several-fold…
Idioma do texto original: inglês
Triple-Loop Consolidation methodology for persistent memory in non-gradient dissipative cognitive architectures. Deep Memory (DM) operates through recording-seeding-reentry cycle. Discrete MoE routing is causally prerequisite. Activation: triple-loop…
Idioma do texto original: inglês
Five-principle framework for building and governing trustworthy AI agents. Covers human control, value alignment, secure interactions, transparency, and privacy in agent architecture design.
Idioma do texto original: inglês
Optimize tool/schema definitions for LLM agent deployments using TSCG principles. Converts JSON tool schemas into token-efficient structured text formats that small models (4B-14B parameters) can reliably interpret. Use when: (1) agent tool-use accuracy drops…
Idioma do texto original: inglês
Turn-level Truncated On-Policy Distillation (TT-OPD) methodology for training multi-turn medical AI agents via reinforcement learning. Addresses multi-turn collapse, response length explosion, and tool-use erosion in clinical dialogue. Use when training…
Idioma do texto original: inglês
Expert guidance for globally shared expert pool Mixture-of-Experts architecture. Based on UniPool paper (arXiv:2605.06665). Use when designing MoE architectures, expert pooling, pool-level balancing, NormRouter, sublinear expert parameter scaling, or…
Idioma do texto original: inglês
Systematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs in V1 visual cortex alignment. Large-scale fMRI analysis reveals that random feature detectors can capture V1 representational structure. Keywords: untrained CNN, V1 cortex,…
Idioma do texto original: inglês
系统RSA比较研究：展示未训练CNN在V1视觉皮层区域与反向传播训练的CNN具有相似表征。通过大规模fMRI和表征相似性分析，挑战传统深度学习需要大量训练的观点。适用于视觉皮层建模、CNN可解释性、神经科学。
Idioma do texto original: chinês
Systematic RSA comparison showing untrained CNNs match backpropagation-trained networks at V1 visual cortex, revealing architecture's dominant role over learning rules in neural alignment. Activation triggers: untrained cnn, backpropagation, v1, rsa,…
Idioma do texto original: inglês
Systematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs at V1 visual cortex. Trigger words: untrained CNN, backpropagation, RSA, V1, representational similarity
Idioma do texto original: inglês
Systematic RSA comparison showing untrained CNNs match backpropagation at V1 alignment with human fMRI. Evaluates BP, FA, PC, and STDP learning rules against THINGS-fMRI dataset using 720 stimuli across 3 subjects. Use when studying brain-model alignment,…
Idioma do texto original: inglês
Systematic RSA comparison showing untrained CNNs match backpropagation-trained CNNs at V1 visual cortex. Untrained random-weights CNN (rho=0.076) exceeds backprop (rho=0.034) at V1/V2 (p<0.001). STDP achieves highest V1 alignment among trained rules…
Idioma do texto original: inglês
Validation-driven LLM workflow pattern - using verification loops to ensure LLM-generated outputs are correct. Extracted from 'Generating Statistical Charts with Validation-Driven LLM Workflows' (arXiv 2026-05-01). Applicable to code generation, data…
Idioma do texto original: inglês
Vector Policy Optimization (VPO) methodology for training LLMs to maintain response diversity during inference-time search. Use when: (1) Training models for test-time compute scaling, (2) Improving AlphaEvolve/AlphaCode-style search procedures, (3)…
Idioma do texto original: inglês
VENCircuit methodology — Von Economo neurons as residual gradient scaffolds in recurrent spiking neural networks for reliable social skill acquisition. Use when researching: Von Economo neurons (VENs), spiking neural networks for social cognition, gradient…
Idioma do texto original: inglês
Voice AI interaction patterns for building realtime voice agents with reasoning, tool use, and multilingual support. Based on OpenAI's GPT-Realtime model release patterns.
Idioma do texto original: inglês
Wavelet-Enhanced Mixture-of-Experts (WaveMoE) foundation model for time series forecasting. Use when building time series prediction models, incorporating frequency-domain information, or designing MoE architectures for temporal data.
Idioma do texto original: inglês
X-Token methodology from arXiv:2605.21699 (May 2026). Projection-guided cross-tokenizer knowledge distillation: P-KL (sparse projection matrix) and H-KL (hybrid relaxed matching) for teaching LLMs with incompatible vocabularies. Use when: cross-tokenizer…
Idioma do texto original: inglês
Privacy-enhanced zero-order federated learning using multi-key homomorphic encryption (xMK-CKKS) over wireless channels. Methodology for secure FL aggregation without channel estimation, supporting N-1 client compromise tolerance. Use when designing…
Idioma do texto original: inglês
Coarse feedback for human-aligned visual representations. Demonstrates that extremely coarse classification signals (e.g., 8 classes) produce representations that match or exceed brain alignment of fine-grained (1000-class) or self-supervised models. Use…
Idioma do texto original: inglês
Implement early stopping strategies for reasoning models based on confidence dynamics. Detects when reasoning trajectories reach high confidence early vs. unproductive long reasoning traces. Use for: (1) optimizing LLM reasoning tasks, (2) reducing…
Idioma do texto original: inglês
FADE: Forgetting through Adaptive Decay for continual learning. Adapts per-parameter weight decay rates online via meta-gradient descent. Balances acquiring new knowledge with retaining old. Activation: FADE, adaptive weight decay, continual learning…
Idioma do texto original: inglês
Fast efficient coding and sensory adaptation in gain-adaptive recurrent networks — unified mechanistic model reconciling adapter-repulsion and prior-attraction phenomena via gain modulation.
Idioma do texto original: inglês
The illusory simplicity of the feedforward pass — evidence for dynamical nature of stimulus encoding in neural networks. Demonstrates that feedforward computation involves complex temporal dynamics rather than static transformations. Applicable to neural…
Idioma do texto original: inglês
Dynamical systems methodology for flexible phase-locking in cortical oscillators. Multi-timescale inhibitory currents enable entrainment to rhythms slower than intrinsic frequency via delayed Hopf bifurcation. Activation: phase-locking, cortical oscillators,…
Idioma do texto original: inglês
Geometric State-Space Neural Network for brain dynamics modeling. Combines state-space models with geometric constraints on brain connectivity to capture latent neural state evolution. Applicable to fMRI/EEG dynamics modeling, functional neuroimaging…
Idioma do texto original: inglês
Robust volatility updates for Hierarchical Gaussian Filtering (HGF). Improves stability and convergence of uncertainty estimation in perceptual inference. Activation: hierarchical gaussian filter, volatility update, perceptual inference, active inference,…
Idioma do texto original: inglês