All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Whisper Ecog Alignment Neural EncodingWhisper 语音模型与人类 ECoG 神经响应的对齐框架。使用可解释时间解析神经编码器，揭示中间层最强的脑对齐，并通过注意力映射和音素分析验证解剖学上的一致性组织。Votes: 0GitHub stars: 3
- Whisper Ecog AlignmentWhisper-ECoG alignment methodology mapping speech foundation model representations to human cortical activity using interpretable time-resolved neural encodingVotes: 0GitHub stars: 3
- Winner Take All Bottleneck DisentangledWinner-Take-All (WTA) bottlenecks enforce disentangled symbolic representations in multi-task learning. Shows WTA circuits (a core cortical motif) within deep networks extract categorical latent factors where single neurons encode single abstract features (object, color, position). Theoretical proof + empirical validation. Activation: WTA, winner-take-all, disentangled representations, symbolic AI, latent factors, cortical circuits, multi-task learning, neural bottleneck, softmax attention, o...Votes: 0GitHub stars: 3
- Winner Take All SpikingWinner-Take-All (WTA) Spiking Transformer for energy-efficient language modeling. Softmax-free, spike-driven self-attention (WSSA/CWSSA), encoder and decoder architectures. Activation: wta spiking transformer, winner-take-all spiking, softmax-free attention, spiking language model, wd-spikingformer, we-spikingformerVotes: 0GitHub stars: 3
- Working Memory Rsnn DelaysWorking memory implementation in recurrent spiking neural networks using heterogeneous synaptic delays. Each synapse equipped with D=41 delays modeled as weight tensor W ∈ R^(N×N×D), trained end-to-end with surrogate-gradient BPTT. Network stores arbitrary target spike patterns as sequential chains of overlapping Spiking Motifs. Achieves F1=1.0 on synthetic benchmark (M=16 patterns, N=512 neurons, T=1000 steps). Activation: working memory snn, recurrent spiking memory, heterogeneous delays, s...Votes: 0GitHub stars: 3
- Worldkv World MemoryWorldKV methodology from arXiv:2605.22718 (May 2026). Training-free KV-cache management for autoregressive video diffusion world models: World Retrieval (evicted KV-chunk reuse) + World Compression (token pruning via key-key similarity). Use when: world model inference, video diffusion, KV-cache optimization, long-context visual generation, persistent world consistency.Votes: 0GitHub stars: 3
- Wta Spiking Transformer LanguageWinner-Take-All (WTA) Spiking Transformer for energy-efficient language modeling using sparse attention and event-driven computation.Votes: 0GitHub stars: 3
- Xoresnet Deep Snn LearningXOResNet: Exclusive-OR Meta-Residuals for Deep Spiking Neural Networks. Novel architecture addressing spike redundancy and information loss in SNN residual learning. OR-ADD shortcut connection merges branch outputs; XOR meta-residuals select pre-learning residuals to mitigate redundant learning. Outperforms SOTA deep SNNs on Fashion-MNIST, CIFAR-10/100, miniImageNet. Use when: deep SNN architecture, residual learning SNN, spike redundancy mitigation, neuromorphic systems, XOR operations in ne...Votes: 0GitHub stars: 3
- Yana Neuromorphic Simulation Hardware GapYANA: Bridging the Neuromorphic Simulation-to-Hardware Gap. Framework for seamless translation of SNN algorithms from simulation to neuromorphic hardware deployment. Activation: YANA, simulation-to-hardware, neuromorphic deployment, SNN hardware gap.Votes: 0GitHub stars: 3
- Zenbrain 7layer Memory ArchitectureZenBrain: Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems. Seven-layer hierarchical memory with 15 integrated neuroscience models. Activation triggers: memory architecture, multi-layer memory, neuroscience-inspired AI, hippocampal consolidation, episodic memory, semantic memory, procedural memory.Votes: 0GitHub stars: 3
- Zuna1 1 Flexible Eeg Foundation ModelZUNA1.1: A 380M-parameter diffusion autoencoder for flexible EEG signal reconstruction, denoising, and super-resolution with arbitrary channel configurations and temporal intervals.Votes: 0GitHub stars: 3
- Neuroworld Latent Brain World ModelNeuroWorld - A Latent Brain World Model for Stimulus-Conditioned Human Brain Dynamics. Framework for causal forecasting of human brain activity using stimulus-conditioned evolution in learned latent brain-state space, separating endogenous states from exogenous multimodal stimuli. Use when modeling naturalistic brain functional dynamics prediction, brain world models, or fMRI-based neural state forecasting.Votes: 0GitHub stars: 3
- Nl Cps Kubernetes ControlReinforcement Learning-Based Kubernetes Control Plane Placement in Multi-Region ClustersVotes: 0GitHub stars: 3
