All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Experimental Insights Towards Explainable And Interpretable Pedestrian Crossing Prediction**arXiv ID:** 2312.02872 **Authors:** Angie Nataly Melo, Carlota Salinas, Miguel Angel Sotelo **Published:** 2023-12-05T16:39:32Z **Abstract:** In the context of autonomous driving, pedestrian crossing prediction is a key component for improving road safety. Presently, the focus of these predictions extends beyond achieving trustworthy results; it is shifting towards the explainability and interpretability of these predictions. This research introduces a novel neuro-symbolic approach that com...Votes: 0GitHub stars: 3
- Exploiting Large Neuroimaging Datasets To Create Connectomeconstrained Approaches For More Robust Efficient And Adaptable Artificial Intelligence**arXiv ID:** 2305.17300 **Authors:** Erik C. Johnson, Brian S. Robinson, Gautam K. Vallabha, Justin Joyce, Jordan K. Matelsky, Raphael Norman-Tenazas, Isaac Western, Marisel Villafañe-Delgado, Martha Cervantes, Michael S. Robinette, Arun V. Reddy, Lindsey Kitchell, Patricia K. Rivlin, Elizabeth P. Reilly, Nathan Drenkow, Matthew J. Roos, I-Jeng Wang, Brock A. Wester, William R. Gray-Roncal, Joan A. Hoffmann **Published:** 2023-05-26T23:04:53Z **Abstract:** Despite the progress in deep learni...Votes: 0GitHub stars: 3
- Exploring Brain Networks Eeg MegSkill for exploring brain networks using noninvasive electrophysiological measurements (EEG/MEG) based on arXiv:2607.17602v1. Covers forward/inverse problems, source reconstruction, connectivity measures, and analysis pipelines.Votes: 0GitHub stars: 3
- Exploring Brain Networks Noninvasive Electrophysiological Measurements---\nname: exploring-brain-networks-noninvasive-electrophysiological-measurements\ndescription: \"Methodology for exploring brain networks using noninvasive electrophysiological measurements (EEG/MEG) based on arXiv:2607.17602\"\n---\n\n## Context\n\nThis skill provides a comprehensive framework for EEG/MEG-based brain network analysis, covering the methodological foundations and practical workflows for investigating functional and effective interactions within large-scale brain networks usin...Votes: 0GitHub stars: 3
- Exponential Family Predictive CodingExtended predictive coding framework using exponential family distributions beyond Gaussian assumptions. Reveals biological neural network properties: nonlinearity, heterogeneity, biological plausibility. Maintains FEP-PC correspondence up to second cumulant. Derives biologically plausible local plasticity rules from EFD variational free energy. Use when: predictive coding, free energy principle, exponential family, variational inference, biological plausibility, local plasticity rules, neura...Votes: 0GitHub stars: 3
- Extension Profile Shape FunctionsBeyond mutual information — extension profiles and shape functions of random variable pairs. Use when analyzing structural properties of joint distributions not captured by mutual information alone, connecting information theory to spectral graph theory, or deriving non-Shannon-type information inequalities.Votes: 0GitHub stars: 3
- Faaid A Transformer Model For Neurosymbolic Facade Reconstruction**arXiv ID:** 2406.01829 **Authors:** Aleksander Plocharski, Jan Swidzinski, Joanna Porter-Sobieraj, Przemyslaw Musialski **Published:** 2024-06-03T22:56:40Z **Abstract:** We introduce a neuro-symbolic transformer-based model that converts flat, segmented facade structures into procedural definitions using a custom-designed split grammar. To facilitate this, we first develop a semi-complex split grammar tailored for architectural facades and then generate a dataset comprising of facades along...Votes: 0GitHub stars: 3
- Fedhealth A Federated Transfer Learning Framework For Wearable Healthcare**arXiv ID:** 1907.09173 **Authors:** Yiqiang Chen, Jindong Wang, Chaohui Yu, Wen Gao, Xin Qin **Published:** 2019-07-22T07:56:33Z **Abstract:** With the rapid development of computing technology, wearable devices such as smart phones and wristbands make it easy to get access to people's health information including activities, sleep, sports, etc. Smart healthcare achieves great success by training machine learning models on a large quantity of user data. However, there are two critical chall...Votes: 0GitHub stars: 3
