All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Interlockingfree Selective Rationalization Through Geneticbased Learning**arXiv ID:** 2412.10312 **Authors:** Federico Ruggeri, Gaetano Signorelli **Published:** 2024-12-13T17:52:48Z **Abstract:** A popular end-to-end architecture for selective rationalization is the select-then-predict pipeline, comprising a generator to extract highlights fed to a predictor. Such a cooperative system suffers from suboptimal equilibrium minima due to the dominance of one of the two modules, a phenomenon known as interlocking. While several contributions aimed at addressing inter...Votes: 0GitHub stars: 3
- Interpretable Machine Learning Through TeachingSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Intrinsic Computational FunctionalismIntrinsic Computational Functionalism methodology — From Observer-Relative Maps to Observer-Independent Structures. Addresses observer-relativity problem in computational theories of consciousness with operationalizable criteria.Votes: 0GitHub stars: 3
- Intrinsic Noise Consolidation Continual LearningDoob-barrier-conditioned diffusion methodology for turning analog neuromorphic hardware noise into a continual-learning resource — per-synapse consolidation via Doob h-transform creates noise-amplified restoring force that yields inverted-U noise-retention relationship. Validated on BrainScaleS-2 neuromorphic silicon with hardware-in-the-loop training.Votes: 0GitHub stars: 3
- Jacobian Geometry Robustness QnnJGRA framework for assessing robustness in NISQ noise-aware Quantum Neural Networks via Jacobian geometry. Captures model sensitivity to parameter perturbations induced by noise through entropy-matched noise calibration, noise-aware training, and noise-conditioned Jacobian extraction. Accepted at IEEE qCCL 2026. Activation: QNN robustness, NISQ noise, Jacobian geometry, quantum neural network, noise-aware training, robustness assessment, decoherence, parameter perturbation, geometric descript...Votes: 0GitHub stars: 3
- Jeffreys Flow SamplingJeffreys Flow framework for robust Boltzmann generators and rare event sampling. Addresses mode collapse in multi-modal distributions using Jeffreys divergence + Parallel Tempering distillation. Use when: sampling rough energy landscapes, Boltzmann generators, rare events, quantum thermal states, path integral Monte Carlo, avoiding KL divergence mode collapse.Votes: 0GitHub stars: 3
- Jost Function Analytic OdeMethodology for analyzing analytic properties of Jost functions in quantum scattering theory via parameter-dependent ODEs (Poincare-Picard theorem). Applies to scattering matrix analytic continuation, complex energy plane analysis, and quantum scattering problems with short-range potentials. Bridges mathematical analysis (ODE theory, complex analysis) with quantum physics. Activation: jost function, quantum scattering theory, analytic continuation scattering matrix, Poincare-Picard theorem, p...Votes: 0GitHub stars: 3
- Kat Kl Agreement Trap TerminationKL Agreement Trap Termination (KAT) for on-policy distillation. Detects persistent low-KL agreement traps and terminates early to improve training efficiency.Votes: 0GitHub stars: 3
- Kernel Hopfield Associative MemoryKernel Hopfield networks: geometric analysis of attractor boundaries and storage capacity limits. KLR-trained associative memories with P/N ~16 for random sequences and ~20 for structured data. Trigger words: kernel Hopfield, associative memory, KLR, attractor basin, storage capacity, kernel logistic regression.Votes: 0GitHub stars: 3
- Kernel Hopfield Attractor GeometryGeometric analysis of attractor boundaries and storage capacity limits in kernel Hopfield networks trained with Kernel Logistic Regression (KLR). Covers attractor basin geometry, Ridge of Optimization, morphing analysis, SNR vs Cover's theorem, and dynamical stability. Activation: kernel Hopfield, KLR associative memory, attractor basin geometry, Ridge of Optimization, morphing analysis Hopfield, storage capacity Hopfield, SNR analysis Hopfield, Cover's theorem associative memory, crosstalk n...Votes: 0GitHub stars: 3
