All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Physics Guided Neural NetworkDesign neural networks that embed physical constraints (equations, symmetries, conservation laws) directly into the computational graph. Use when modeling physical systems, scientific computing, or when physics-informed AI is needed. Keywords: PGNN, physics-guided NN, physics-informed ML, physics-embedded NN, scientific ML, holographic QCD, AdS Dirac equation.Votes: 0GitHub stars: 3
- Physics Guided TransformerDesign Transformer architectures that embed physical structure (heat kernels, diffusion dynamics, temporal causality) into attention mechanisms. Use for physics-aware sequence modeling, scientific computing with Transformers, or when physical priors improve Transformer performance. Keywords: PGT, physics-guided attention, physics-aware Transformer, heat-kernel Transformer, diffusion attention, physical Transformer.Votes: 0GitHub stars: 3
- Physicsinformed Neural Networks Biological 2mathrmdt ReactioPhysics-informed neural networks (PINNs) provide a powerful framework for learning governing equations of dynamical systems from data. Biologically-informed neural networks (BINNs) are a variant of PINNs that preserve the known differential operator Activation: neural, network, dynamics, populationVotes: 0GitHub stars: 3
- Prediktor Patient Knowledge Graph Drug ResponsePREDIKTOR: Patient-centered multi-view framework aligning personalized knowledge graphs with gene-level perturbation representations for clinical drug response prediction. Combines DysRegNet GRN construction, DrugBank integration, GNN encoding, LINCS L1000 pretraining, and CLIP-style contrastive alignment.Votes: 0GitHub stars: 3
- Probability Geometry Schwinger DysonScore-mismatch field methodology for probing probability geometry using Schwinger-Dyson identities. Bridges statistical mechanics, information theory, and quantum field theory through geometric interpretation of equilibrium violations.Votes: 0GitHub stars: 3
- Proximodistal Exploration In Motor Learning As An Emergent Property Of Optimization**arXiv ID:** 1712.05249 **Authors:** Freek Stulp, Pierre-Yves Oudeyer **Published:** 2017-12-14T14:31:51Z **Abstract:** To harness the complexity of their high-dimensional bodies during sensorimotor development, infants are guided by patterns of freezing and freeing of degrees of freedom. For instance, when learning to reach, infants free the degrees of freedom in their arm proximodistally, i.e. from joints that are closer to the body to those that are more distant. Here, we formulate and st...Votes: 0GitHub stars: 3
- Q Prior Chaos ForecastingQuantum statistical prior (Q-Prior) methodology for chaotic system forecasting. Based on arXiv:2606.13422 — provable quantum advantage via two-copy Bell measurement for invariant measure estimation.Votes: 0GitHub stars: 3
- Qpinn Integro Fractional PdeQuantum Physics-Informed Neural Networks for solving integro-differential equations (IDEs) and fractional integro-partial differential equations (FIPDEs) using variational quantum circuits with affine feature maps.Votes: 0GitHub stars: 3
- Recoverability Collapse Information DecodersRecoverability collapse in self-referential information decoders — thermodynamic framework for analyzing when adaptive systems coupling inference to irreversible action lose recoverability under sustained overload. Use when analyzing AI system stability, distributed system failures, or decoder collapse under high-throughput regimes.Votes: 0GitHub stars: 3
- Room Temperature Dipole Synchronization NanocavityRoom-temperature synchronized dipole state methodology in plasmonic nanogap 2D arrays under continuous-wave pumping.Votes: 0GitHub stars: 3
- Rts Neural Physics Ode LearningHybrid neural-physics framework for learning unknown components of ODEs using Rauch-Tung-Striebel smoother and neural networksVotes: 0GitHub stars: 3
- Rts Smoother Guided Learning Physics Based Neural Differential Models- **Title**: RTS Smoother-Guided Learning of Physics-Based Neural Differential Models - **Authors**: Ahmet Demirkaya, Georgios Stratis, Tales Imbiriba, Zachary D. Danziger, Deniz Erdogmus - **arXiv ID**: 2607.15180 - **URL**: http://arxiv.org/abs/2607.15180 - **Subjects**: Machine Learning (cs.LG); Systems and Control (eess.SY) - **Abstract**: Ordinary differential equations (ODEs) are widely used to model dynamical systems in physics, biology, neuroscience, and physiology, but in many applicatiVotes: 0GitHub stars: 3