- Finetuning And Evaluating Opensource Large Language Models For The Army Domain**arXiv ID:** 2410.20297 **Authors:** Daniel C. Ruiz, John Sell **Published:** 2024-10-27T00:39:24Z **Abstract:** In recent years, the widespread adoption of Large Language Models (LLMs) has sparked interest in their potential for application within the military domain. However, the current generation of LLMs demonstrate sub-optimal performance on Army use cases, due to the prevalence of domain-specific vocabulary and jargon. In order to fully leverage LLMs in-domain, many organizations have ...Votes: 0GitHub stars: 3
- Flow Matching In Context Brain DynamicsFlow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics methodology. First generative model of whole-cortex fMRI dynamics for unseen cognitive tasks. Per-timestep conditioned diffusion transformer with compositional language priors and spatial priors for counterfactual neuroscience.Votes: 0GitHub stars: 3
- Flow Matching In Context Priors Brain DynamicsFlow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics — per-timestep conditioned diffusion transformer for generating realistic fMRI brain dynamics during unseen cognitive tasks. Activation: flow matching, fMRI generation, counterfactual neuroscience, brain dynamics, diffusion transformer, in-context prior.Votes: 0GitHub stars: 3
- Fmri Mahalanobis Bures WhiteningDe-individualizing fMRI signals via Mahalanobis whitening and Bures geometry — methodology for distilling meaningful information from fMRI by treating data whitening as quantum-inspired state de-individualization using Bures distance.Votes: 0GitHub stars: 3
- Fmri Mahalanobis Bures WhiteningDe-individualizing fMRI signals via Mahalanobis whitening and Bures geometry — quantum-motivated dimensionality reduction for brain imagingVotes: 0GitHub stars: 3
- Fractional Quantum Information MemoryFractional quantum information methodology using Riemann-Liouville derivative formalism with memory effects. Covers quantum information measures in fractional quantum mechanics, generalized entropy measures, and non-Markovian dynamics.Votes: 0GitHub stars: 3
- Free Energy Rl InvestmentFree Energy-Entropy Duality methodology for risk-sensitive reinforcement learning in continuous-time investment management. Reformulates benchmarked asset allocation as a linear-quadratic-Gaussian stochastic differential game under an equivalent probability measure.Votes: 0GitHub stars: 3
- From English To More Languages Parameterefficient Model Reprogramming For Crosslingual Speech Recognition**arXiv ID:** 2301.07851 **Authors:** Chao-Han Huck Yang, Bo Li, Yu Zhang, Nanxin Chen, Rohit Prabhavalkar, Tara N. Sainath, Trevor Strohman **Published:** 2023-01-19T02:37:56Z **Abstract:** In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to recognize the other languages. We design different auxiliary neura...Votes: 0GitHub stars: 3
- Frozen Rate Operator ConnectomeConnectome rate operator analysis methodology — understanding how degree, weight govern gross response while exact wiring governs input routing. Use when analyzing complete connectomes, studying mushroom body function, or modeling neural network response properties.Votes: 0GitHub stars: 3
- Functional Connectomes Of Neural Networks**arXiv ID:** 2412.15279 **Authors:** Tananun Songdechakraiwut, Yutong Wu **Published:** 2024-12-18T03:46:30Z **Abstract:** The human brain is a complex system, and understanding its mechanisms has been a long-standing challenge in neuroscience. The study of the functional connectome, which maps the functional connections between different brain regions, has provided valuable insights through various advanced analysis techniques developed over the years. Similarly, neural networks, inspired b...Votes: 0GitHub stars: 3
