Menu
Skills in this repository
SkillsMP has collected 4,114 skills from hiyenwong/ai_collection. Open a skill to review its source and details.
hiyenwong/ai_collectionShowing 40 of 4,114 collected skills.
Hyperbolic Learning on Brain Graphs (HLBG) framework for brain disorder diagnosis. Uses Lorentzian hyperbolic space to model hierarchical relationships among ROIs, functional communities, and whole-brain network. Introduces Graph-aware Mamba (GaMamba) for…
Instruct-Particulate methodology for feed-forward 3D object articulation reconstruction using kinematic control. Enables scalable recovery of articulated 3D structures from single images or multi-view inputs. Use when: 3D articulation recovery, feed-forward…
Discover interdisciplinary research connections using knowledge graph analysis (PageRank, Louvain, vector similarity). Use when analyzing cross-domain research, finding unexpected connections, or exploring interdisciplinary patterns. Keywords: 跨学科发现,…
Methodology for aligning quantum operators (unitary matrices) with LLM latent spaces using trainable embeddings. Enables LLMs to understand and reason about quantum representations for Clifford+T circuit synthesis. arXiv: 2606.13811
Multi-agent AI governance system with provable post-quantum security (MAGIQ framework). Defines and enforces communication/access-control policies for agent-to-agent sessions using quantum-resistant cryptography with UC security proofs. Use when: post-quantum…
Multilevel Covariate-Assisted Principal Regression (MCAP) for brain functional connectivity analysis. Handles hierarchically nested neuroimaging data, identifies cluster-specific projections, and models covariance matrix outcomes with subject-level…
Monte Carlo Tree Search (MCTS) methodology for discovering optimal data encoding circuits in quantum-classical neural networks. Addresses the open question of why certain quantum data encodings outperform others by treating encoding circuit design as a…
Membrane Potential Alignment (MPA) - Test-time adaptation method for spiking neural networks in intracortical brain-computer interfaces. Realigns pretrained decoders to shifted neural recordings by matching membrane potential distributions via KL divergence -…
MerLin discovery engine for photonic and hybrid quantum machine learning. Embeds linear optical circuit simulation into PyTorch/scikit-learn for end-to-end differentiable training of quantum layers. Use when: (1) building hybrid quantum-classical ML models,…
ML-hybrid distributed caching methodology combining traditional caching algorithms (LRU, LFU, ARC, TLRU) with lightweight machine learning for predictive eviction and adaptive sizing. Use when: (1) designing cache systems for dynamic environments, (2)…
Maximum Likelihood Decoding methodology for CSS quantum error correction codes — reformulates MLD as partition function computation in classical spin models, enabling exact MLD via tensor network contraction and approximate MLD via belief propagation.…
Model Predictive Control (MPC) stability and suboptimality analysis under plant-model mismatch. Covers discounted and undiscounted infinite-horizon optimal control, stability guarantees with model uncertainty, and suboptimality bounds. Use when analyzing MPC…
Methodology from Anthropic research for converting LLM activations into human-readable natural language text using a reconstruction-based training loop with Activation Verbalizer and Activation Reconstructor.
Neural Cellular Automata (NCA) attractor analysis methodology. Studies stability, geometry, and dynamics of learned attractors in self-organizing neural systems using dynamical systems theory. Methods for analyzing ordered vs chaotic behavior, long-horizon…
Theory of learning high-dimensional controlled non-linear dynamical systems via neural ODEs trained with online stochastic gradient descent, solved using dynamical mean field theory. Activation: neural ode, mean field theory, dynamical systems, training…
Dissociating spatial frequency reliance from adversarial robustness in neurally aligned DCNNs. Shows that adversarial robustness from neural alignment is NOT primarily driven by spatial frequency bias (LSF or human channel), but by deeper representational…
Neuroscience-inspired memory architecture design for AI agents. Maps biological memory systems (working, short-term, episodic, semantic, procedural, core, cross-context) to AI agent memory layers. Integrates neuroscience models including Hebbian learning,…
Neuromorphic visual attention framework for sign language recognition on SpiNNaker hardware. Combines event-based vision sensors with spiking neural networks for energy-efficient real-time ASL recognition. Use when: deploying low-power gesture/sign…
Contravariance Theory methodology — formal proof that minimal DNN solutions to hard tasks exhibit strong alignment of privileged axes, with alignment "zipping" up the network hierarchy. Bridges NeuroAI convergent evolution theory and brain-DNN comparison…
Brain-Inspired Unsupervised Self-Reflection (BUS) framework for enhancing VLM reasoning without labeled data. Uses neuroscience-backed backward prediction to enable self-verification on unlabeled data.
