All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Systems Engineering Apr14 2026Systems engineering research synthesis from April 14, 2026 arXiv papers. 8 papers covering: multikernel serverless OS, datacenter digital twins, proactive K8s autoscaling with DQN, CPS hardware testing, multi-robot rigidity control, Koopman irregular sampling, physics-informed SSM, and LLM-based formal verification.Votes: 0GitHub stars: 3
- Systems Engineering Apr2026Systems engineering research synthesis from April 2026 arXiv papers. Covers: (1) Situation-aware feedback-predictive control for autonomous vehicles in unstructured traffic, (2) Heterogeneous dual-network framework for emergency UAV coordination, (3) Multi-agent reinforcement learning for 3D coverage optimization, (4) Output-feedback safe control with chance constraints for stochastic systems, (5) LLM-driven multi-agent coordination with personality-aware interaction. Use when: designing auto...Votes: 0GitHub stars: 3
- Systems Engineering Apr2026Systems engineering research synthesis covering April-May 2026 arXiv papers. April 2026 methodologies: (1) Situation-aware feedback-predictive control for autonomous vehicles, (2) Heterogeneous dual-network UAV coordination, (3) Multi-agent RL for 3D coverage, (4) Output-feedback safe control with chance constraints, (5) LLM-driven multi-agent HRI. May 2026 additions: (6) Convex hybrid modeling via operator theory, (7) SHIA SysML-hardware interface, (8) Sheaf-theoretic MBSE consistency (see r...Votes: 0GitHub stars: 3
- Systems EngineeringSystems engineering skills for multi-agent systems, control theory, and complex systems. This is a parent category containing specialized skills for systems-level engineering work.Votes: 0GitHub stars: 3
- Towards Optimal Vpu Compiler Cost Modeling By Using Neural Networks To Infer Hardware Performances**arXiv ID:** 2205.04586 **Authors:** Ian Frederick Vigogne Goodbody Hunter, Alessandro Palla, Sebastian Eusebiu Nagy, Richard Richmond, Kyle McAdoo **Published:** 2022-05-09T22:48:39Z **Abstract:** Calculating the most efficient schedule of work in a neural network compiler is a difficult task. There are many parameters to be accounted for that can positively or adversely affect that schedule depending on their configuration - How work is shared between distributed targets, the subdivision o...Votes: 0GitHub stars: 3
- Sparsity Ceiling Snn Energy EfficiencyThe Sparsity Ceiling framework for analyzing where Spiking Neural Networks can and cannot trade activity for energy efficiency. Provides information-theoretic bounds on firing rates based on memory load, state width, and task difficulty. Use when analyzing SNN energy efficiency, neuromorphic hardware deployment, or comparing recurrent vs attention-based architectures.Votes: 0GitHub stars: 3
- Sparsity Ceiling Spiking Networks EnergyThe Sparsity Ceiling framework for analyzing where Spiking Neural Networks can and cannot trade activity for energy efficiency. Use when studying energy-efficiency limits in SNNs, analyzing the relationship between sparsity and computational capability, or evaluating neuromorphic hardware performance across different network architectures.Votes: 0GitHub stars: 3
- Spike Htr Spiking Neural TransformerSpike-HTR: Spiking Neural Transformer for Handwritten Text Recognition - hybrid spiking recognizer that controls both spiking steps and sequence positions processed by deep sequence mixer. Use when working with handwritten text recognition, spiking neural networks for computer vision, or computational efficiency in SNNs.Votes: 0GitHub stars: 3
- Spikepeft Parameter Efficient Snn FinetuningSpikePEFT framework for parameter-efficient adaptation of spiking neural networks on point cloud data. Uses Intrinsic Dynamics Tuning (IDT) and Silent-State Disambiguation Adaptation (SSDA) to achieve high accuracy while updating only ~5% of parameters.Votes: 0GitHub stars: 3
- Spiking Neural Networks Elephant ReinforcementSpiking Neural Networks with Elephant Reinforcement — finite stochastic spiking-neuron network where past firing activity modifies future excitability through reinforcement-dependent threshold.Votes: 0GitHub stars: 3
- A Low Precision Simd Spiking Neural Compute EngineSpiking Neural Networks (SNNs) offer a promising solution for energy-efficient edge intelligence; however, their hardware deployment is constrained by memory overhead, inefficient scaling operations, ...Votes: 0GitHub stars: 3
- Adaptive Spiking Neuron DesignFunctional design framework for adaptive spiking neurons enabling high-performance vision and language modeling. Activation: adaptive spiking, adaptive snn, spiking neuron design, functional spiking, 自适应脉冲神经元.Votes: 0GitHub stars: 3