- Functional Whole Brain Models FwbmFunctional Whole-Brain Models (fWBMs) - unified modeling paradigm integrating bottom-up whole-brain modeling with top-down neuroconnectionism. Defines 4 minimal criteria and 3-pillar roadmap for unifying brain structure and cognitive function. Based on arXiv:2605.18118 (May 2026). Use when studying whole-brain modeling, neural mass models, brain-inspired DNN architectures, connectome-based modeling, or cross-scale brain computation frameworks.Votes: 0GitHub stars: 3
- Gauge Field Fokker Planck DynamicsNonreversible gauge field methodology for Fokker-Planck dynamics — formulates stationary-density-preserving perturbations as gauge fields that deform relaxation spectra while leaving invariant state fixed. Connects supersymmetric Hamiltonians, non-Hermitian quantum mechanics, and neural network learning of finite forces.Votes: 0GitHub stars: 3
- Generative Quantum EmbeddingGenerative optimization framework for quantum data embeddings. Uses energy-based generative learning to synthesize gate sequences that optimize embedding structures, with fidelity-based surrogate objectives and Wasserstein-distance bounds for diagnosing when embedding optimization will be effective.Votes: 0GitHub stars: 3
- Globally Optimal Snn Parameter ReconstructionGlobally optimal Spiking Neural Network (SNN) training via parameter reconstruction. Extends convexification of parallel feedforward threshold networks to parallel recurrent threshold networks, subsuming parallel SNNs as a structured special case. Eliminates surrogate gradient approximation errors by reconstructing optimal parameters directly. Use when training SNNs, optimizing spiking networks, avoiding surrogate gradient issues, or exploring convex SNN training methods. arXiv: 2605.08022Votes: 0GitHub stars: 3
- Globally Optimal Snn Parameter ReconstructionGlobally optimal Spiking Neural Network (SNN) training via parameter reconstruction methodology. Extends convexification of parallel feedforward threshold networks to parallel recurrent threshold networks, enabling parameter reconstruction algorithm that avoids surrogate gradient approximation errors. Applicable to SNN training, optimization, energy-efficient neural networks. Triggers: SNN training, surrogate gradient, spiking neural network optimization, convex training, globally optimal SNN.Votes: 0GitHub stars: 3
- Graft Neural Population AdapterGRAFT methodology for Transformer-based neural population activity modeling with gain-recalibrated adapters enabling cross-day BCI recalibrationVotes: 0GitHub stars: 3
- Graft Neural Population Transformer RecalibrationGRAFT: Transformer-based neural population activity model with gain-recalibrated adapters for cross-day BCI recalibration. Separates reusable temporal dynamics from recalibratable neuron interface. Achieves state-of-the-art 0.3866 co-bps on NLB'21 MC Maze. Recalibrates to new datasets by updating only 9.21% of parameters. Supports data-efficient cross-day generalization in brain-computer interfaces.Votes: 0GitHub stars: 3
- Graph Regularized Eeg Emotion RecognitionGraph-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 classifiers, affective BCI systems, or applying graph regularization to psychological classification tasks.Votes: 0GitHub stars: 3
- Grid Cells Reduce Spatial Aliasing Hippocampal PlaceGrid cells reduce spatial aliasing in place representations.Votes: 0GitHub stars: 3
- Hard Core Boson Quantum Circuit SynthesisHard-core boson algebra for efficient quantum circuit simulation and synthesis. Provides natural representation of multi-qubit systems without sign corrections, with substantially improved execution times over IBM Qiskit, combined with genetic algorithms for circuit synthesis.Votes: 0GitHub stars: 3
- Hcq Alzheimer Classification Vae Quantum KernelsHybrid Classical-Quantum pipeline for Alzheimer's classification using supervised β-VAE and quantum kernels (arXiv:2606.14194)Votes: 0GitHub stars: 3
- Hcq Alzheimer Quantum ClassificationHybrid Classical-Quantum pipeline for Alzheimer's classification — supervised β-VAE + quantum kernels + quantum feature mapsVotes: 0GitHub stars: 3