- Kernel Hopfield Event Driven RetrievalEvent-driven asynchronous retrieval in Kernel Logistic Regression (KLR) Hopfield networks for neuromorphic associative memory. Covers asynchronous update dynamics, large-margin attractor energy landscapes, and sparse event-driven computation. Use when: (1) building neuromorphic associative memory systems, (2) optimizing Hopfield network retrieval for energy efficiency, (3) analyzing event-driven neural computation, (4) studying kernel-based associative memories, or (5) comparing synchronous v...Votes: 0GitHub stars: 3
- Kinematic Zero Shot BciConserved Kinematic Representations for Zero-Shot Decoding in Handwriting BCIs. Methodology aligning neural activity to imagined kinematics for zero-shot capable ML decoding of unseen characters in BCI systems. Use when: researching brain-computer interfaces, motor cortex representations, zero-shot decoding, handwriting BCIs, kinematic primitives, logographic language neuroprosthetics, compositional motor control. Keywords: zero-shot BCI, kinematic representation, handwriting decoding, motor ...Votes: 0GitHub stars: 3
- Kirchhoff Inspired Neural NetworksKirchhoff-Inspired Neural Network (KINN) - state-variable-based network architecture built on Kirchhoff's current law for evolving high-order perception. Derives numerically stable state updates from ODEs, enabling explicit decoupling and encoding of higher-order evolutionary components. Keywords: KINN, Kirchhoff, ODE-based neural networks, high-order perception, PDE solving, physics-informed neural networks, state-variable networks.Votes: 0GitHub stars: 3
- Kirchhoff Neural Network High Order PerceptionKirchhoff-inspired Neural Network combining circuit theory with high-order topological structures for perceptual computation. Models neural information flow using Kirchhoff's laws on graph circuits with simplicial complexes, enabling higher-order interaction processing beyond pairwise connections. Activation: Kirchhoff, high-order, simplicial complex, neural circuit, perception, topological neural network.Votes: 0GitHub stars: 3
- Klr Hopfield Event Driven RetrievalKernel Logistic Regression (KLR) Hopfield Network with asynchronous event-driven retrieval methodology. Enables high-capacity associative memory (P/N ≈ 30, vs classical 0.14N) with neuromorphic-compatible sparse computation. Use when: designing associative memory systems, event-driven neuromorphic hardware deployment, comparing Hopfield variants (KLR vs MHN), analyzing attractor landscapes, kernel-based neural networks, or studying asynchronous vs synchronous retrieval dynamics in neural comp...Votes: 0GitHub stars: 3
- Knowledgeaware Evolutionary Graph Neural Architecture Search**arXiv ID:** 2411.17339 **Authors:** Chao Wang, Jiaxuan Zhao, Lingling Li, Licheng Jiao, Fang Liu, Xu Liu, Shuyuan Yang **Published:** 2024-11-26T11:32:45Z **Abstract:** Graph neural architecture search (GNAS) can customize high-performance graph neural network architectures for specific graph tasks or datasets. However, existing GNAS methods begin searching for architectures from a zero-knowledge state, ignoring the prior knowledge that may improve the search efficiency. The available knowl...Votes: 0GitHub stars: 3
- Koopman Representation LearningKoopman operator theory for learning eigenfunctions from observations at arbitrary, non-vanishing time intervals. Addresses aliasing from oscillatory dynamics and sampling patterns, with phase alignment near true frequencies. Use for: Koopman operator learning, dynamical system analysis, data assimilation, irregular sampling, eigenfunction identification. Activation: Koopman operator, eigenfunction learning, dynamical systems, irregular sampling, data assimilation.Votes: 0GitHub stars: 3