- Adaptive Spiking Neurons VisionAdaptive Spiking Neuron (ASN) methodology for vision and language modeling. Implements adaptive spiking neurons capable of handling large-scale applications with temporal dynamics and multi-timescale processing. Activation: adaptive spiking neuron, ASN, vision SNN, language SNN, large-scale spiking neural network, temporal dynamics.Votes: 0GitHub stars: 3
- Aigor Modular Neuromorphic ArchitectureAIGOR - modular, event-driven neuromorphic architecture for configurable SNN inference. Organizes neurons into timestep-synchronized processing cores with packet-switched communication, supporting multiple neuron models (LIF, HH, AH) and configurable precision.Votes: 0GitHub stars: 3
- Arxiv 2608 06346v1 Trajdebug Tracing Error Lifecycle To Identify CritTRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories (arXiv: 2608.06346v1)Votes: 0GitHub stars: 3
- Arxiv 2608 11865v1 Lapis Laplacian Spiking Attention Via First Spike**arXiv ID:** 2608.11865v1 **Authors:** Kaiwen Tang, Jiaqi Zheng, Zixuan Zhu, Yiqun Wang, Zhanglu Yan, Weng-Fai Wong **URL:** http://arxiv.org/abs/2608.11865v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 13221 Tsugo Probing Search Efficiency In Llm Reasoning VTsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems (arXiv: 2608.13221)Votes: 0GitHub stars: 3
- Arxiv 2608 18341v1 Low Power Neuromorphic Acoustic Anomaly Detection**arXiv ID:** 2608.18341v1 **Authors:** Steven C. Nesbit, Victor M. Vergara, Michael A. Felix, Evan T. Kain, Luis R. García Carrillo, Gerd J. Kunde, Andrew T. Sornborger **URL:** http://arxiv.org/abs/2608.18341v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 19885 Separating Covariate Shift From Mechanism Change WSeparating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition (arXiv: 2608.19885)Votes: 0GitHub stars: 3
- Arxiv 2608 19888 Evidence Before Expansion Reuse Spawn Or Defer InEvidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools (arXiv: 2608.19888)Votes: 0GitHub stars: 3
- Arxiv 2608 20054 What You Can T See Is What You Learn Restricted EvWhat You Can't See Is What You Learn: Restricted Evidence Visibility Favors Compositional Generalization in Shared-Genome Language-Model Societies (arXiv: 2608.20054)Votes: 0GitHub stars: 3
- Arxiv 2608 20195 From Agent Behaviour To Agent Friendly DocumentatiFrom Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation (arXiv: 2608.20195)Votes: 0GitHub stars: 3
- Arxiv 2608 20220 Insufficiencybench Evaluating Llm Legal Advice OnInsufficiencyBench: Evaluating LLM legal advice on underspecified user queries (arXiv: 2608.20220)Votes: 0GitHub stars: 3
- Arxiv 2608 20271 Catching The Rug Early Prediction Of Fraudulent MeCatching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning (arXiv: 2608.20271)Votes: 0GitHub stars: 3
- Arxiv 2608 22729v1 Spiking Neural Networks For Continuous Control Neu**arXiv ID:** 2608.22729v1 **Authors:** Jessica Hunter, Md Maruf Hossain Shuvo, Krishna Roy **URL:** http://arxiv.org/abs/2608.22729v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 24073v1 Orbitalif An Efficient Spiking Federated Learning**arXiv ID:** 2608.24073v1 **Authors:** Bohan Zhang, Chenyu Xu, Yijie Mao, Yuanming Shi **URL:** http://arxiv.org/abs/2608.24073v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 25536v1 Syn2logic End To End Neuromorphic Design Automatio**arXiv ID:** 2608.25536v1 **Authors:** Artur Podobas **URL:** http://arxiv.org/abs/2608.25536v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 25738v1 Memark Membrane Space Watermarking For Spiking Neu**arXiv ID:** 2608.25738v1 **Authors:** Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta **URL:** http://arxiv.org/abs/2608.25738v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 25871v1 Cedar Controlled And Event Driven Demand Forecasti**arXiv ID:** 2608.25871v1 **Authors:** Junjie Meng, Ranxu Zhang, Zi-an Zhang, Shujun Liu, Xiaoning Qi, Xiaozhou Xu, Yanyong Zhang, Hui Xiong, Chao Wang **URL:** http://arxiv.org/abs/2608.25871v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2608 30439v1 Event Driven Language Models With Sparse Neural Ac**arXiv ID:** 2608.30439v1 **Authors:** Simon Richter, Ruhai Lin, Jason Yik, Taylor Kergan, Rui-Jie Zhu, Farshad Moradi, Jason Eshraghian **URL:** http://arxiv.org/abs/2608.30439v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Arxiv 2609 08070v1 A Gradient Based Yet Spike Timing Dependent Soluti**arXiv ID:** 2609.08070v1 **Authors:** Xiangnan Zhang, Jingxin Liu, Ranqi Lu, Jingyu Liu, Qunxi Dong, Fuze Tian, Lixian Zhu, Bin Hu, Björn W. Schuller **URL:** http://arxiv.org/abs/2609.08070v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- As Fedbridge Ann Snn Federated LearningAS-FedBridge framework for heterogeneous ANN-SNN federated learning. Creates lightweight Bridge with Pseudo-Spike Interface to align continuous ANN activations with discrete SNN spikes. Use when implementing mixed ANN-SNN federated learning systems, addressing representational misalignment in edge AI, or optimizing resource-efficient collaborative learning across heterogeneous neural network architectures.Votes: 0GitHub stars: 3
