All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Coherence Law Noisy Equivariant QnnCoherence law for trainability in noisy equivariant quantum neural networks. Proves that readout-visible sector coherence determines gradient survival under decoherence, not just symmetry structure.Votes: 0GitHub stars: 3
- Collaborative Interactive Evolution Of Art In The Latent Space Of Deep Generative Models**arXiv ID:** 2403.19620 **Authors:** Ole Hall, Anil Yaman **Published:** 2024-03-28T17:40:15Z **Abstract:** Generative Adversarial Networks (GANs) have shown great success in generating high quality images and are thus used as one of the main approaches to generate art images. However, usually the image generation process involves sampling from the latent space of the learned art representations, allowing little control over the output. In this work, we first employ GANs that are trained to ...Votes: 0GitHub stars: 3
- Collaborative Storytelling With Largescale Neural Language Models**arXiv ID:** 2011.10208 **Authors:** Eric Nichols, Leo Gao, Randy Gomez **Published:** 2020-11-20T04:36:54Z **Abstract:** Storytelling plays a central role in human socializing and entertainment. However, much of the research on automatic storytelling generation assumes that stories will be generated by an agent without any human interaction. In this paper, we introduce the task of collaborative storytelling, where an artificial intelligence agent and a person collaborate to create a unique ...Votes: 0GitHub stars: 3
- Color Code Pipe DiagramsLattice surgery compilation methodology for color codes using pipe diagrams — extends surface-code pipe diagram framework to triangular color codes on 6.6.6 lattice. Enables distance-independent spacetime optimization, correlation surface realization, and automated compilation to syndrome extraction circuits.Votes: 0GitHub stars: 3
- Combining Modelfree Qensembles And Modelbased Approaches For Informed Exploration**arXiv ID:** 1806.04552 **Authors:** Sreecharan Sankaranarayanan, Raghuram Mandyam Annasamy, Katia Sycara, Carolyn Penstein Rosé **Published:** 2018-06-12T14:24:02Z **Abstract:** Q-Ensembles are a model-free approach where input images are fed into different Q-networks and exploration is driven by the assumption that uncertainty is proportional to the variance of the output Q-values obtained. They have been shown to perform relatively well compared to other exploration strategies. Further, m...Votes: 0GitHub stars: 3
- Compact Latent Coordination For Autonomous Vehicles At Unsignalized 1Compact Latent Coordination for Autonomous Vehicles at Unsignalized IntersectionsVotes: 0GitHub stars: 3
- Compact Latent Coordination For Autonomous Vehicles At UnsignalizedCompact Latent Coordination for Autonomous Vehicles at Unsignalized IntersectionsVotes: 0GitHub stars: 3
- Comparing Heterogeneous Entities Using Artificial Neural Networks Of Trainable Weighted Structural Components And Machinelearned Activation Functions**arXiv ID:** 1801.03143 **Authors:** Artit Wangperawong, Kettip Kriangchaivech, Austin Lanari, Supui Lam, Panthong Wangperawong **Published:** 2018-01-09T21:20:08Z **Abstract:** To compare entities of differing types and structural components, the artificial neural network paradigm was used to cross-compare structural components between heterogeneous documents. Trainable weighted structural components were input into machine-learned activation functions of the neurons. The model was used for...Votes: 0GitHub stars: 3
- Competitive Complementary ToolsThis skill implements the methodology from arXiv:2607.18460 "Competitive and Complementary Tools". The framework models the co-evolution of human competence and AI tool reliance as a bistable dynamical system, analyzing critical thresholds for competence collapse and agency transfer between humans and AI systems.Votes: 0GitHub stars: 3
- Compound Pulse Gadget SynthesisHolistic pulse synthesis methodology for quantum algorithms that bypasses discrete gate-stitching to compile algorithms directly into continuous compound pulse gadgets. Use when optimizing quantum circuits for trapped-ion or superconducting hardware, reducing gate overhead, minimizing decoherence exposure, or compiling QSVT/Hamiltonian simulation algorithms. Activation: compound pulse gadgets, GRAPE pulse engineering, holistic pulse synthesis, continuous pulse compilation, QSVT block-encoding...Votes: 0GitHub stars: 3
