All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Dynamical Hamiltonian EncodingDynamical Hamiltonian Encoding (DHE) methodology for quantum machine learning and quantum finance data encoding. Addresses the Inverse Born Rule Fallacy — the limitation of standard amplitude encoding (psi = sqrt(P)) that renders quantum states 'phase-deaf' by restricting to the positive real orthant. DHE uses data to generate non-commutative Hamiltonian evolution (based on QIFT) rather than static phase-locked vectors. Use when: designing quantum data encoding for ML/finance, implementing am...Votes: 0GitHub stars: 3
- E3nn Euclidean Neural Networks**arXiv ID:** 2207.09453 **Authors:** Mario Geiger, Tess Smidt **Published:** 2022-07-18T21:19:40Z **Abstract:** We present e3nn, a generalized framework for creating E(3) equivariant trainable functions, also known as Euclidean neural networks. e3nn naturally operates on geometry and geometric tensors that describe systems in 3D and transform predictably under a change of coordinate system. The core of e3nn are equivariant operations such as the TensorProduct class or the spherical harmonics...Votes: 0GitHub stars: 3
- Entropy Maximization ManifoldMaximum entropy path ensemble embedding for manifold learning and dimensionality reductionVotes: 0GitHub stars: 3
- Equilibrium Propagation For Nonconservative Systems**arXiv ID:** 2602.03670 **Authors:** Antonino Emanuele Scurria, Dimitri Vanden Abeele, Bortolo Matteo Mognetti, Serge Massar **Published:** 2026-02-03T15:52:23Z **Abstract:** Equilibrium Propagation (EP) is a physics-inspired learning algorithm that uses stationary states of a dynamical system both for inference and learning. In its original formulation it is limited to conservative systems, $\textit{i.e.}$ to dynamics which derive from an energy function. Given their applications, it is imp...Votes: 0GitHub stars: 3
- Exclusion Statistics Thermodynamic ResourceHaldane fractional exclusion statistics as tunable thermodynamic resource for quantum heat engines — bosonic working mediums exceed fermionic Whitney power limit by 1.52×.Votes: 0GitHub stars: 3
- Exploratory Experience Shapes The Geometry Of PredDerived from arXiv:2605.27929 - Exploratory Experience Shapes the Geometry of Predictive RepresentationsVotes: 0GitHub stars: 3
- Exploring Structures In Physics Problems Can Ai AgExploring Structures in Physics Problems: Can AI Agents Discover Statistical Mechanical Mappings?Votes: 0GitHub stars: 3
- Faster Physics In PythonSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Fermionic Bell Sampling Non GaussianityFermionic 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.Votes: 0GitHub stars: 3
- Fermionic Non Gaussianity Bell SamplingMonotones 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, covariance operator, fermionic algorithms.Votes: 0GitHub stars: 3
- Floquet Controlled Phonon LasingFloquet-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, Eremeev, 2026).Votes: 0GitHub stars: 3
- Formal Derivation Of Mesh Neural Networks With Their Forwardonly Gradient Propagation**arXiv ID:** 1905.06684 **Authors:** Federico A. Galatolo, Mario G. C. A. Cimino, Gigliola Vaglini **Published:** 2019-05-16T12:22:26Z **Abstract:** This paper proposes the Mesh Neural Network (MNN), a novel architecture which allows neurons to be connected in any topology, to efficiently route information. In MNNs, information is propagated between neurons throughout a state transition function. State and error gradients are then directly computed from state updates without backward computa...Votes: 0GitHub stars: 3
- From Read Out Geometry To In Silico StimulationDistributed functional-connectivity signature of Alzheimer's disease methodology using subject-specific reservoir-computing models to reconstruct individual lagged functional connectivity and develop personalized neuromodulation strategies. Shows that optimal stimulation targets are distributed patterns rather than focal sites, requiring model-informed targeting based on therapeutic responsiveness rather than read-out deviation magnitude.Votes: 0GitHub stars: 3
- Gamma C Peak Covariant Recoveryγ_c-Peak covariant quantum error recovery methodology across organic qubit platforms — cryptochrome, MAO-A, Posner molecules, and radical-pair systems. Applicable to quantum brain models, biological quantum coherence, and organic quantum computing platforms.Votes: 0GitHub stars: 3
- Gated Graph Sequence Neural Networks**arXiv ID:** 1511.05493 **Authors:** Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel **Published:** 2015-11-17T18:10:12Z **Abstract:** Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modify to use gated recurrent units ...Votes: 0GitHub stars: 3
