All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Evolutionary Echo State Network Evolving Reservoirs In The Fourier Space**arXiv ID:** 2206.04951 **Authors:** Sebastian Basterrech, Gerardo Rubino **Published:** 2022-06-10T08:59:40Z **Abstract:** The Echo State Network (ESN) is a class of Recurrent Neural Network with a large number of hidden-hidden weights (in the so-called reservoir). Canonical ESN and its variations have recently received significant attention due to their remarkable success in the modeling of non-linear dynamical systems. The reservoir is randomly connected with fixed weights that don't chan...Votes: 0GitHub stars: 3
- Evolutionary Hyperparameter Optimization To Find LDerived from arXiv:2606.29684 - Evolutionary Hyperparameter Optimization to Find Lightweight CNN Models for Autonomous SteeringVotes: 0GitHub stars: 3
- Evolutionary Multiobjective Fusion Of Deepfake Speech Detectors**arXiv ID:** 2604.01330 **Authors:** Vojtěch Staněk, Martin Perešíni, Lukáš Sekanina, Anton Firc, Kamil Malinka **Published:** 2026-04-01T19:17:59Z **Abstract:** While deepfake speech detectors built on large self-supervised learning (SSL) models achieve high accuracy, employing standard ensemble fusion to further enhance robustness often results in oversized systems with diminishing returns. To address this, we propose an evolutionary multi-objective score fusion framework that jointly mini...Votes: 0GitHub stars: 3
- Experiments On Properties Of Hidden Structures Of Sparse Neural Networks**arXiv ID:** 2107.12917 **Authors:** Julian Stier, Harshil Darji, Michael Granitzer **Published:** 2021-07-27T16:18:13Z **Abstract:** Sparsity in the structure of Neural Networks can lead to less energy consumption, less memory usage, faster computation times on convenient hardware, and automated machine learning. If sparsity gives rise to certain kinds of structure, it can explain automatically obtained features during learning. We provide insights into experiments in which we show how spar...Votes: 0GitHub stars: 3
- Faithful And Accurate Selfattention Attribution For Message Passing Neural Networks Via The Computation Tree Viewpoint**arXiv ID:** 2406.04612 **Authors:** Yong-Min Shin, Siqing Li, Xin Cao, Won-Yong Shin **Published:** 2024-06-07T03:40:15Z **Abstract:** The self-attention mechanism has been adopted in various popular message passing neural networks (MPNNs), enabling the model to adaptively control the amount of information that flows along the edges of the underlying graph. Such attention-based MPNNs (Att-GNNs) have also been used as a baseline for multiple studies on explainable AI (XAI) since attention ha...Votes: 0GitHub stars: 3
- Fast And Efficient Local Search For Genetic Programming Based Loss Function Learning**arXiv ID:** 2403.00865 **Authors:** Christian Raymond, Qi Chen, Bing Xue, Mengjie Zhang **Published:** 2024-03-01T02:20:04Z **Abstract:** In this paper, we develop upon the topic of loss function learning, an emergent meta-learning paradigm that aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning framework for task and model-agnostic loss function learning via a hybrid search approach. The fra...Votes: 0GitHub stars: 3
- Feature Learning In L2regularized Dnns Attractionrepulsion And Sparsity**arXiv ID:** 2205.15809 **Authors:** Arthur Jacot, Eugene Golikov, Clément Hongler, Franck Gabriel **Published:** 2022-05-31T14:10:15Z **Abstract:** We study the loss surface of DNNs with $L_{2}$ regularization. We show that the loss in terms of the parameters can be reformulated into a loss in terms of the layerwise activations $Z_{\ell}$ of the training set. This reformulation reveals the dynamics behind feature learning: each hidden representations $Z_{\ell}$ are optimal w.r.t. to an attr...Votes: 0GitHub stars: 3
- Feedback Augmented Self Distillation Fail Improve Retrieval Interleaved Search AgentsSkill derived from arXiv:2607.17558 - Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?Votes: 0GitHub stars: 3
- Filtered Batch Normalization**arXiv ID:** 2010.08251 **Authors:** Andras Horvath, Jalal Al-afandi **Published:** 2020-10-16T08:56:57Z **Abstract:** It is a common assumption that the activation of different layers in neural networks follow Gaussian distribution. This distribution can be transformed using normalization techniques, such as batch-normalization, increasing convergence speed and improving accuracy. In this paper we would like to demonstrate, that activations do not necessarily follow Gaussian distribution in...Votes: 0GitHub stars: 3