- Computational And Storage Efficient Quadratic Neurons For Deep Neural Networks**arXiv ID:** 2306.07294 **Authors:** Chuangtao Chen, Grace Li Zhang, Xunzhao Yin, Cheng Zhuo, Ulf Schlichtmann, Bing Li **Published:** 2023-06-10T11:25:31Z **Abstract:** Deep neural networks (DNNs) have been widely deployed across diverse domains such as computer vision and natural language processing. However, the impressive accomplishments of DNNs have been realized alongside extensive computational demands, thereby impeding their applicability on resource-constrained devices. To address t...Votes: 0GitHub stars: 3
- Concentric Esn Assessing The Effect Of Modularity In Cycle Reservoirs**arXiv ID:** 1805.09244 **Authors:** Davide Bacciu, Andrea Bongiorno **Published:** 2018-05-23T15:58:57Z **Abstract:** The paper introduces concentric Echo State Network, an approach to design reservoir topologies that tries to bridge the gap between deterministically constructed simple cycle models and deep reservoir computing approaches. We show how to modularize the reservoir into simple unidirectional and concentric cycles with pairwise bidirectional jump connections between adjacent loo...Votes: 0GitHub stars: 3
- Concept Probing Where To Find Humandefined Concepts Extended Version**arXiv ID:** 2507.18681 **Authors:** Manuel de Sousa Ribeiro, Afonso Leote, João Leite **Published:** 2025-07-24T16:30:10Z **Abstract:** Concept probing has recently gained popularity as a way for humans to peek into what is encoded within artificial neural networks. In concept probing, additional classifiers are trained to map the internal representations of a model into human-defined concepts of interest. However, the performance of these probes is highly dependent on the internal represen...Votes: 0GitHub stars: 3
- Conditional Morphogenesis Emergent Generation Of Structural Digits Via Neural Cellular Automata**arXiv ID:** 2512.08360 **Authors:** Ali Sakour **Published:** 2025-12-09T08:36:54Z **Abstract:** Biological systems exhibit remarkable morphogenetic plasticity, where a single genome can encode various specialized cellular structures triggered by local chemical signals. In the domain of Deep Learning, Differentiable Neural Cellular Automata (NCA) have emerged as a paradigm to mimic this self-organization. However, existing NCA research has predominantly focused on continuous texture synthes...Votes: 0GitHub stars: 3
- Confidence Threshold Neural Diving**arXiv ID:** 2202.07506 **Authors:** Taehyun Yoon **Published:** 2022-02-15T15:23:22Z **Abstract:** Finding a better feasible solution in a shorter time is an integral part of solving Mixed Integer Programs. We present a post-hoc method based on Neural Diving to build heuristics more flexibly. We hypothesize that variables with higher confidence scores are more definite to be included in the optimal solution. For our hypothesis, we provide empirical evidence that confidence threshold techniq...Votes: 0GitHub stars: 3
- Constitutional Midtraining Content Presence DrivesConstitutional Midtraining: Content Presence Drives Alignment GainsVotes: 0GitHub stars: 3
- Constraint Aware Aggregation For Federated ReinforConstraint-Aware Aggregation for Federated Reinforcement Learning in Microgrid Energy Coordination - Federated Reinforcement Learning (FedRL) enables coordination of distributed energy resources without sharing raw local data, but standard aggregation...Votes: 0GitHub stars: 3
- Contextbased Deep Learning Architecture With Optimal Integration Layer For Image Parsing**arXiv ID:** 2204.06214 **Authors:** Ranju Mandal, Basim Azam, Brijesh Verma **Published:** 2022-04-13T07:35:39Z **Abstract:** Deep learning models have been efficient lately on image parsing tasks. However, deep learning models are not fully capable of exploiting visual and contextual information simultaneously. The proposed three-layer context-based deep architecture is capable of integrating context explicitly with visual information. The novel idea here is to have a visual layer to learn...Votes: 0GitHub stars: 3
- Contextual Graph Markov Model A Deep And Generative Approach To Graph Processing**arXiv ID:** 1805.10636 **Authors:** Davide Bacciu, Federico Errica, Alessio Micheli **Published:** 2018-05-27T15:04:05Z **Abstract:** We introduce the Contextual Graph Markov Model, an approach combining ideas from generative models and neural networks for the processing of graph data. It founds on a constructive methodology to build a deep architecture comprising layers of probabilistic models that learn to encode the structured information in an incremental fashion. Context is diffused in...Votes: 0GitHub stars: 3