- Krylov Complexity Analog SimulatorBridging Krylov complexity theory with universal analog quantum simulation — using Lanczos algorithm and Krylov subspace growth to characterize computational power of analog quantum simulators. Activation: Krylov complexity, analog quantum simulator, Lanczos algorithm quantum, operator growth complexity.Votes: 0GitHub stars: 3
- L System Neural Network EvolutionL-System genetic encoding methodology for scalable neural network evolution. Uses Lindenmayer system grammar to encode neural networks, enabling compact representation and efficient evolutionary search. Applies to: neuroevolution, scalable network encoding, genetic algorithms, neural architecture search. Activation: L-system neural encoding, Lindenmayer neuroevolution, genetic network encoding, scalable neural evolution, grammar-based NAS.Votes: 0GitHub stars: 3
- Large Neural Networks Learning From Scratch With Very Few Data And Without Explicit Regularization**arXiv ID:** 2205.08836 **Authors:** Christoph Linse, Thomas Martinetz **Published:** 2022-05-18T10:08:28Z **Abstract:** Recent findings have shown that highly over-parameterized Neural Networks generalize without pretraining or explicit regularization. It is achieved with zero training error, i.e., complete over-fitting by memorizing the training data. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in ...Votes: 0GitHub stars: 3
- Latent Memory Palace Reasoning Control Variational InferenceLatent 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 compute. Variable-length action tokenizer. Activation: latent memory, reasoning for control, autoregressive variational inference, adaptive reasoning, continuous control.Votes: 0GitHub stars: 3
- Latent On Policy Self DistillationLOPD: learnable privileged context for agentic AI evolution.Votes: 0GitHub stars: 3
- Lazy Learning A Biologicallyinspired Plasticity Rule For Fast And Energy Efficient Synaptic Plasticity**arXiv ID:** 2303.16067 **Authors:** Aaron Pache, Mark CW van Rossum **Published:** 2023-03-26T16:17:04Z **Abstract:** When training neural networks for classification tasks with backpropagation, parameters are updated on every trial, even if the sample is classified correctly. In contrast, humans concentrate their learning effort on errors. Inspired by human learning, we introduce lazy learning, which only learns on incorrect samples. Lazy learning can be implemented in a few lines of code ...Votes: 0GitHub stars: 3
- Learning In The Machine Random Backpropagation And The Deep Learning Channel**arXiv ID:** 1612.02734 **Authors:** Pierre Baldi, Peter Sadowski, Zhiqin Lu **Published:** 2016-12-08T17:15:45Z **Abstract:** Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is remarkable both because of its effectiveness, in spite of using random matrices to communicate error information, and because it compl...Votes: 0GitHub stars: 3
- Learning Intrinsic Sparse Structures Within Long Shortterm Memory**arXiv ID:** 1709.05027 **Authors:** Wei Wen, Yuxiong He, Samyam Rajbhandari, Minjia Zhang, Wenhan Wang, Fang Liu, Bin Hu, Yiran Chen, Hai Li **Published:** 2017-09-15T01:10:23Z **Abstract:** Model compression is significant for the wide adoption of Recurrent Neural Networks (RNNs) in both user devices possessing limited resources and business clusters requiring quick responses to large-scale service requests. This work aims to learn structurally-sparse Long Short-Term Memory (LSTM) by reduc...Votes: 0GitHub stars: 3
- Learning To CommunicateSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Learning To Cooperate Compete And CommunicateSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Learning To Model Other MindsSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Learning To Play Minecraft With Video PretrainingSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Linear Reservoir Computing BottleneckMethodology for analyzing information processing capacity limits in linear reservoir computing systems and identifying quantum advantages in reservoir computing.Votes: 0GitHub stars: 3
- Lionmuon OptimizerLionMuon optimizer methodology - alternating between spectral (Muon) and sign-based (Lion) updates on a fixed period for compute-efficient large-scale trainingVotes: 0GitHub stars: 3