- As Fedbridge Heterogeneous Ann Snn Federated LearningAS-FedBridge methodology for heterogeneous ANN-SNN federated learning with pseudo-spike bridge distillation. Enables mixed ANN-SNN client training by projecting continuous signals into spike-compatible space to overcome representational misalignment. Use when implementing federated learning systems with both traditional ANNs and energy-efficient Spiking Neural Networks on edge devices.Votes: 0GitHub stars: 3
- Attacking The Spike On The Transferability And Security Of Spiking Neural Networks To Adversarial Examples**arXiv ID:** 2209.03358 **Authors:** Nuo Xu, Kaleel Mahmood, Haowen Fang, Ethan Rathbun, Caiwen Ding, Wujie Wen **Published:** 2022-09-07T17:05:48Z **Abstract:** Spiking neural networks (SNNs) have attracted much attention for their high energy efficiency and recent advances in classification performance. However, unlike traditional deep learning approaches, the study of SNN robustness to adversarial examples remains relatively underdeveloped. In this work, we advance the adversarial attack ...Votes: 0GitHub stars: 3
- Averageovertime Spiking Neural Networks For Uncertainty Estimation In Regression**arXiv ID:** 2412.00278 **Authors:** Tao Sun, Sander Bohté **Published:** 2024-11-29T23:13:52Z **Abstract:** Uncertainty estimation is a standard tool to quantify the reliability of modern deep learning models, and crucial for many real-world applications. However, efficient uncertainty estimation methods for spiking neural networks, particularly for regression models, have been lacking. Here, we introduce two methods that adapt the Average-Over-Time Spiking Neural Network (AOT-SNN) framewor...Votes: 0GitHub stars: 3
- Axonal Delay As A Shortterm Memory For Feed Forward Deep Spiking Neural Networks**arXiv ID:** 2205.02115 **Authors:** Pengfei Sun, Longwei Zhu, Dick Botteldooren **Published:** 2022-04-20T16:56:42Z **Abstract:** The information of spiking neural networks (SNNs) are propagated between the adjacent biological neuron by spikes, which provides a computing paradigm with the promise of simulating the human brain. Recent studies have found that the time delay of neurons plays an important role in the learning process. Therefore, configuring the precise timing of the spike is a ...Votes: 0GitHub stars: 3
- Backpropagationfree Spiking Neural Networks With The Forwardforward Algorithm**arXiv ID:** 2502.20411 **Authors:** Mohammadnavid Ghader, Saeed Reza Kheradpisheh, Bahar Farahani, Mahmood Fazlali **Published:** 2025-02-19T12:44:26Z **Abstract:** Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm that emulates neuronal activity through discrete spike-based processing. Despite their advantages, training SNNs with traditional backpropagation (BP) remains challenging due to computational inefficiencies and a lack of biological plausibility. ...Votes: 0GitHub stars: 3
- Bayesian Continual Learning Via Spiking Neural Networks**arXiv ID:** 2208.13723 **Authors:** Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone **Published:** 2022-08-29T17:11:14Z **Abstract:** Among the main features of biological intelligence are energy efficiency, capacity for continual adaptation, and risk management via uncertainty quantification. Neuromorphic engineering has been thus far mostly driven by the goal of implementing energy-efficient machines that take inspiration from the time-based computing paradigm of biological brains. I...Votes: 0GitHub stars: 3
- Bayesian Speech SnnBayesian inference methodology for Spiking Neural Networks in speech processing. Uses IVON (Improved Variational Online Newton) to smooth the angular predictive landscape caused by threshold-based spike generation. Demonstrates improved NLL and Brier scores on Heidelberg Digits and Speech Commands datasets. Activation: bayesian SNN, speech SNN, surrogate gradient, IVON, loss landscape smoothing, uncertainty quantification, variational inference.Votes: 0GitHub stars: 3