- Forgetfree Continual Learning With Softwinning Subnetworks**arXiv ID:** 2303.14962 **Authors:** Haeyong Kang, Jaehong Yoon, Sultan Rizky Madjid, Sung Ju Hwang, Chang D. Yoo **Published:** 2023-03-27T07:53:23Z **Abstract:** Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which states that competitive smooth (non-binary) subnetworks exist within a dense network in continual learning tasks, we investigate two proposed architecture-based continual learning methods which sequentially learn and select adaptive binary- (WSN) and non-binary Soft-S...Votes: 0GitHub stars: 3
- Frozen Lgp QaoaFrozenLGP adaptive decomposition framework for divide-and-conquer QAOA. Transforms partitionability from an assumption into an enforceable property by freezing obstructing vertices and folding their energy into linear bias terms. Enables 100% decomposition coverage on graphs up to 10,000 vertices including dense/high-connectivity instances. Activation: FrozenLGP, divide-and-conquer QAOA, qubit freezing, graph partitioning QAOA, adaptive decomposition, max-flow vertex cut, dense graph QAOAVotes: 0GitHub stars: 3
- Gamr A Guided Attention Model For Visual Reasoning**arXiv ID:** 2206.04928 **Authors:** Mohit Vaishnav, Thomas Serre **Published:** 2022-06-10T07:52:06Z **Abstract:** Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes. Here, we present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR), which instantiates an active vision theory -- positing that the brain solves complex visual reasoning problems dynamically -- via sequences of atte...Votes: 0GitHub stars: 3
- Gaussian Mean Width Identification CapacitySingle-letter efficiently computable strong converse bound on classical identification capacity of quantum channels via Gaussian mean width analysisVotes: 0GitHub stars: 3
- Gc Opd Group Calibrated On Policy DistillationGroup-Calibrated On-Policy Distillation (GC-OPD) for long-context reasoning that combines verifier rewards with token-level teacher guidance. Use when training students on long-context evidence-aggregation tasks where global task constraints matter.Votes: 0GitHub stars: 3
- Generalization Bounds For Deep Convolutional Neural Networks**arXiv ID:** 1905.12600 **Authors:** Philip M. Long, Hanie Sedghi **Published:** 2019-05-29T17:20:36Z **Abstract:** We prove bounds on the generalization error of convolutional networks. The bounds are in terms of the training loss, the number of parameters, the Lipschitz constant of the loss and the distance from the weights to the initial weights. They are independent of the number of pixels in the input, and the height and width of hidden feature maps. We present experiments using CIFAR-1...Votes: 0GitHub stars: 3
- Generalpurpose Incontext Learning By Metalearning Transformers**arXiv ID:** 2212.04458 **Authors:** Louis Kirsch, James Harrison, Jascha Sohl-Dickstein, Luke Metz **Published:** 2022-12-08T18:30:22Z **Abstract:** Modern machine learning requires system designers to specify aspects of the learning pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn, instead aims to learn those aspects, and promises to unlock greater capabilities with less manual effort. One particularly ambitious goal of meta-learning is to train ...Votes: 0GitHub stars: 3
- Generate More Than One Child In Your Coevolutionary Semisupervised Learning Gan**arXiv ID:** 2504.20560 **Authors:** Francisco Sedeño, Jamal Toutouh, Francisco Chicano **Published:** 2025-04-29T09:04:22Z **Abstract:** Generative Adversarial Networks (GANs) are very useful methods to address semi-supervised learning (SSL) datasets, thanks to their ability to generate samples similar to real data. This approach, called SSL-GAN has attracted many researchers in the last decade. Evolutionary algorithms have been used to guide the evolution and training of SSL-GANs with grea...Votes: 0GitHub stars: 3
- Generating Images From Caption And Vice Versa Via Clipguided Generative Latent Space Search**arXiv ID:** 2102.01645 **Authors:** Federico A. Galatolo, Mario G. C. A. Cimino, Gigliola Vaglini **Published:** 2021-02-02T18:00:13Z **Abstract:** In this research work we present CLIP-GLaSS, a novel zero-shot framework to generate an image (or a caption) corresponding to a given caption (or image). CLIP-GLaSS is based on the CLIP neural network, which, given an image and a descriptive caption, provides similar embeddings. Differently, CLIP-GLaSS takes a caption (or an image) as an input, ...Votes: 0GitHub stars: 3