Graph-regularized learning framework for EEG-based emotion recognition using psychological emotion topology. Conceptualizes emotions as nodes in a graph with edges encoding proximity based on dimensional emotion theories. Use when building EEG emotion…
Sample-Adaptive Hyperbolic Graph Neural Network (SA-HGNN) for EEG-based depression recognition. Combines sample-adaptive graph construction with hyperbolic graph convolution and attention pooling to capture hierarchical brain network structure in EEG signals.
STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Predictive Architecture for EEG self-supervised learning. Largest EEG foundation model (47,703 sessions, ages 5-81) using JEPA-style latent prediction with EMA tokenizer + auxiliary signal…
Validation methodology for deep multimodal brain-encoding models (TRIBE, the 2025 Algonauts challenge winner) against behavioral engagement metrics. Tests whether predicted fMRI signals forecast aggregate population behavior (YouTube replay heatmaps,…
Learning biophysical Hodgkin-Huxley models from extracellular MEA measurements using differentiable simulation and simulation-based inference. Enables precise neurostimulation prediction from minutes of recording instead of hours of stimulus testing.
Causal mechanism framework for anhedonia and reward valuation deficits in Vision-Language Models — mechanistic analysis linking VLM reward processing to Nucleus Accumbens dysfunction patterns from clinical depression research.
Neuromorphic silicon neuron controller (SiLIF-DBS) for adaptive deep brain stimulation in Parkinson's Disease — CMOS-implemented closed-loop aDBS achieving 75% power reduction with beta-band biomarker tracking.
Model-free temporal-switch (TS) framework for transferable lightweight neuromorphic computing. Enables direct transfer of trained models to unseen hardware devices without post-training calibration by incorporating a broader spectrum of devices during…
Haken Lighthouse model with adaptive conduction delays and phase locking theory. Provides analytically tractable framework for phase-locked states in delayed spiking networks, spike-time perturbation stability analysis, and activity-dependent white matter…
Non-Hermitian Potential Well Formalism for modeling the Global Neuronal Workspace (GNW) consciousness framework. Uses nonlinear Schrödinger-type equation in imaginary time with non-Hermitian, non-normal Hamiltonian and Lotka-Volterra-type term to reproduce…
Interpretable machine learning methodology for predicting Parkinson's disease motor severity (MDS-UPDRS Part III) from neuroimaging features — Quantitative Susceptibility Mapping (QSM) MRI and multiband multiecho resting-state fMRI Regional Homogeneity…
Comprehensive 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…
Treats LLM-as-judge evaluator-replacement ambiguity as a measurement-validity problem. Judge upgrades are not interchangeable. Stronger judges reduce but don't remove position/verbosity bias. Proposes audit trails including dataset slices, bias probes, and…
Formalizes the Context Access Divide (CAD) as a dimension of agentic inequality operating at the interaction level. Dynamic Context Retrieval vs Manual Attachment causes combinatorial collapse in task-success probability. Proposes contextuality as complement…
Capability-driven benchmark for evaluating proactive agents in dynamic real-world settings. UniClawBench evaluates five foundational capabilities (Skill Usage, Exploration, Long-Context Reasoning, Multimodal Understanding, Cross-Platform Coordination) across…
Latent Memory Palace (LMP): reasoning for control policies as autoregressive variational inference. Organizes information in latent memory palace with iterative adaptive retrieval. LMP-π achieves strong performance with interpretable adaptive test-time…
HCC-STAR: clinically aligned LLM for hepatocellular carcinoma staging, treatment, and prognosis. Reads EMR narratives, outputs risk stratification, guideline-consistent treatments with rationales, and survival estimates. Outperforms GPT-5 and Gemini-2.5 Pro.…
Multi-agent marketplace simulation studying formal mechanisms for market stability with self-interested LLM agents. 18 DeepSeek-V3 agents with complementary specialties trade in constrained network. Mediation identified as top mechanism, robust under…
Memory-augmented agentic framework that exposes a frozen VLA as a retryable contact-rich primitive composed with analytic primitives. Learns operating range from execution traces and failure models. +38.6pp on LIBERO-Pro, +25.4pp on RoboCasa365. Activation:…
Hierarchical machine teaching algorithm for robust reward learning across multiple MDPs. Demonstrates comparisons impose stronger constraints than demonstrations in unlimited-data regime. Greedily selects informative environments then queries low-cost…