- A Computer Vision Enabled Damage Detection Model With Improved Yolov5 Based On Transformer Prediction Head**arXiv ID:** 2303.04275 **Authors:** Arunabha M. Roy, Jayabrata Bhaduri **Published:** 2023-03-07T22:53:36Z **Abstract:** Objective:Computer vision-based up-to-date accurate damage classification and localization are of decisive importance for infrastructure monitoring, safety, and the serviceability of civil infrastructure. Current state-of-the-art deep learning (DL)-based damage detection models, however, often lack superior feature extraction capability in complex and noisy environments, ...Votes: 0GitHub stars: 3
- A Deep Evolutionary Approach To Bioinspired Classifier Optimisation For Brainmachine Interaction**arXiv ID:** 1908.04784 **Authors:** Jordan J. Bird, Diego R. Faria, Luis J. Manso, Anikó Ekárt, Christopher D. Buckingham **Published:** 2019-08-13T16:49:30Z **Abstract:** This study suggests a new approach to EEG data classification by exploring the idea of using evolutionary computation to both select useful discriminative EEG features and optimise the topology of Artificial Neural Networks. An evolutionary algorithm is applied to select the most informative features from an initial set o...Votes: 0GitHub stars: 3
- A Dual Hypothesis Reasoning Framework For Llm GuarDerived from arXiv:2607.17575 - A Dual-Hypothesis Reasoning Framework for LLM GuardrailsVotes: 0GitHub stars: 3
- A Global Workspace In Language ModelsA global workspace in language modelsVotes: 0GitHub stars: 3
- Actpcgeom Towards Scalable Online Neuralsymbolic Learning Via Accelerating Active Predictive Coding With Information Geometry Diverse Cognitive Mechanisms**arXiv ID:** 2501.04832 **Authors:** Ben Goertzel **Published:** 2025-01-08T20:38:02Z **Abstract:** This paper introduces ActPC-Geom, an approach to accelerate Active Predictive Coding (ActPC) in neural networks by integrating information geometry, specifically using Wasserstein-metric-based methods for measure-dependent gradient flows. We propose replacing KL-divergence in ActPC's predictive error assessment with the Wasserstein metric, suggesting this may enhance network robustness. To mak...Votes: 0GitHub stars: 3
- Adapting A Language Model While Preserving Its General Knowledge**arXiv ID:** 2301.08986 **Authors:** Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu **Published:** 2023-01-21T17:57:53Z **Abstract:** Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a particular domain to adapt the LM so that end-tasks in the domain can give improved performances. However, existing DA-training methods are in some sense blind as they ...Votes: 0GitHub stars: 3
- Adapting Bert For Continual Learning Of A Sequence Of Aspect Sentiment Classification Tasks**arXiv ID:** 2112.03271 **Authors:** Zixuan Ke, Hu Xu, Bing Liu **Published:** 2021-12-06T02:46:06Z **Abstract:** This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL system that incrementally learns a sequence of ASC tasks should address the following two issues: (1) transfer knowledge learned from previous tas...Votes: 0GitHub stars: 3
- Adaptive Adversaries A Multi Turn Multi Llm BenchmDerived from arXiv:2607.18063 - Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent SecurityVotes: 0GitHub stars: 3
- Adaptive Adversaries Multi Turn Multi Llm Benchmark Llm Agent SecuritySkill derived from arXiv:2607.18063 - Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent SecurityVotes: 0GitHub stars: 3
- Adaptive Transformers In Rl**arXiv ID:** 2004.03761 **Authors:** Shakti Kumar, Jerrod Parker, Panteha Naderian **Published:** 2020-04-08T01:03:10Z **Abstract:** Recent developments in Transformers have opened new interesting areas of research in partially observable reinforcement learning tasks. Results from late 2019 showed that Transformers are able to outperform LSTMs on both memory intense and reactive tasks. In this work we first partially replicate the results shown in Stabilizing Transformers in RL on both react...Votes: 0GitHub stars: 3
- Agentic Erp Multi Agent Large Language Model ArchiDerived from arXiv:2607.17331 - Agentic ERP: Multi-Agent Large Language Model Architecture for Autonomous Enterprise Resource PlanningVotes: 0GitHub stars: 3
- Agentic Erp Multi Agent Large Language Model Architecture Autonomous Enterprise Resource PlanniSkill derived from arXiv:2607.17331 - Agentic ERP: Multi-Agent Large Language Model Architecture for Autonomous Enterprise Resource PlanniVotes: 0GitHub stars: 3
- Agentic Evolution Path To Evolving LlmsAgentic Evolution is the Path to Evolving LLMs: Proposes that LLM evolution should be driven by agentic interactions rather than passive fine-tuning. Models evolve through interaction with environments, tools, and other agents, developing capabilities via experience. Activation: agentic-evolution, llm-evolution, scaling.Votes: 0GitHub stars: 3