- Generative Classifiers Avoid Shortcut Solutions**arXiv ID:** 2512.25034 **Authors:** Alexander C. Li, Ananya Kumar, Deepak Pathak **Published:** 2025-12-31T18:31:46Z **Abstract:** Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the label. We show that generative classifiers, which use class-conditional generative models, can avoid this issue by modeling all f...Votes: 0GitHub stars: 3
- Genetic Algorithm Gradient Descent Debi NnGenetic algorithm vs. gradient descent comparison for training distance-encoding biomorphic neural networks (DEBI-NN) in low-data medical regimesVotes: 0GitHub stars: 3
- Geosd Geometric Self DistillationGeometric Self-Distillation (GeoSD) methodology for preserving OOD generalization during privileged-context self-distillation. Uses Hellinger loss and Fisher-Rao proximal term to prevent drift in predictive behavior.Votes: 0GitHub stars: 3
- Gradientbased Design Of Computational Granular Crystals**arXiv ID:** 2404.04825 **Authors:** Atoosa Parsa, Corey S. O'Hern, Rebecca Kramer-Bottiglio, Josh Bongard **Published:** 2024-04-07T06:24:47Z **Abstract:** There is growing interest in engineering unconventional computing devices that leverage the intrinsic dynamics of physical substrates to perform fast and energy-efficient computations. Granular metamaterials are one such substrate that has emerged as a promising platform for building wave-based information processing devices with the pot...Votes: 0GitHub stars: 3
- Gram Gradient Routed Auxiliary ModulesGRAM (Gradient-Routed Auxiliary Modules) methodology for creating removable compartments for dual-use knowledge in AI models. Enables surgical control over model capabilities without affecting general performance.Votes: 0GitHub stars: 3
- Graphbench Nextgeneration Graph Learning Benchmarking**arXiv ID:** 2512.04475 **Authors:** Timo Stoll, Chendi Qian, Ben Finkelshtein, Ali Parviz, Darius Weber, Fabrizio Frasca, Hadar Shavit, Antoine Siraudin, Arman Mielke, Marie Anastacio, Erik Müller, Maya Bechler-Speicher, Michael Bronstein, Mikhail Galkin, Holger Hoos, Mathias Niepert, Bryan Perozzi, Jan Tönshoff, Christopher Morris **Published:** 2025-12-04T05:30:31Z **Abstract:** Machine learning on graphs has made substantial progress across domains such as molecular property prediction a...Votes: 0GitHub stars: 3
- Grasp Force Optimization As A Bilinear Matrix Inequality Problem A Deep Learning Approach**arXiv ID:** 2312.05034 **Authors:** Hirakjyoti Basumatary, Daksh Adhar, Riddhiman Shaw, Shyamanta M. Hazarika **Published:** 2023-12-08T13:28:21Z **Abstract:** Grasp force synthesis is a non-convex optimization problem involving constraints that are bilinear. Traditional approaches to this problem involve general-purpose gradient-based nonlinear optimization and semi-definite programming. With a view towards dealing with postural synergies and non-smooth but convex positive semidefinite con...Votes: 0GitHub stars: 3
- Group Intervention Causal Discovery SubsystemsGroup intervention-based causal discovery for identifying causal structure in deep neural network subsystems — extending causal discovery from single neurons to functional subnetwork groups. Activation: causal discovery, deep network, subsystem, group intervention, causal structure, neural circuit, interpretability, interventional causality.Votes: 0GitHub stars: 3
- Growing Neural Network Breadth Depth TimeDifferentiable cost framework for jointly optimizing neural network architecture (breadth/width, depth/layers, temporal recurrence) alongside task performance. Bio-inspired growth principle enabling networks to autonomously develop architectures matching task complexity — mimicking biological neural development.Votes: 0GitHub stars: 3
- Guided Evolutionary Neural Architecture Search With Efficient Performance Estimation**arXiv ID:** 2208.06475 **Authors:** Vasco Lopes, Miguel Santos, Bruno Degardin, Luís A. Alexandre **Published:** 2022-07-22T10:58:32Z **Abstract:** Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures seem to yield good results. This paper proposes GEA, a novel approach for guided NAS. GEA guides the evolution by exploring t...Votes: 0GitHub stars: 3
- H2sd Hybrid Hindsight Self DistillationHybrid Hindsight Self-Distillation for Reinforcement Learning with Verifiable RewardsVotes: 0GitHub stars: 3
- Headcast Attention Heads Video GenerationHeadCast methodology for efficient autoregressive video generation through training-free attention head classification and KV cache optimization.Votes: 0GitHub stars: 3