- Goal Graphbased Objectivealigned Diffusion Solvers For Dynamic Multiobjective Optimization**arXiv ID:** 2605.19119 **Authors:** Xingyu Li **Published:** 2026-05-18T21:11:03Z **Abstract:** Existing neural combinatorial optimization solvers frame solution search as imitation of optimal decisions, inherently limiting their utility to single-objective minimization and static constraints. We propose GOAL, a conditioned diffusion solver over relational graph representations that enables controllable decision generations by conditioning on human-specified objectives. We introduce a heter...Votes: 0GitHub stars: 3
- Gradient Free Riemannian Langevin SamplerWe address the problem of efficiently sampling multimodal probability distributions, where standard Markov Chain Monte Carlo methods often suffer from poor mixing and mode trapping. To mitigate these. Based on arXiv:2607.07519.Votes: 0GitHub stars: 3
- Graph Based Correlation Matrix GenerationGraph-Based Correlation Matrix Generation using convex optimization for controlled sparsity and mean off-diagonal values. Use when generating realistic correlation matrices for neuroscience, finance, or other domains requiring graph-structured correlations with specific statistical properties.Votes: 0GitHub stars: 3
- Graph Structured Online Difficulty EstimationRLVR difficulty estimation via graph structure.Votes: 0GitHub stars: 3
- Graphical Coaction Frw IntegralsGraphical coaction methodology for FRW integrals using twisted (co)homology intersection theory — decomposing cosmological integrals into diagram-decorated building blocks.Votes: 0GitHub stars: 3
- Graphtime Convolutional Neural Networks**arXiv ID:** 2103.01730 **Authors:** Elvin Isufi, Gabriele Mazzola **Published:** 2021-03-02T14:03:44Z **Abstract:** Spatiotemporal data can be represented as a process over a graph, which captures their spatial relationships either explicitly or implicitly. How to leverage such a structure for learning representations is one of the key challenges when working with graphs. In this paper, we represent the spatiotemporal relationships through product graphs and develop a first principle graph-...Votes: 0GitHub stars: 3
- Green Wearable Computing PhysicsTowards Green Wearable Computing: A Physics-Aware Spiking Neural Network for Energy-Efficient IMU-ba... Activation: 物理感知, spiking, physics-aware, snnVotes: 0GitHub stars: 3
- Hamiltonian Complexity StoquasticHamiltonian complexity analysis methodology for stoquastic sparse Hamiltonians. Covers StoqMA complexity class, quantum complexity classification, and sparse Hamiltonian analysis. Activation: stoquastic Hamiltonian, Hamiltonian complexity, StoqMA, quantum complexity classVotes: 0GitHub stars: 3
- Hermitian Inner Product Time AxisMechanism for time-axis selection in quantum systems via Hermitian inner product choice — identifies the symmetry-breaking step that selects future-timelike axis and locates Born rule as projection onto that axis. Applicable to quantum foundations, Lorentz symmetry emergence from qubit structure, and Hilbert space construction.Votes: 0GitHub stars: 3
- Higher Gauge Theory CohomologyHigher Gauge Theory via Differential Nonabelian Cohomology — streamlined introduction to global completion of Maxwell-type higher gauge fields using cohesive homotopy theory and flux quantization.Votes: 0GitHub stars: 3
- Higher Order Geometric Updates For Levenberg Marquardt Method Via RiemannNonlinear least-squares optimization is central to regression, physics-informed neural networks, and other machine-learning tasks. Such problems have a natural geometric interpretation, model predicti. Based on arXiv:2607.07623.Votes: 0GitHub stars: 3
- Ifclora Topology Aware Rank AllocationIFCLoRA framework for topology-aware rank allocation in parameter-efficient fine-tuning, dynamically allocating LoRA ranks based on model architecture topology and task requirements.Votes: 0GitHub stars: 3
- Incorporating Symbolic Domain Knowledge Into Graph Neural Networks**arXiv ID:** 2010.13900 **Authors:** Tirtharaj Dash, Ashwin Srinivasan, Lovekesh Vig **Published:** 2020-10-23T16:22:21Z **Abstract:** Our interest is in scientific problems with the following characteristics: (1) Data are naturally represented as graphs; (2) The amount of data available is typically small; and (3) There is significant domain-knowledge, usually expressed in some symbolic form. These kinds of problems have been addressed effectively in the past by Inductive Logic Programming ...Votes: 0GitHub stars: 3
- Interlayer Information Similarity Assessment Of Deep Neural Networks Via Topological Similarity And Persistence Analysis Of Data Neighbour Dynamics**arXiv ID:** 2012.03793 **Authors:** Andrew Hryniowski, Alexander Wong **Published:** 2020-12-07T15:34:58Z **Abstract:** The quantitative analysis of information structure through a deep neural network (DNN) can unveil new insights into the theoretical performance of DNN architectures. Two very promising avenues of research towards quantitative information structure analysis are: 1) layer similarity (LS) strategies focused on the inter-layer feature similarity, and 2) intrinsic dimensionalit...Votes: 0GitHub stars: 3
