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.
Arrovian impossibility theorem for Automated Market Maker (AMM) design. Proves no aggregation rule for weighted-product AMMs can be simultaneously fair and strategy-proof when n>2 liquidity providers. Key result: fairness forces mean-type aggregation…
Architecture-aware quantum state preparation using Bucket Brigade QRAM (BBQRAM) with segment tree for polylogarithmic query time. Covers complex-valued matrix encoding, classical precomputation of rotation angles, and magnitude-then-phase procedures. Enables…
Distributional Portfolio Optimization (DPO) unified framework — organizing Bayesian, robust, chance-constrained, stochastic-allocation, and distributional RL portfolio methods through joint coupling Gamma_theta(dw,dr). Includes Wasserstein-CVaR duality,…
Critical analysis methodology for quantum data encoding — identifies how naive amplitude encoding (psi=sqrt(P)) abelianizes the Hilbert space and fails to achieve genuine quantum advantage in QML/finance. Advocates for Dynamical Hamiltonian Encoding (DHE)…
Portfolio Optimization with Mean-Variance-Spectrum Preferences
Portfolio Selection is More of a Belle Art Than Economics or Finance
Regime-aware Continual Adaptive Portfolio management (ReCAP) — integrating continual learning into portfolio management via adaptive regime detection, policy libraries, and regime-gated policy combination. Accepted by KDD 2026. Activation: regime detection,…
ESG and joint fragility analysis in equity markets using stress-amplified resilience framework. Analyzes clustered fragility across downside returns, volatility spikes, and deteriorating tradability. Use when: ESG investing, stress testing, portfolio…
Code2LoRA: Hypernetwork-generated LoRA adapters for code language models under software evolution. Supports static and dynamic adaptation scenarios with zero inference overhead. Activation: code LLM adaptation, repository-specific LoRA, hypernetwork adapters,…
Compositional boundaries for density fusion methodology from arXiv:2606.05871 — algebraic compositionality analysis for hierarchical probabilistic model fusion. Characterizes normalized weighted linear pooling as the unique order-invariant fusion rule and…
Distributional matrix completion methodology using kernel mean embeddings and Tucker rank for probability-distribution-valued matrices. Represents each matrix entry as a probability distribution via RKHS embeddings, introduces functional unfolding operators…
Double Preconditioning (DoPr) optimization paradigm combining gradient-wise preconditioning (Adam/Muon) with activation-wise preconditioning (KFAC) to improve test-time performance in settings with train-test feedback mismatch. Addresses error accumulation in…
Single-letter efficiently computable strong converse bound on classical identification capacity of quantum channels via Gaussian mean width analysis
Latent reasoning framework using normalizing flows for continuous thoughts that preserves CoT advantages (left-to-right generation, KV-cache, likelihood estimation)
Parameter-efficient continual learning using spectral decomposition with soft penalty protecting principal components while adapting long-tail spectral coordinates
Wasserstein Exponential Smoothing methodology from arXiv:2606.05560 — extends classical exponential smoothing to distributional time series in Wasserstein space. Provides consistent parameter estimation via Wasserstein distance minimization, applicable to…
Amortized Nonlinear Model Predictive Control using state-dependent quadratic programs (QPs) with single-network residual-corrector architecture. Replaces expensive real-time NLP solving with differentiable interior-point QP layer, enabling deployment on…
Deep Reinforcement Learning for dynamic multi-pair trading in cryptocurrency markets. Filter-then-Rank pair selection with PPO+LSTM execution agent within deterministic risk shielding. Evaluated on Binance USD-M Futures with bootstrap robustness validation.…
Partition-logic framework for modeling complementarity in social measurement. Applies non-Boolean event structures (partition logics) to social-science settings where mutually incompatible observation modes reveal different aspects of a definite latent state.…
Repeated Policy Regret (RP-Regret) methodology for regret minimization in repeated games with adaptive opponents — addresses limitations of external regret when opponents respond to history of play.