- Local Plasticity Rules Can Learn Deep Representations Using Selfsupervised Contrastive Predictions**arXiv ID:** 2010.08262 **Authors:** Bernd Illing, Jean Ventura, Guillaume Bellec, Wulfram Gerstner **Published:** 2020-10-16T09:32:35Z **Abstract:** Learning in the brain is poorly understood and learning rules that respect biological constraints, yet yield deep hierarchical representations, are still unknown. Here, we propose a learning rule that takes inspiration from neuroscience and recent advances in self-supervised deep learning. Learning minimizes a simple layer-specific loss functio...Votes: 0GitHub stars: 3
- Loewner Order AlgorithmIterative algorithm to compute minimal upper bounds in the Loewner order on Hermitian matrices. Use for quantum information, convex optimization, operator theory, and numerical linear algebra tasks involving matrix inequalities.Votes: 0GitHub stars: 3
- Looking Through Glass Box**arXiv ID:** 2603.06272 **Authors:** Alexis Kafantaris **Published:** 2026-03-06T13:32:12Z **Abstract:** This essay is about a neural implementation of the fuzzy cognitive map, the FHM, and corresponding evaluations. Firstly, a neural net has been designed to behave the same way that an FCM does; as inputs it accepts many fuzzy cognitive maps and propagates them in order to learn causality patterns. Moreover, the network uses langevin differential Dynamics, which avoid overfit, to inverse so...Votes: 0GitHub stars: 3
- Magic For The Age Of Quantized Dnns**arXiv ID:** 2403.14999 **Authors:** Yoshihide Sawada, Ryuji Saiin, Kazuma Suetake **Published:** 2024-03-22T07:21:09Z **Abstract:** Recently, the number of parameters in DNNs has explosively increased, as exemplified by LLMs (Large Language Models), making inference on small-scale computers more difficult. Model compression technology is, therefore, essential for integration into products. In this paper, we propose a method of quantization-aware training. We introduce a novel normalization ...Votes: 0GitHub stars: 3
- Magic Number Theoretic ComplexityAnalyze quantum algorithms through the lens of magic (non-stabilizerness) and number-theoretic complexity. Covers the resource-theoretic framework for quantifying genuinely quantum resources in quantum algorithms, particularly Shor's factoring algorithm. Use when: (1) analyzing quantum algorithm resource requirements beyond gate counts, (2) studying the connection between classical computational hardness and quantum resource consumption, (3) evaluating magic state requirements for fault-toler...Votes: 0GitHub stars: 3
- Majority Of Three Pac OptimalityStatistical learning theory methodology proving majority-of-three voting is optimal in the realizable PAC settingVotes: 0GitHub stars: 3
- Majorization Supermodularity InformationMajorization lattice supermodularity and subadditivity framework — two structural majorization relations (precursors) underlying supermodularity and subadditivity of all sum-concave functions including Tsallis, Rényi, and Shannon entropies on the majorization lattice. Applies to quantum information theory, entropy inequalities, lattice theory. Activation: majorization, supermodularity, subadditivity, majorization lattice, Tsallis entropy, Rényi entropy, sum-concave, information theory lattice...Votes: 0GitHub stars: 3
- Margin Runtime Confidence Calibration"Multi-Agent Runtime Grading via Incremental Normalization (MARGIN) — online confidence calibration for multi-agent AI coordination. Use when building multi-agent systems that need to weight agent trustworthiness at runtime: (1) coordinating responses from multiple foundation models, (2) selecting which agent's output to trust when self-reported confidence is unreliable, (3) calibrating confidence under distribution shift without held-out data or retraining.Votes: 0GitHub stars: 3