- Irreducible Correlator Geometry**Source**: Kaito Kobayashi, "Irreducible Geometry of Higher-Order Correlator Families" (arXiv:2607.08761, July 2026)Votes: 0GitHub stars: 3
- Istar Algebraic Collapse IsingiSTAR methodology exploiting algebraic collapse in continuous Ising solvers — detects stabilized coordinates during late-stage simulated bifurcation and eliminates them via variational frozen-set identity, removing 64%+ of dense interaction work.Votes: 0GitHub stars: 3
- Learning Multimodal Graphtograph Translation For Molecular Optimization**arXiv ID:** 1812.01070 **Authors:** Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola **Published:** 2018-12-03T20:28:09Z **Abstract:** We view molecular optimization as a graph-to-graph translation problem. The goal is to learn to map from one molecular graph to another with better properties based on an available corpus of paired molecules. Since molecules can be optimized in different ways, there are multiple viable translations for each input graph. A key challenge is therefore t...Votes: 0GitHub stars: 3
- Linear Leakyintegrateandfire Neuron Model Based Spiking Neural Networks And Its Mapping Relationship To Deep Neural Networks**arXiv ID:** 2207.04889 **Authors:** Sijia Lu, Feng Xu **Published:** 2022-05-31T17:02:26Z **Abstract:** Spiking neural networks (SNNs) are brain-inspired machine learning algorithms with merits such as biological plausibility and unsupervised learning capability. Previous works have shown that converting Artificial Neural Networks (ANNs) into SNNs is a practical and efficient approach for implementing an SNN. However, the basic principle and theoretical groundwork are lacking for training a...Votes: 0GitHub stars: 3
- Llm For The Development Of Fcm**arXiv ID:** 2607.04983 **Authors:** Alexis Kafantaris **Published:** 2026-07-06T12:18:54Z **Abstract:** This article is about the development of a fuzzy cognitive map using a local large language model. In the light of recent advances it is evident that large language models, and even local large language models are capable of extracting quantities from textual data. In other words, a local LLM like Qwen2.5-32B, or probably larger, can accept entities as prompt input and determine relevant ...Votes: 0GitHub stars: 3
- Lossless Compression Of Neural Network Components Weights Checkpoints And Kv Caches In Lowprecision Formats**arXiv ID:** 2508.19263 **Authors:** Anat Heilper, Doron Singer **Published:** 2025-08-20T12:46:50Z **Abstract:** As deep learning models grow and deployment becomes more widespread, reducing the storage and transmission costs of neural network weights has become increasingly important. While prior work such as ZipNN has shown that lossless compression methods - particularly those based on Huffman encoding floating-point exponents can significantly reduce model sizes, these techniques have p...Votes: 0GitHub stars: 3
- Lti Systems Ode SolutionsRestrictive conditions for solving LTI systems by Ordinary Differential Equations - clarifying smoothness assumptions and applicability limits of standard solution methods. Activation: LTI systems, ODE solutions, system theory, control theory foundations.Votes: 0GitHub stars: 3
- Magic Entropy CftMagic Rényi entropy methodology unifying quantification of nonstabilizerness and non-Gaussianity across spins, bosons, and fermions using conformal field theory analysis.Votes: 0GitHub stars: 3
- Many Hamiltonian SparsifiableHamiltonian sparsification methodology showing that many quantum Hamiltonians can be reduced to significantly fewer terms while preserving system behavior for all states. Use when optimizing quantum simulations, reducing circuit depth, or simplifying Hamiltonians.Votes: 0GitHub stars: 3
- Multiobjective Evolutionary Design Of Composite Datadriven Models**arXiv ID:** 2103.01301 **Authors:** Iana S. Polonskaia, Nikolay O. Nikitin, Ilia Revin, Pavel Vychuzhanin, Anna V. Kalyuzhnaya **Published:** 2021-03-01T20:45:24Z **Abstract:** In this paper, a multi-objective approach for the design of composite data-driven mathematical models is proposed. It allows automating the identification of graph-based heterogeneous pipelines that consist of different blocks: machine learning models, data preprocessing blocks, etc. The implemented approach is based...Votes: 0GitHub stars: 3
- Multiparameter Hamiltonian EstimationOptimal multiparameter estimation for quantum systems using the unified Cramér-Rao bound framework. Use when: (1) estimating functions of multiple parameters in quantum Hamiltonians, (2) designing quantum sensing protocols, (3) analyzing precision limits for non-commuting generators, (4) optimizing quantum metrology with multiple parameters. Based on arXiv:2605.04136.Votes: 0GitHub stars: 3