- Benchmarking Fairness In Spiking Neural Networks Data Bias Spurious Features And Hardware Effects**arXiv ID:** 2605.27407 **Authors:** Hudi He, Fukun Wang, Zhe Wang, Xinyi Wang, Shuhan Ye, Jiarui Liu, Qing Qing, Ziqi Xu, Xikun Zhang, Renqiang Luo **Published:** 2026-05-08T02:29:00Z **Abstract:** Evaluating fairness in Spiking Neural Networks (SNNs) demands rigorous benchmarks that reflect real-world complexities, yet existing assessments remain limited by superficial dataset diversity and idealized hardware assumptions. This work introduces the first systematic fairness benchmark for SNN...Votes: 0GitHub stars: 3
- Boost Eventdriven Tactile Learning With Location Spiking Neurons**arXiv ID:** 2210.04277 **Authors:** Peng Kang, Srutarshi Banerjee, Henry Chopp, Aggelos Katsaggelos, Oliver Cossairt **Published:** 2022-10-09T14:49:27Z **Abstract:** Tactile sensing is essential for a variety of daily tasks. And recent advances in event-driven tactile sensors and Spiking Neural Networks (SNNs) spur the research in related fields. However, SNN-enabled event-driven tactile learning is still in its infancy due to the limited representation abilities of existing spiking neuron...Votes: 0GitHub stars: 3
- Brain Inspired Snn Pattern Analysis分析 Spiking Neural Networks (SNN) 和脑启发计算论文，提炼可复用的技术模式和实现指南。Use when analyzing papers about: spiking neural networks, brain-inspired computing, neuromorphic systems, biological learning rules, SNN architectures, or extracting implementation patterns from neuroscience papers.Votes: 0GitHub stars: 3
- Brain NeuromorphicNeuromorphic VLSI systems take inspiration from biology to enable efficient emulation of large-scale spiking neural networks and to explore new computational paradigms. To establis... Activation: spiking neural network, neural dynamics, neuromorphicVotes: 0GitHub stars: 3
- Brain Scale Snn SimulationBrain-scale spiking neural network simulation using network topology exploitation. Enables efficient large-scale SNN simulations by leveraging network structure. Activation: brain-scale, snn simulation, network topology, spiking neural networks, large-scale neural simulation.Votes: 0GitHub stars: 3
- Braininspired Graph Spiking Neural Networks For Commonsense Knowledge Representation And Reasoning**arXiv ID:** 2207.05561 **Authors:** Hongjian Fang, Yi Zeng, Jianbo Tang, Yuwei Wang, Yao Liang, Xin Liu **Published:** 2022-07-11T05:22:38Z **Abstract:** How neural networks in the human brain represent commonsense knowledge, and complete related reasoning tasks is an important research topic in neuroscience, cognitive science, psychology, and artificial intelligence. Although the traditional artificial neural network using fixed-length vectors to represent symbols has gained good performan...Votes: 0GitHub stars: 3
- Circulate Firing Snn Direct TrainingDirect training algorithm for SNNs with circulate-firing neurons and learnable surrogate gradients. Three core innovations for membrane potential dynamics optimization.Votes: 0GitHub stars: 3
- Clane Neuromorphic Continual LearningCLANE - 在神经形态硬件（Intel Loihi 2）上从事件相机实现动作的持续学习。首个端到端部署的神经形态持续学习系统，结合脉冲 2D CNN 和 CLP-SNN 学习头，通过 Temporal Aggregation Layer 和 Normalization Layer 处理动作序列。实现 100x 能量降低和 16x 延迟减少。Activation: neuromorphic continual learning, event camera, Loihi 2, spiking CNN, CLP-SNN, action recognition, on-device learning, energy-efficient AI, edge deployment, 神经形态持续学习, 事件相机, 能量高效 AI.Votes: 0GitHub stars: 3
- Clockless Asynchronous Neuromorphic ComputingClockless asynchronous neuromorphic computing methodology — scalable spiking neural networks on FPGAs without dedicated analog hardware. Use when designing energy-efficient neuromorphic systems, implementing Boolean spiking neurons on FPGAs, or bridging analog neuromorphic gaps with reconfigurable digital chips. Also triggers: clockless SNN, FPGA neuromorphic, asynchronous spiking, autonomous spiking dynamics, reconfigurable neuromorphic chip.Votes: 0GitHub stars: 3
- Clockless Fpga Neuromorphic ScalingScalable neuromorphic computing via clockless (asynchronous) FPGA-based Boolean spiking neurons. Use when: designing scalable neuromorphic architectures, implementing autonomous time-continuous spiking dynamics on commercial FPGAs, building energy-efficient Boolean neural processors without custom ASIC, or studying emergent spiking behavior from asynchronous digital circuits. Covers excitatory/inhibitory synaptic weight configuration, audio classification benchmarks, and scaling strategies fo...Votes: 0GitHub stars: 3
- Clockless Neuromorphic ChipScalable neuromorphic computing from autonomous spiking dynamics in clockless (asynchronous) reconfigurable FPGA chips. Boolean spiking neurons with configurable E/I weights, spike-encoded data pipeline, and competitive audio classification at significantly lower power.Votes: 0GitHub stars: 3