- Hdcnn Hierarchical Deep Convolutional Neural Network For Large Scale Visual Recognition**arXiv ID:** 1410.0736 **Authors:** Zhicheng Yan, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis DeCoste, Wei Di, Yizhou Yu **Published:** 2014-10-03T01:17:20Z **Abstract:** In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way ...Votes: 0GitHub stars: 3
- Heterogeneous Neural Predictivity LmAnalysis framework for evaluating language model neural predictivity during naturalistic comprehension. Identifies heterogeneous brain-language alignment patterns across participants and brain regions, separating predictive usefulness from shared neural organization claims (arXiv: 2606.26880)Votes: 0GitHub stars: 3
- Hierarchical Residuals Exploit Braininspired Compositionality**arXiv ID:** 2502.16003 **Authors:** Francisco M. López, Jochen Triesch **Published:** 2025-02-21T23:35:08Z **Abstract:** We present Hierarchical Residual Networks (HiResNets), deep convolutional neural networks with long-range residual connections between layers at different hierarchical levels. HiResNets draw inspiration on the organization of the mammalian brain by replicating the direct connections from subcortical areas to the entire cortical hierarchy. We show that the inclusion of hie...Votes: 0GitHub stars: 3
- Hierarchical Temporal Receptive Windows And Zeroshot Timescale Generalization In Biologically Constrained Scaleinvariant Deep Networks**arXiv ID:** 2601.02618 **Authors:** Aakash Sarkar, Marc W. Howard **Published:** 2026-01-06T00:36:45Z **Abstract:** Human cognition integrates information across nested timescales. While the cortex exhibits hierarchical Temporal Receptive Windows (TRWs), local circuits often display heterogeneous time constants. To reconcile this, we trained biologically constrained deep networks, based on scale-invariant hippocampal time cells, on a language classification task mimicking the hierarchical s...Votes: 0GitHub stars: 3
- Highway Long Shortterm Memory Rnns For Distant Speech Recognition**arXiv ID:** 1510.08983 **Authors:** Yu Zhang, Guoguo Chen, Dong Yu, Kaisheng Yao, Sanjeev Khudanpur, James Glass **Published:** 2015-10-30T06:40:14Z **Abstract:** In this paper, we extend the deep long short-term memory (DLSTM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers. These direct links, called highway connections, enable unimpeded information flow across different layers and thus alleviate the gradient vanishing problem when...Votes: 0GitHub stars: 3
- Hot State Displacement SensingQuantum-enhanced displacement sensing using hot (thermal) quantum states without mandatory ground-state cooling. Identifies parity-selection and coherence mechanisms for maintaining sensitivity with mixed states, and formulates optimization comparing cooling vs direct hot-state preparation under decoherence. (arXiv: 2606.13650)Votes: 0GitHub stars: 3
- How Multimodal Integration Boost The Performance Of Llm For Optimization Case Study On Capacitated Vehicle Routing Problems**arXiv ID:** 2403.01757 **Authors:** Yuxiao Huang, Wenjie Zhang, Liang Feng, Xingyu Wu, Kay Chen Tan **Published:** 2024-03-04T06:24:21Z **Abstract:** Recently, large language models (LLMs) have notably positioned them as capable tools for addressing complex optimization challenges. Despite this recognition, a predominant limitation of existing LLM-based optimization methods is their struggle to capture the relationships among decision variables when relying exclusively on numerical text pro...Votes: 0GitHub stars: 3
- Htann Ann Cann HybridizationFirst theory-grounded framework for population-scale ANN-CANN hybridization, discovering functional bias-variance complementarity for stable visual object trackingVotes: 0GitHub stars: 3
- Humainsjunior A 38b Language Model Achieving Gpt4olevel Factual Accuracy By Directed Exoskeleton Reasoning**arXiv ID:** 2510.25933 **Authors:** Nissan Yaron, Dan Bystritsky, Ben-Etzion Yaron **Published:** 2025-10-29T20:12:36Z **Abstract:** We introduce Humans-Junior, a 3.8B model that matches GPT-4o on the FACTS Grounding public subset within a $\pm 5$ pp equivalence margin. Results. On Q1--Q500 under identical judges, GPT-4o scores 73.5% (95% CI 69.5--77.2) and Humans-Junior 72.7% (95% CI 68.7--76.5); the paired difference is 0.8 pp (bootstrap 95% CI $-3.1$ to $+4.7$; permutation $p = 0.72$; Co...Votes: 0GitHub stars: 3