- Hebbian Fast Weights VitHebbian Fast-Weight (HFW) modules integrated into Vision Transformer architectures for few-shot learning. Activation triggers: hebbian fast weights, hebbian ViT, fast synaptic updates, transformer meta-learning, few-shot transformer, hebbian plasticity vision, swin hebbian, prototypical network hebbian, rapid adaptation transformer.Votes: 0GitHub stars: 3
- Hebbian Memoryaugmented Recurrent Networks Engram Neurons In Deep Learning**arXiv ID:** 2507.21474 **Authors:** Daniel Szelogowski **Published:** 2025-07-29T03:34:32Z **Abstract:** Despite success across diverse tasks, current artificial recurrent network architectures rely primarily on implicit hidden-state memories, limiting their interpretability and ability to model long-range dependencies. In contrast, biological neural systems employ explicit, associative memory traces (i.e., engrams) strengthened through Hebbian synaptic plasticity and activated sparsely dur...Votes: 0GitHub stars: 3
- Hes Data Selection ReasoningHES (High-Entropy Sum) methodology from arXiv:2605.22389 (May 2026). Training-free metric for LLM reasoning data selection: sums entropy of top-k highest-entropy tokens per reasoning sample. Effective across SFT, RFT, and RL training paradigms. Use when: LLM reasoning data curation, data quality filtering, rejection sampling for reasoning, RL training data selection, long-CoT data filtering.Votes: 0GitHub stars: 3
- Hiracam Preserving Finegrained Spatial Relevance In Gradientbased Visual Explanations**arXiv ID:** 2608.19407 **Authors:** Manasi Nerurkar, Ali A. Minai **Published:** 2026-08-19T19:44:43Z **Abstract:** Deep Learning models can include billions of parameters or more, making it difficult to explain their internal transformations and outputs. However, explainability is increasing in importance due to the use of AI in crucial applications. This paper focuses on the interpretability of convolutional neural networks (CNNs). Building on the popular gradient based method LayerCAM fo...Votes: 0GitHub stars: 3
- Hopfield Temporal Complexity**来源论文：** arXiv:2406.12895 - Temporal Complexity of a Hopfield-Type Neural Model in Random and Scale-Free GraphsVotes: 0GitHub stars: 3
- How To Dodge Complex Software Analytics**arXiv ID:** 1902.01838 **Authors:** Amritanshu Agrawal, Wei Fu, Di Chen, Xipeng Shen, Tim Menzies **Published:** 2019-02-05T18:16:56Z **Abstract:** Machine learning techniques applied to software engineering tasks can be improved by hyperparameter optimization, i.e., automatic tools that find good settings for a learner's control parameters. We show that such hyperparameter optimization can be unnecessarily slow, particularly when the optimizers waste time exploring "redundant tunings"', i....Votes: 0GitHub stars: 3
- Hybrid Neural Network Visual TrackingSkill for implementing and understanding the theory-grounded hybrid neural network (HTNN) that integrates artificial neural networks (ANNs) with continuous attractor neural networks (CANNs) for stable visual object tracking, as proposed in arXiv:2606.22604.Votes: 0GitHub stars: 3
- Hydrofusionlmf Semisupervised Multinetwork Fusion With Largemodel Adaptation For Longterm Daily Runoff Forecasting**arXiv ID:** 2510.03744 **Authors:** Qianfei Fan, Jiayu Wei, Peijun Zhu, Wensheng Ye, Meie Fang **Published:** 2025-10-04T09:09:06Z **Abstract:** Accurate decade-scale daily runoff forecasting in small watersheds is difficult because signals blend drifting trends, multi-scale seasonal cycles, regime shifts, and sparse extremes. Prior deep models (DLinear, TimesNet, PatchTST, TiDE, Nonstationary Transformer, LSTNet, LSTM) usually target single facets and under-utilize unlabeled spans, limitin...Votes: 0GitHub stars: 3
- Hypergeometric High Precision EvaluationMethodology for high-precision numerical evaluation of multivariate hypergeometric functions using Pfaffian systems and contour restriction. Applicable to quantum field theory, string theory, number theory, and statistics computations.Votes: 0GitHub stars: 3
- Hypergraph Neural Stochastic Diffusion An Sde Framework For UncertaintyHypergraph neural networks have shown powerful capability in modeling higher-order relations, yet their predictive uncertainty remains underexplored. Unlike pairwise graphs, uncertainty in hypergraphs. Based on arXiv:2607.07330.Votes: 0GitHub stars: 3
- Ice ReviewICE review workflow for consolidating knowledge from completed tasks into reusable memory and future leverage.Votes: 0GitHub stars: 3