CHASMBrain - Hierarchical Mamba architecture for image-to-fMRI brain reconstruction with coarse-to-fine strategy. Use when building brain encoding models, visual cortex modeling, or implementing Mamba-based neural decoding systems. Separates global semantic…
Source text: Chinese
Game-theoretic energetic framework for asymmetric excitatory-inhibitory neural circuits. Extends energy-based models to E-I networks, revealing competitive dynamics where each neuron minimizes its own energy. Applies network stability principles to…
Dynamical Alignment principle resolves SNN performance paradox. Fixed neural structure can operate in different computational modes driven by input temporal dynamics. Bimodal landscape: dissipative (energy-efficient sparse coding) vs expansive (high…
EEG基础模型的诊断审计方法论 - 揭示EEG基础模型在高准确率背后可能隐藏的主体身份特征陷阱，提出系统性评估框架区分真实临床生物标志物与主体识别特征。
Source text: Chinese
Updating the standard neuron model in artificial neural networks — replacing point neuron model with realistic cortical cell model improves expressivity, robustness, and learning efficiency
Vision Hopfield Memory Network (V-HMN) - brain-inspired backbone with hierarchical Hopfield memory + predictive-coding refinement. Local patch memory + global episodic memory + error correction. Enhanced interpretability, data efficiency, biological…
组合性计算的理论框架 - 在抑制主导的阈值线性网络中使用低秩连接规则实现固定点的组合性，揭示大脑如何高效分解复杂任务为可复用的基本单元。
Source text: Chinese
内在计算功能主义方法论 — 从观察者相对映射到观察者独立结构。解决计算理论意识中的观察者相对性问题，提供可操作化的标准框架。
Source text: Chinese
Renormalization Group (RG) interpretability framework for deep neural networks. Establishes correspondence between RG in statistical physics and DNN training, proving DNN feature extraction is equivalent to RG flow on exponential family distributions. Based…
Automated proving methodology for Shannon-type entropy inequalities using fine-tuned language models and guided tree search. Bridges information theory with AI for automated mathematical theorem discovery. Applicable to entropy inequality verification,…
Fermionic non-Gaussianity analysis via Bell sampling — bridge degree monotone, Gaussian conversion no-go theorems, and efficient quantum algorithms for certifying non-Gaussian cost of state preparation.
Monotones and efficient quantum algorithms for fermionic non-Gaussianity via Bell sampling. Quantifies non-Gaussianity resources for fermionic quantum computation platforms. Activation: fermionic quantum computing, Bell sampling, non-Gaussianity monotones,…
Floquet-engineered phonon lasing methodology for quantum control systems. Design squeezed phonon lasers via Floquet control of solid-state defects with coupled mechanical oscillators and spin systems. From arXiv:2606.05083 (Molinares, Rastelli, Montenegro,…
Enhancement of charge correlations and topological markers in interacting non-Hermitian Su-Schrieffer-Heeger models.
Room-temperature synchronized dipole state methodology in plasmonic nanogap 2D arrays under continuous-wave pumping.
Explicit convergence rates for Sum-of-Hermitian-Squares hierarchies over the Pauli algebra, enabling accuracy guarantees for noncommutative polynomial optimization in quantum theory.
CR-HO-QAOA framework for certified higher-order quantum collateral allocation with CSA-aware constraints and feasible-subspace mixers. Uses higher-order binary models for margin requirements, concentration limits, and substitution structure, with CP-SAT…
Decoded Quantum Interferometry (DQI) extended beyond Hamming space to translation association schemes for structured optimization on finite geometries.
Quantum networking using diamond color defects (NV/SiV centers) for scalable quantum communication, distributed quantum computing, and sensing. Comprehensive methodology covering optical properties, spin-qubit control, spin-photon interfaces, nanophotonic…
Differentially private estimation of smooth optimal transport maps using wavelet density estimators and stability bounds. Privacy-preserving statistical methodology for OT map estimation. Activation: differential privacy, optimal transport, private…