- Sequential Kv Cache Compression Via Probabilistic Language Tries Beyond The Pervector Shannon Limit**arXiv ID:** 2604.15356 **Authors:** Gregory Magarshak **Published:** 2026-04-10T22:48:19Z **Abstract:** Recent work on KV cache quantization, culminating in TurboQuant, has approached the Shannon entropy limit for per-vector compression of transformer key-value caches. We observe that this limit applies to a strictly weaker problem than the one that actually matters: compressing the KV cache as a sequence. The tokens stored in a KV cache are not arbitrary floating-point data -- they are sam...Votes: 0GitHub stars: 3
- Shallow Unorganized Neural Networks Using Smart Neuron Model For Visual Perception**arXiv ID:** 1907.09050 **Authors:** Richard Jiang, Danny Crookes **Published:** 2019-07-21T23:09:35Z **Abstract:** The recent success of Deep Neural Networks (DNNs) has revealed the significant capability of neural computing in many challenging applications. Although DNNs are derived from emulating biological neurons, there still exist doubts over whether or not DNNs are the final and best model to emulate the mechanism of human intelligence. In particular, there are two discrepancies betwe...Votes: 0GitHub stars: 3
- Sic Overlap Stark Units Number TheoryQuantum SIC-POVM overlap analysis via algebraic number theory — Stark units, ray class fields, and Galois theory for exact quantum state characterization. Use when analyzing SIC-POVM overlaps, quantum state tomography, algebraic number theory in quantum information, or Stark units.Votes: 0GitHub stars: 3
- Social Spatial Navigation Phase TransitionsSocial-spatial dependencies in visual navigation learning with neural network agents. Demonstrates phase transitions from individual to social following strategies based on information quality and spatial effects.Votes: 0GitHub stars: 3
- Stablesleep Sourcefree Testtime Adaptation For Sleep Staging With Lightweight Safety Rails**arXiv ID:** 2509.02982 **Authors:** Hritik Arasu, Faisal R Jahangiri **Published:** 2025-09-03T03:42:31Z **Abstract:** Sleep staging models often degrade when deployed on patients with unseen physiology or recording conditions. We propose a streaming, source-free test-time adaptation (TTA) recipe that combines entropy minimization (Tent) with Batch-Norm statistic refresh and two safety rails: an entropy gate to pause adaptation on uncertain windows and an EMA-based reset to reel back drift....Votes: 0GitHub stars: 3
- Stl A Signed And Truncated Logarithm Activation Function For Neural Networks**arXiv ID:** 2307.16389 **Authors:** Yuanhao Gong **Published:** 2023-07-31T03:41:14Z **Abstract:** Activation functions play an essential role in neural networks. They provide the non-linearity for the networks. Therefore, their properties are important for neural networks' accuracy and running performance. In this paper, we present a novel signed and truncated logarithm function as activation function. The proposed activation function has significantly better mathematical properties, such ...Votes: 0GitHub stars: 3
- Sum Of Hermitian Squares Pauli ConvergenceExplicit convergence rates for Sum-of-Hermitian-Squares hierarchies over the Pauli algebra, enabling accuracy guarantees for noncommutative polynomial optimization in quantum theory.Votes: 0GitHub stars: 3
- Tensor Field Networks Rotation And Translationequivariant Neural Networks For 3d Point Clouds**arXiv ID:** 1802.08219 **Authors:** Nathaniel Thomas, Tess Smidt, Steven Kearnes, Lusann Yang, Li Li, Kai Kohlhoff, Patrick Riley **Published:** 2018-02-22T18:17:31Z **Abstract:** We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer. 3D rotation equivariance removes the need for data augmentation to identify features in arbitrary orientations. Our network uses filters built from spherical harmonics;...Votes: 0GitHub stars: 3
- The Loss Landscape Of Overparameterized Neural Networks**arXiv ID:** 1804.10200 **Authors:** Y Cooper **Published:** 2018-04-26T17:58:45Z **Abstract:** We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from $\mathbb{R}^n$ to $\mathbb{R}$ - in particular, nonconvex, with discrete global minima. In this paper, we prove that in at least one important way, the loss function of an overparameterized neural network does not loo...Votes: 0GitHub stars: 3
- Thermodynamic NetworksFramework for autonomous physics-based computation using non-equilibrium steady states in thermodynamic networks. Models computation as exchanges of conserved quantities between finite-size reservoirs relaxing toward equilibrium. Use when designing physical computing systems, thermodynamic engines, or autonomous molecular computation.Votes: 0GitHub stars: 3
- Topology From DecoherenceTopology from decoherence methodology — inducing topological quantum phases via correlated environment-induced dephasing in open many-body systems, characterized by winding numbers and non-Hermitian skin effects.Votes: 0GitHub stars: 3