- Continual Learning Of A Mixed Sequence Of Similar And Dissimilar Tasks**arXiv ID:** 2112.10017 **Authors:** Zixuan Ke, Bing Liu, Xingchang Huang **Published:** 2021-12-18T22:37:30Z **Abstract:** Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some work has also been done to transfer previously learned knowledge to the new task when the tasks are similar and have shared knowledge. To the best of our knowledge, no techniqu...Votes: 0GitHub stars: 3
- Continual Lifelong Learning In Natural Language Processing A Survey**arXiv ID:** 2012.09823 **Authors:** Magdalena Biesialska, Katarzyna Biesialska, Marta R. Costa-jussà **Published:** 2020-12-17T18:44:36Z **Abstract:** Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting previously acquired knowledge. Furthermore, CL is particularly challenging for language learning, as natural language is...Votes: 0GitHub stars: 3
- Continuous Pde Dynamics Forecasting With Implicit Neural Representations**arXiv ID:** 2209.14855 **Authors:** Yuan Yin, Matthieu Kirchmeyer, Jean-Yves Franceschi, Alain Rakotomamonjy, Patrick Gallinari **Published:** 2022-09-29T15:17:50Z **Abstract:** Effective data-driven PDE forecasting methods often rely on fixed spatial and / or temporal discretizations. This raises limitations in real-world applications like weather prediction where flexible extrapolation at arbitrary spatiotemporal locations is required. We address this problem by introducing a new data-dri...Votes: 0GitHub stars: 3
- Controllability Multiplexing And Transfer Learning In Networks Using Evolutionary Learning**arXiv ID:** 1811.05592 **Authors:** Rise Ooi, Chao-Han Huck Yang, Pin-Yu Chen, Vìctor Eguìluz, Narsis Kiani, Hector Zenil, David Gomez-Cabrero, Jesper Tegnèr **Published:** 2018-11-14T01:36:52Z **Abstract:** Networks are fundamental building blocks for representing data, and computations. Remarkable progress in learning in structurally defined (shallow or deep) networks has recently been achieved. Here we introduce evolutionary exploratory search and learning method of topologically flexibl...Votes: 0GitHub stars: 3
- Coordinating From Memory Graph Structured ExperienSkill generated from arXiv paper 2607.19985: Coordinating from Memory: Graph-Structured Experience Reuse for Multi-Agent Adaptation in Dynamic ManufacturingVotes: 0GitHub stars: 3
- Coquasi Bialgebroids Cocycle TwistingCoquasi-bialgebroid theory over noncommutative base algebras using Takeuchi coalgebra formalism. Product associative up to invertible normalized 3-cocycle, with twisting theorem by convolution-invertible 2-cochains and Connes-Moscovici-type constructions.Votes: 0GitHub stars: 3
- Cost Aware Fusion DecompositionCost-aware Fusion-based Decomposition (CFD) methodology for synthesizing photonic graph states. Decomposes target graph states into ring, star, and linear motifs, assembles via Type-I fusion to minimize resource overhead. Exploits local Clifford (LC) equivalence to find synthesis-friendly representations. Achieves up to 84.6% reduction in resource overhead vs baseline constructions. From arXiv:2606.02880 (Ji et al., 2026).Votes: 0GitHub stars: 3
- Creative Ai Through Evolutionary Computation**arXiv ID:** 1901.03775 **Authors:** Risto Miikkulainen **Published:** 2019-01-12T00:26:13Z **Abstract:** The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new. Such solutions exist in extremely large, high-dimensional, and complex search spaces. Population-based search techniques, i.e. variants of evolutionary computation, are well suited to finding them. These techniques are also well positioned to take advantage of large-...Votes: 0GitHub stars: 3
- Ctl Evaluating Generalization On Neverseen Compositional Patterns Of Known Functions And Compatibility Of Neural Representations**arXiv ID:** 2210.06350 **Authors:** Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber **Published:** 2022-10-12T16:01:57Z **Abstract:** Well-designed diagnostic tasks have played a key role in studying the failure of neural nets (NNs) to generalize systematically. Famous examples include SCAN and Compositional Table Lookup (CTL). Here we introduce CTL++, a new diagnostic dataset based on compositions of unary symbolic functions. While the original CTL is used to test length generalization or ...Votes: 0GitHub stars: 3