- Human Ai Agent Interaction As A Neuroplastic TrainHuman-AI Agent Interaction as a Neuroplastic Training Environment - Interaction with AI agents has become one of the most frequent activities of everyday digital life. Whether conversing with an assistant, working with...Votes: 0GitHub stars: 3
- Hybrid Biophysical Neuron Neural OdeHybrid biophysical neuron modeling combining Neural ODEs with conductance-based models. Embeds data-driven Neural ODE components into mechanistic neuron models, capturing unknown ion channel kinetics while preserving interpretability. Enables 10x computational reduction of multi-compartment neurons.Votes: 0GitHub stars: 3
- Hybrid Quantum Classical Topological Phase RecognitionHybrid quantum-classical neural network architecture for sample-efficient topological phase recognition. Uses shallow parameterized quantum circuits for nonlocal measurement basis transformation, jointly trained with classical neural networks, reducing sample complexity by ~10x.Votes: 0GitHub stars: 3
- Hybrid Quantum Neural Phase RecognitionHybrid quantum-classical neural network for quantum phase recognition - jointly trains shallow parameterized quantum circuit with classical neural network, reduces sample complexity by ~10x, distinguishes topological phases on superconducting hardwareVotes: 0GitHub stars: 3
- Hyperbolic Learning Brain GraphsHyperbolic Learning on Brain Graphs (HLBG) methodology for brain disorder diagnosis. Exploits hierarchical geometry of hyperbolic space to model ROI→community→whole-brain relationships.Votes: 0GitHub stars: 3
- Hyperbolic Neural Population Geometry ComputationHyperbolic geometry framework for neural population activity in hippocampus. Modern Hopfield Network computes MMSE estimator, hyperbolic associative memory yields larger capacity than Euclidean models. ICML 2026 paper. Activation: hyperbolic geometry, neural population, hippocampus, associative memory, Hopfield network, spatial navigation, cognitive map, memory capacity, MMSE estimator.Votes: 0GitHub stars: 3
- Ia Qcn Ring GlioblastomaImportance-Aware Quantum Convolutional Neural Network (IA-QCNN) with ring-topology for MGMT promoter methylation prediction in glioblastoma. Specialized quantum CNN architecture for medical biomarker prediction.Votes: 0GitHub stars: 3
- Identity Trap Eeg Foundation ModelsEEG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。Votes: 0GitHub stars: 3
- Inducing Functions Through Reinforcement Learning Without Task Specification**arXiv ID:** 2111.11647 **Authors:** Junmo Cho, Dong-Hwan Lee, Young-Gyu Yoon **Published:** 2021-11-23T04:42:02Z **Abstract:** We report a bio-inspired framework for training a neural network through reinforcement learning to induce high level functions within the network. Based on the interpretation that animals have gained their cognitive functions such as object recognition - without ever being specifically trained for - as a result of maximizing their fitness to the environment, we plac...Votes: 0GitHub stars: 3
- Intrinsic Noise Consolidation DoobDoob h-transform barrier-conditioned diffusion for continual learning on analog neuromorphic hardware. Converts intrinsic device noise from accuracy tax to consolidation dividend. Activation: Doob h-transform, barrier conditioning, analog noise, neuromorphic continual learning, BrainScaleS-2, intrinsic noise consolidation, inverted-U retentionVotes: 0GitHub stars: 3
- Iqp Circuit TrainabilityIQP (Instantaneous Quantum Polynomial-time) circuit methodology for near-term quantum optimization. Use when: designing IQP circuits for Hamiltonian optimization, analyzing connectivity-trainability trade-offs in variational quantum circuits, selecting circuit architectures for NISQ-era optimization, understanding how IQP circuit depth/structure affects optimization performance vs trainability (barren plateaus), implementing penalty-free quantum optimization workflows. Core insight: IQP circu...Votes: 0GitHub stars: 3