- Towards A Mathematical Understanding Of The Difficulty In Learning With Feedforward Neural Networks**arXiv ID:** 1611.05827 **Authors:** Hao Shen **Published:** 2016-11-17T19:29:27Z **Abstract:** Training deep neural networks for solving machine learning problems is one great challenge in the field, mainly due to its associated optimisation problem being highly non-convex. Recent developments have suggested that many training algorithms do not suffer from undesired local minima under certain scenario, and consequently led to great efforts in pursuing mathematical explanations for such obse...Votes: 0GitHub stars: 3
- Training Binary Neural Networks Without Floating Point Precision**arXiv ID:** 2310.19815 **Authors:** Federico Fontana **Published:** 2023-10-19T13:48:21Z **Abstract:** The main goal of this work is to improve the efficiency of training binary neural networks, which are low latency and low energy networks. The main contribution of this work is the proposal of two solutions comprised of topology changes and strategy training that allow the network to achieve near the state-of-the-art performance and efficient training. The time required for training and th...Votes: 0GitHub stars: 3
- Vector Policy Optimization Training For Diversity Improves Testtime Search**arXiv ID:** 2605.22817 **Authors:** Ryan Bahlous-Boldi, Isha Puri, Idan Shenfeld, Akarsh Kumar, Mehul Damani, Sebastian Risi, Omar Khattab, Zhang-Wei Hong, Pulkit Agrawal **Published:** 2026-05-21T17:59:26Z **Abstract:** Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a variety of task-specific reward functions. Unfortunately, the standard paradigm of LLM post-trainin...Votes: 0GitHub stars: 3
- Visualizing Representational Dynamics With Multidimensional Scaling Alignment**arXiv ID:** 1906.09264 **Authors:** Baihan Lin, Marieke Mur, Tim Kietzmann, Nikolaus Kriegeskorte **Published:** 2019-06-21T03:46:18Z **Abstract:** Representational similarity analysis (RSA) has been shown to be an effective framework to characterize brain-activity profiles and deep neural network activations as representational geometry by computing the pairwise distances of the response patterns as a representational dissimilarity matrix (RDM). However, how to properly analyze and visuali...Votes: 0GitHub stars: 3
- Whats The Magic Word A Control Theory Of Llm Prompting**arXiv ID:** 2310.04444 **Authors:** Aman Bhargava, Cameron Witkowski, Shi-Zhuo Looi, Matt Thomson **Published:** 2023-10-02T22:35:40Z **Abstract:** Prompt engineering is crucial for deploying LLMs but is poorly understood mathematically. We formalize LLM systems as a class of discrete stochastic dynamical systems to explore prompt engineering through the lens of control theory. We offer a mathematical analysis of the limitations on the controllability of self-attention as a function of the ...Votes: 0GitHub stars: 3
- Why Flow Matching Is Particle Swarm Optimization**arXiv ID:** 2507.20810 **Authors:** Kaichen Ouyang **Published:** 2025-07-28T13:21:14Z **Abstract:** This paper preliminarily investigates the duality between flow matching in generative models and particle swarm optimization (PSO) in evolutionary computation. Through theoretical analysis, we reveal the intrinsic connections between these two approaches in terms of their mathematical formulations and optimization mechanisms: the vector field learning in flow matching shares similar mathemat...Votes: 0GitHub stars: 3
- Practical Quantum Topological Data AnalysisPractical Quantum Topological Data Analysis with Applications to High-Dimensional Feature Extraction and Time Series AnalysisVotes: 0GitHub stars: 3
- Project DealProject DealVotes: 0GitHub stars: 3
- Pt Snn Csp SolverParallel Tempering integration for Spiking Neural Network-based CSP solvers — overcoming local-minimum traps in stochastic SNN optimization. From arXiv:2607.08897 (Uludag et al., Jul 2026).Votes: 0GitHub stars: 3
- Ptq4snn Membrane Aware Post Training QuantizationPTQ4SNN: joint weight and membrane quantization for SNNs.Votes: 0GitHub stars: 3
- Quantispect Structure Aware 3d Cnn PredecoderStructure-aware lightweight 3D CNN pre-decoder for scalable surface code quantum error correction. Use when designing or benchmarking neural QEC decoders for surface codes, implementing spatio-temporal syndrome processing, replacing dense 3D convolutions with factorized branches, or co-designing lightweight pre-decoders with classical matching decoders. Trigger words: QuantiSpect, surface code neural decoder, 3D CNN QEC, FastHyperBlock, quantum error correction pre-decoder, spatio-temporal sy...Votes: 0GitHub stars: 3