- Curiosity Driven Exploration Of Learned Disentangled Goal Spaces**arXiv ID:** 1807.01521 **Authors:** Adrien Laversanne-Finot, Alexandre Péré, Pierre-Yves Oudeyer **Published:** 2018-07-04T11:23:57Z **Abstract:** Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to discover repertoires of policies producing a wide diversity of effects. Often these algorithms relied on eng...Votes: 0GitHub stars: 3
- Cyclic Data Parallelism For Efficient Parallelism Of Deep Neural Networks**arXiv ID:** 2403.08837 **Authors:** Louis Fournier, Edouard Oyallon **Published:** 2024-03-13T08:39:21Z **Abstract:** Training large deep learning models requires parallelization techniques to scale. In existing methods such as Data Parallelism or ZeRO-DP, micro-batches of data are processed in parallel, which creates two drawbacks: the total memory required to store the model's activations peaks at the end of the forward pass, and gradients must be simultaneously averaged at the end of the...Votes: 0GitHub stars: 3
- D3vl Understanding Driving Scenes From 3d Time SerSkill generated from arXiv paper 2607.19528: D3VL: Understanding Driving Scenes from 3D Time Series Data and Video with Language ModelsVotes: 0GitHub stars: 3
- Darwin G Del MachineDarwin Gödel MachineVotes: 0GitHub stars: 3
- Data Driven Sde Subsampling RatesData-driven methodology for selecting optimal subsampling rates in SDE parameter estimation when data-model compatibility scales are unknown.Votes: 0GitHub stars: 3
- Data Driven Techniques Translational NeuroscienceNeurodegenerative diagnosis via multimodal fusion.Votes: 0GitHub stars: 3
- Dealing With Drift Of Adaptation Spaces In Learningbased Selfadaptive Systems Using Lifelong Selfadaptation**arXiv ID:** 2211.02658 **Authors:** Omid Gheibi, Danny Weyns **Published:** 2022-11-04T07:45:48Z **Abstract:** Recently, machine learning (ML) has become a popular approach to support self-adaptation. ML has been used to deal with several problems in self-adaptation, such as maintaining an up-to-date runtime model under uncertainty and scalable decision-making. Yet, exploiting ML comes with inherent challenges. In this paper, we focus on a particularly important challenge for learning-based...Votes: 0GitHub stars: 3
- Decoding Neural Responses In Mouse Visual Cortex Through A Deep Neural Network**arXiv ID:** 1911.05479 **Authors:** Asim Iqbal, Phil Dong, Christopher M Kim, Heeun Jang **Published:** 2019-10-26T05:02:33Z **Abstract:** Finding a code to unravel the population of neural responses that leads to a distinct animal behavior has been a long-standing question in the field of neuroscience. With the recent advances in machine learning, it is shown that the hierarchically Deep Neural Networks (DNNs) perform optimally in decoding unique features out of complex datasets. In this s...Votes: 0GitHub stars: 3
- Deep Learning For Explicitly Modeling Optimization Landscapes**arXiv ID:** 1703.07394 **Authors:** Shumeet Baluja **Published:** 2017-03-21T19:12:35Z **Abstract:** In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependencies between the input parameters. Decades of research with stochastic search techniques has shown the benefit of explicitly modeling the interactions between sets of parameters and the overall quality of the solutions discovered. We demonstrate a novel method, based on learning dee...Votes: 0GitHub stars: 3
- Deep Loopy Neural Network Model For Graph Structured Data Representation Learning**arXiv ID:** 1805.07504 **Authors:** Jiawei Zhang **Published:** 2018-05-19T03:33:20Z **Abstract:** Existing deep learning models may encounter great challenges in handling graph structured data. In this paper, we introduce a new deep learning model for graph data specifically, namely the deep loopy neural network. Significantly different from the previous deep models, inside the deep loopy neural network, there exist a large number of loops created by the extensive connections among nodes i...Votes: 0GitHub stars: 3
- Deep Neural Regression Collapse**arXiv ID:** 2603.23805 **Authors:** Akshay Rangamani, Altay Unal **Published:** 2026-03-25T00:26:16Z **Abstract:** Neural Collapse is a phenomenon that helps identify sparse and low rank structures in deep classifiers. Recent work has extended the definition of neural collapse to regression problems, albeit only measuring the phenomenon at the last layer. In this paper, we establish that Neural Regression Collapse (NRC) also occurs below the last layer across different types of models. We s...Votes: 0GitHub stars: 3