- Medical Domain AdaptationMedical image domain adaptation and transfer learning methodology. Use when working with medical imaging AI tasks including: (1) adapting pre-trained models to new clinical domains with scarce annotated data, (2) parameter-efficient fine-tuning for medical image segmentation/classification, (3) handling domain shift between different medical imaging sites/modalities, (4) federated learning for medical images across institutions. Covers RKHS-MMD, PEFT, MedSR, and imbalanced classification in m...Votes: 0GitHub stars: 3
- Memoir Memory Rewriting Neural NetworksMethodology for analyzing the effects of memory rewriting during neural network inference, comparing coupled vs read-only pondering architectures.Votes: 0GitHub stars: 3
- Mest Accurate And Fast Memoryeconomic Sparse Training Framework On The Edge**arXiv ID:** 2110.14032 **Authors:** Geng Yuan, Xiaolong Ma, Wei Niu, Zhengang Li, Zhenglun Kong, Ning Liu, Yifan Gong, Zheng Zhan, Chaoyang He, Qing Jin, Siyue Wang, Minghai Qin, Bin Ren, Yanzhi Wang, Sijia Liu, Xue Lin **Published:** 2021-10-26T21:15:17Z **Abstract:** Recently, a new trend of exploring sparsity for accelerating neural network training has emerged, embracing the paradigm of training on the edge. This paper proposes a novel Memory-Economic Sparse Training (MEST) framework ta...Votes: 0GitHub stars: 3
- Meta Learning Context Enables TrainingMeta-learning In-Context approach for training-free cross-subject brain decoding. Uses meta-trained models to decode fMRI activity patterns across different subjects without retraining. Activation: meta-learning, brain decoding, cross-subject, fMRI decoding, training-free, in-context learning, neural decoding, generalizable decodingVotes: 0GitHub stars: 3
- Meta Learning Context EnablesMeta-learning In-Context Enables Training-Free Cross Subject Brain Decoding... Activation: 脑, 元学习, meta-learning, brainVotes: 0GitHub stars: 3
- Meta Learning For WrestlingSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Meta Learning Human Visual RepresentationsMeta-learning methodology for achieving human-like visual representations. Proposes that meta-learning (learning to learn) pressure shapes neural representations to support open-ended tasks. Compared to pretrained models, meta-learned representations better predict human similarity judgments, semantic rule learning, and high-level visual cortex activity. Activation: meta-learning, visual representations, brain alignment, human similarity, semantic learning, few-shot learning, visual cortexVotes: 0GitHub stars: 3
- Meta Learning Ict Brain Decoding元学习上下文方法实现无需训练的跨被试脑解码。通过上下文学习实现训练无关的跨个体fMRI解码。适用于零样本脑解码、快速脑机接口、个体化神经科学。触发词：元学习脑解码、上下文学习、跨被试、训练无关、零样本。Votes: 0GitHub stars: 3
- Meta Learning In Context Brain Decoding V3Meta-learning in-context brain decoding methodology for zero-shot cross-subject generalization in BCI. Enables training-free adaptation to new users by framing brain signal decoding as an in-context learning problem — constructing support sets from other subjects and using them as context at inference time without any fine-tuning. Applicable to EEG, MEG, fMRI, and invasive recordings.Votes: 0GitHub stars: 3
- Meta Learning In Context Brain Decoding V4BrainCoDec v4 — Foundation framework for training-free cross-subject fMRI-based semantic visual decoding via meta-optimized in-context learning. Achieves zero-shot generalization across subjects and scanners without anatomical alignment or stimulus overlap. Use when: cross-subject brain decoding, fMRI visual reconstruction, training-free neural decoding, meta-learning for neuroscience, brain-computer interfaces. Trigger: brain decoding, fMRI decoding, cross-subject, meta-learning in-context, ...Votes: 0GitHub stars: 3
- Meta Learning In Context Brain Decoding V5BrainCoDec v5 — Foundation framework for training-free cross-subject brain decoding using meta-learning in-context approach. Enables zero-shot visual decoding from fMRI without subject-specific training. Activation: brain decoding, meta-learning, in-context, cross-subject, fMRI decoding, zero-shot brain decoding.Votes: 0GitHub stars: 3