- Quantum Driven Neuromorphic Million QubitQuantum-Driven Neuromorphic Computing methodology for million-qubit scale systems. Integrates quantum computing principles with neuromorphic architectures to achieve scalable, energy-efficient computation at million-qubit scales.Votes: 0GitHub stars: 3
- Quantum Error Correction Biological AnalogyStructural analogy methodology between quantum error correction (QEC) and biological error correction (BEC) in neural circuits, focusing on redundant encodings, constraint-based inference, and codespace protection.Votes: 0GitHub stars: 3
- Quantum Magic Noncommutativity Qrcname: quantum-magic-noncommutativity-qrc description: "Skill for understanding and applying quantum reservoir computing theory based on quantum magic and non-commutativity as computational resources. Use when analyzing QRC architectures, designing quantum reservoir systems, or studying quantum advantages in temporal information processing." ---Votes: 0GitHub stars: 3
- Quantum Reservoir Neurodynamical ForecastingQuantum Reservoir Computing (QRC) methodology for neurodynamical forecasting using transverse-field Ising model, heterogeneous quantum measurements, and polynomial ridge regression. Applied to EEG-like data with parallel reservoir architecture.Votes: 0GitHub stars: 3
- A Quantum Like Benchmark For Context Sensitive AssDerived from arXiv:2606.12449 - A quantum-like benchmark for context-sensitive associative memory with adaptive plasticityVotes: 0GitHub stars: 3
- Adaptive Qec DecoderAdaptive confidence-gated quantum error correction decoding methodology. Two-stage inference: lightweight neural fast-path + MWPM refinement for latency-constrained QEC systems. Use when designing real-time quantum decoders, hardware-aware QEC co-design, or latency-accuracy trade-off optimization.Votes: 0GitHub stars: 3
- Ai Quantum Comprehensive ReviewComprehensive review of the AI-Quantum Information interface — covering AI for quantum systems (measurement, algorithm discovery, hardware stabilization) and quantum for AI (algorithmic speedups, expressivity, trainability, generalization).Votes: 0GitHub stars: 3
- Almost Iid Quantum InformationAlternative definitions and analysis of "almost i.i.d." quantum states for practical quantum information theory. The i.i.d. assumption is ubiquitous in quantum information theory but too stringent for practical settings. Introduces definitions based on normalized quantum Wasserstein distance and local-structure analysis. Use when: analyzing quantum information sources beyond i.i.d. assumption, designing quantum protocols for correlated sources, studying quantum Wasserstein distance applicatio...Votes: 0GitHub stars: 3
- Alternating Minimization Gate SynthesisAlternating-minimization methodology for large-scale multimode entangling-gate synthesis in trapped-ion systems. Use when designing multi-tone control fields for entangling gates, optimizing spin-spin interactions while suppressing spin-motion entanglement, or scaling gate synthesis to large ion chains (N=100-1000). Activation: alternating minimization, gate synthesis, trapped-ion, multimode entangling, multi-tone control, spin-spin interaction, programmable interaction engineering, Mølmer-Sø...Votes: 0GitHub stars: 3
- Arxiv 2608 05595v1 How Much Reconstruction Does Quantum Machine Learn**arXiv ID:** 2608.05595v1 **Authors:** Prabhjot Singh, Adel N. Toosi, Rajkumar Buyya **URL:** http://arxiv.org/abs/2608.05595v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 05610v1 Lc Implicit Qaoa Active Workspace Capped Exact Obj**arXiv ID:** 2608.05610v1 **Authors:** Chih-Chung Hsu **URL:** http://arxiv.org/abs/2608.05610v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 05646v1 Rasp Qaoa Resource Aware Per Instance Selection Fo**arXiv ID:** 2608.05646v1 **Authors:** Chih-Chung Hsu **URL:** http://arxiv.org/abs/2608.05646v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 05686v1 Provably Efficient Self Calibrating Quantum Fault**arXiv ID:** 2608.05686v1 **Authors:** Weiyuan Gong, Hong-Ye Hu **URL:** http://arxiv.org/abs/2608.05686v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 05819v1 Learning To Rank Tensor Network Contraction Plans**arXiv ID:** 2608.05819v1 **Authors:** Alfred M. Pastor, Maribel Castillo, Jose M. Badia **URL:** http://arxiv.org/abs/2608.05819v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 05995 A Unified Risk View Of Uncertainty Posterior RiskA Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies (arXiv: 2608.05995)Votes: 0GitHub stars: 3
- Arxiv 2608 05995v1 A Unified Risk View Of Uncertainty Posterior RiskA Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies (arXiv: 2608.05995v1)Votes: 0GitHub stars: 3