- Deep Oscillatory Neural Network**arXiv ID:** 2405.03725 **Authors:** Nurani Rajagopal Rohan, Vigneswaran C, Sayan Ghosh, Kishore Rajendran, Gaurav A, V Srinivasa Chakravarthy **Published:** 2024-05-06T06:17:16Z **Abstract:** We propose a novel, brain-inspired deep neural network model known as the Deep Oscillatory Neural Network (DONN). Deep neural networks like the Recurrent Neural Networks indeed possess sequence processing capabilities but the internal states of the network are not designed to exhibit brain-like oscilla...Votes: 0GitHub stars: 3
- Dendritic In Context Learning SnnDendriCL methodology for dendritic in-context learning in single-layer spiking neural networks. Demonstrates that a single dendritic compartment with online-LMS dynamics implements complete in-context learning, eliminating the need for attention, depth, or inference-time plasticity.Votes: 0GitHub stars: 3
- Differential Learning Kinetics Govern The Transition From Memorization To Generalization During Incontext Learning**arXiv ID:** 2412.00104 **Authors:** Alex Nguyen, Gautam Reddy **Published:** 2024-11-27T22:12:29Z **Abstract:** Transformers exhibit in-context learning (ICL): the ability to use novel information presented in the context without additional weight updates. Recent work shows that ICL emerges when models are trained on a sufficiently diverse set of tasks and the transition from memorization to generalization is sharp with increasing task diversity. One interpretation is that a network's limit...Votes: 0GitHub stars: 3
- Discovering Software Parallelization Points Using Deep Neural Networks**arXiv ID:** 2509.16215 **Authors:** Izavan dos S. Correia, Henrique C. T. Santos, Tiago A. E. Ferreira **Published:** 2025-09-05T15:32:23Z **Abstract:** This study proposes a deep learning-based approach for discovering loops in programming code according to their potential for parallelization. Two genetic algorithm-based code generators were developed to produce two distinct types of code: (i) independent loops, which are parallelizable, and (ii) ambiguous loops, whose dependencies are unc...Votes: 0GitHub stars: 3
- Discrete And Fuzzy Dynamical Genetic Programming In The Xcsf Learning Classifier System**arXiv ID:** 1201.5604 **Authors:** Richard J. Preen, Larry Bull **Published:** 2012-01-26T18:54:42Z **Abstract:** A number of representation schemes have been presented for use within learning classifier systems, ranging from binary encodings to neural networks. This paper presents results from an investigation into using discrete and fuzzy dynamical system representations within the XCSF learning classifier system. In particular, asynchronous random Boolean networks are used to represent t...Votes: 0GitHub stars: 3
- Distributed Hierarchical Temporal Memory With SharDerived from arXiv:2606.31789 - Distributed Hierarchical Temporal Memory with Shared Associative Memory for Cross-Entity Preemptive WarningVotes: 0GitHub stars: 3
- Dla Trainability By DesignTrainability-by-Design methodology for scalable Quantum Machine Learning using Dynamical Lie Algebra (DLA) constraints. Embeds group-theoretic geometric priors as structural regularizers to restrict DLA growth to polynomial regime, guaranteeing gradient-rich training landscapes while avoiding barren plateaus. arXiv:2606.31536Votes: 0GitHub stars: 3
- Do You Really Need To Pretrain Q Functions For OnlDo You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?Votes: 0GitHub stars: 3
- Do You Remember Toward Memory Centric Multimodal ADerived from arXiv:2607.11919 - Do You Remember? Toward Memory-Centric Multimodal AIVotes: 0GitHub stars: 3
- Driada Cross Scale Neural AnalysisDRIADA Python toolkit for cross-scale analysis of single-neuron selectivity and population dynamics. Unifies neural signals (calcium imaging, spike trains, simulated networks) with time-aligned behavior in a shared data model for selectivity testing, dimensionality reduction, and network analysis.Votes: 0GitHub stars: 3
- Driada Neural Analysis ToolkitDRIADA - Python toolkit for cross-scale analysis of single-neuron selectivity and population dynamics. Enables unified analysis from single-cell selectivity to population-level dynamics in neuroscience experiments.Votes: 0GitHub stars: 3