- Iceberg Error DetectionFault-tolerant error detection using the Iceberg [[2m, 2m-2, 2]] quantum error-detecting code. Implements beyond-break-even error detection for multi-qubit gates on trapped-ion quantum computers. Keywords: quantum error detection, Iceberg code, fault-tolerant, trapped-ion, multi-qubit gates, Toffoli, Bell state, error correction.Votes: 0GitHub stars: 3
- Implicit Regularization In Tensor Factorization**arXiv ID:** 2102.09972 **Authors:** Noam Razin, Asaf Maman, Nadav Cohen **Published:** 2021-02-19T15:10:26Z **Abstract:** Recent efforts to unravel the mystery of implicit regularization in deep learning have led to a theoretical focus on matrix factorization -- matrix completion via linear neural network. As a step further towards practical deep learning, we provide the first theoretical analysis of implicit regularization in tensor factorization -- tensor completion via certain type of no...Votes: 0GitHub stars: 3
- Implicit Regularization With Polynomial Growth In Deep Tensor Factorization**arXiv ID:** 2207.08942 **Authors:** Kais Hariz, Hachem Kadri, Stéphane Ayache, Maher Moakher, Thierry Artières **Published:** 2022-07-18T21:04:37Z **Abstract:** We study the implicit regularization effects of deep learning in tensor factorization. While implicit regularization in deep matrix and 'shallow' tensor factorization via linear and certain type of non-linear neural networks promotes low-rank solutions with at most quadratic growth, we show that its effect in deep tensor factorizati...Votes: 0GitHub stars: 3
- Implicit Variance Regularization In Noncontrastive Ssl**arXiv ID:** 2212.04858 **Authors:** Manu Srinath Halvagal, Axel Laborieux, Friedemann Zenke **Published:** 2022-12-09T13:56:42Z **Abstract:** Non-contrastive SSL methods like BYOL and SimSiam rely on asymmetric predictor networks to avoid representational collapse without negative samples. Yet, how predictor networks facilitate stable learning is not fully understood. While previous theoretical analyses assumed Euclidean losses, most practical implementations rely on cosine similarity. To g...Votes: 0GitHub stars: 3
- Improving Expert Specialization In Mixture Of Experts**arXiv ID:** 2302.14703 **Authors:** Yamuna Krishnamurthy, Chris Watkins, Thomas Gaertner **Published:** 2023-02-28T16:16:45Z **Abstract:** Mixture of experts (MoE), introduced over 20 years ago, is the simplest gated modular neural network architecture. There is renewed interest in MoE because the conditional computation allows only parts of the network to be used during each inference, as was recently demonstrated in large scale natural language processing models. MoE is also of potential ...Votes: 0GitHub stars: 3
- Improving The Performance Of Neural Networks In Regression Tasks Using Drawering**arXiv ID:** 1612.01589 **Authors:** Konrad Zolna **Published:** 2016-12-05T23:28:54Z **Abstract:** The method presented extends a given regression neural network to make its performance improve. The modification affects the learning procedure only, hence the extension may be easily omitted during evaluation without any change in prediction. It means that the modified model may be evaluated as quickly as the original one but tends to perform better. This improvement is possible because the m...Votes: 0GitHub stars: 3
- Inducing Semistructured Sparsity By Masking For Efficient Model Inference In Convolutional Networks**arXiv ID:** 2411.00288 **Authors:** David A. Danhofer **Published:** 2024-11-01T00:53:33Z **Abstract:** The crucial role of convolutional models, both as standalone vision models and backbones in foundation models, necessitates effective acceleration techniques. This paper proposes a novel method to learn semi-structured sparsity patterns for convolution kernels in the form of maskings enabling the utilization of readily available hardware accelerations. The approach accelerates convolution...Votes: 0GitHub stars: 3
- Infrastructure For Deep LearningSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Instance Generation For Metablackbox Optimization Through Latent Space Reverse Engineering**arXiv ID:** 2509.15810 **Authors:** Chen Wang, Yue-Jiao Gong, Zhiguang Cao, Zeyuan Ma **Published:** 2025-09-19T09:37:48Z **Abstract:** To relieve intensive human-expertise required to design optimization algorithms, recent Meta-Black-Box Optimization (MetaBBO) researches leverage generalization strength of meta-learning to train neural network-based algorithm design policies over a predefined training problem set, which automates the adaptability of the low-level optimizers on unseen probl...Votes: 0GitHub stars: 3