- Non Hermitian Ssh Charge CorrelationsEnhancement of charge correlations and topological markers in interacting non-Hermitian Su-Schrieffer-Heeger models.Votes: 0GitHub stars: 3
- Non Invertible Topological Order AnalysisAnalysis methodology for non-invertible symmetry enriched topological orders (NI-SETO) using unitary fusion categories and anyon condensation. Combines category theory, topological quantum field theory, and string net models for quantum computing research.Votes: 0GitHub stars: 3
- Nonadiabatic Holonomic Nonhermitian GatesNonadiabatic holonomic single-qubit gates in non-Hermitian systems — leveraging exceptional points for faster geometric quantum gates while maintaining fault tolerance.Votes: 0GitHub stars: 3
- Nonlinear Separation Principle Applications Neural NetworksNonlinear separation principle with applications to neural networks, control and learning. Extends classical separation principle to nonlinear systems, enabling independent design of state observers and controllers for neural network-based systems. Activation: separation principle, neural network control, nonlinear observers, state estimation, control theoryVotes: 0GitHub stars: 3
- Nonlinear Separation PrincipleNonlinear separation principle for recurrent neural networks using contraction theory. Guarantees global exponential stability for interconnected controller-observer systems. Applicable to: neural network stability analysis, nonlinear control design, implicit deep learning, observer design, firing rate networks. Activation: separation principle, contraction theory, RNN stability, nonlinear control, observer design, firing rate neural network, Hopfield network stabilityVotes: 0GitHub stars: 3
- On The Ability Of Graph Neural Networks To Model Interactions Between Vertices**arXiv ID:** 2211.16494 **Authors:** Noam Razin, Tom Verbin, Nadav Cohen **Published:** 2022-11-29T18:58:07Z **Abstract:** Graph neural networks (GNNs) are widely used for modeling complex interactions between entities represented as vertices of a graph. Despite recent efforts to theoretically analyze the expressive power of GNNs, a formal characterization of their ability to model interactions is lacking. The current paper aims to address this gap. Formalizing strength of interactions throu...Votes: 0GitHub stars: 3
- On The Decision Boundary Of Deep Neural Networks**arXiv ID:** 1808.05385 **Authors:** Yu Li, Lizhong Ding, Xin Gao **Published:** 2018-08-16T09:25:50Z **Abstract:** While deep learning models and techniques have achieved great empirical success, our understanding of the source of success in many aspects remains very limited. In an attempt to bridge the gap, we investigate the decision boundary of a production deep learning architecture with weak assumptions on both the training data and the model. We demonstrate, both theoretically and emp...Votes: 0GitHub stars: 3
- Only Strict Saddles In The Energy Landscape Of Predictive Coding Networks**arXiv ID:** 2408.11979 **Authors:** Francesco Innocenti, El Mehdi Achour, Ryan Singh, Christopher L. Buckley **Published:** 2024-08-21T20:23:44Z **Abstract:** Predictive coding (PC) is an energy-based learning algorithm that performs iterative inference over network activities before updating weights. Recent work suggests that PC can converge in fewer learning steps than backpropagation thanks to its inference procedure. However, these advantages are not always observed, and the impact of P...Votes: 0GitHub stars: 3
- Phenokg Knowledge Graphdriven Gene Discovery And Patient Insights From Phenotypes Alone**arXiv ID:** 2506.13119 **Authors:** Kamilia Zaripova, Ege Özsoy, Nassir Navab, Azade Farshad **Published:** 2025-06-16T05:54:12Z **Abstract:** Identifying causative genes from patient phenotypes remains a significant challenge in precision medicine, with important implications for the diagnosis and treatment of genetic disorders. We propose a novel graph-based approach for predicting causative genes from patient phenotypes, with or without an available list of candidate genes, by integratin...Votes: 0GitHub stars: 3
- Physics Guided Generative OptimizationGenerate-and-evaluate loop for quantum circuit optimization combining conditional diffusion models, physics-informed neural networks, and graph neural networks. Use when optimizing Trotter-Suzuki decompositions, designing quantum circuits with generative models, or applying physics-guided neural optimization to NISQ compilation. Triggered by: generative quantum optimization, Trotter Suzuki decomposition, PINN feedback quantum, diffusion model circuit, NISQ compilation.Votes: 0GitHub stars: 3