- Agentic Graphrag Citation ProvenanceMethodology for evaluating citation faithfulness in Agentic GraphRAG systems as a trajectory-level problem. Addresses how cited evidence, traversal context, and graph structure influence answer accuracy. Use when: building GraphRAG systems, evaluating citation quality, designing knowledge graph retrieval, or analyzing agent traversal patterns. Triggers: GraphRAG citation evaluation, retrieval provenance, knowledge graph traversal analysis, citation faithfulness, agentic RAG.Votes: 0GitHub stars: 3
- Agentic Rl Llm SurveySkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Agon Competitive Cross Model Rl With Implicit Rival Grading Of ReasoningReinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind todays reasoning models, yet it grades only the final answer. On hard problems this trains models to write more rather. Based on arXiv:2607.07690.Votes: 0GitHub stars: 3
- An Interpretable Automated Mechanism Design Framework With Large Language Models**arXiv ID:** 2502.12203 **Authors:** Jiayuan Liu, Mingyu Guo, Vincent Conitzer **Published:** 2025-02-16T12:33:03Z **Abstract:** Mechanism design has long been a cornerstone of economic theory, with traditional approaches relying on mathematical derivations. Recently, automated approaches, including differentiable economics with neural networks, have emerged for designing payments and allocations. While both analytical and automated methods have advanced the field, they each face significant...Votes: 0GitHub stars: 3
- Analysis Of Error Sources In Llmbased Hypothesis Search For Fewshot Rule Induction**arXiv ID:** 2509.01016 **Authors:** Aishni Parab, Hongjing Lu, Ying Nian Wu, Sumit Gulwani **Published:** 2025-08-31T22:42:58Z **Abstract:** Inductive reasoning enables humans to infer abstract rules from limited examples and apply them to novel situations. In this work, we compare an LLM-based hypothesis search framework with direct program generation approaches on few-shot rule induction tasks. Our findings show that hypothesis search achieves performance comparable to humans, while direc...Votes: 0GitHub stars: 3
- Arpp Latent SsmSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Arxiv 2510 20351 When Large Language Models Know The Table A FramewWhen Large Language Models Know the Table: A Framework for Assessing Data Contamination in Tabular Datasets (arXiv: 2510.20351)Votes: 0GitHub stars: 3
- Arxiv 2601 21124 Phasecoder Microphone Geometry Agnostic Spatial AuPhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs (arXiv: 2601.21124)Votes: 0GitHub stars: 3
- Arxiv 2603 00059 Stochastic Parrots Or Singing In Harmony Testing FStochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data (arXiv: 2603.00059)Votes: 0GitHub stars: 3
- Arxiv 2603 05997 Mm Ists Cooperating Irregularly Sampled Time SerieMM-ISTS: Cooperating Irregularly Sampled Time Series Forecasting with Multimodal Vision-Text LLMs (arXiv: 2603.05997)Votes: 0GitHub stars: 3
- Arxiv 2603 08652 Coco Code As Cot For Text To Image Preview And RarCoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation (arXiv: 2603.08652)Votes: 0GitHub stars: 3
- Arxiv 2604 01170 Online Reasoning Calibration Test Time Training EnOnline Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning (arXiv: 2604.01170)Votes: 0GitHub stars: 3
- Arxiv 2605 00737 To Call Or Not To Call A Framework To Assess And OTo Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling (arXiv: 2605.00737)Votes: 0GitHub stars: 3
- Arxiv 2605 16411 Reducing Hallucination In Vision Language Models VReducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift (arXiv: 2605.16411)Votes: 0GitHub stars: 3
- Arxiv 2606 18519 As You Wish Mission Planning With Formal VerificatAs You Wish: Mission Planning with Formal Verification using LLMs in Precision Agriculture (arXiv: 2606.18519)Votes: 0GitHub stars: 3
- Arxiv 2607 07144 Fractal Kv Cache Archives Lossless Symbolic StoragFractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference (arXiv: 2607.07144)Votes: 0GitHub stars: 3
- Arxiv 2607 21090 Training Large Language Models For Self ExplanatioTraining Large Language Models for Self-Explanation Faithfulness (arXiv: 2607.21090)Votes: 0GitHub stars: 3
- Arxiv 2607 21291 Adaptive Depth Sparse Framework Similarity DrivenAdaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs (arXiv: 2607.21291)Votes: 0GitHub stars: 3
- Arxiv 2607 21327 From Static Bibliometrics To Dynamic Knowledge GraFrom Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Scie (arXiv: 2607.21327)Votes: 0GitHub stars: 3
- Arxiv 2607 27698 Guiding Large Language Models With Genetic ProgramGuiding Large Language Models with Genetic Programming-Evolved Heuristic Knowledge for Dynamic Multi-Mode Project Scheduling (arXiv: 2607.27698)Votes: 0GitHub stars: 3
- Arxiv 2608 00023 Role Steering Of Language Models For Social SimulaRole Steering of Language Models for Social Simulations (arXiv: 2608.00023)Votes: 0GitHub stars: 3
- Arxiv 2608 02940 When Compression Scores Cannot Decide InformationWhen Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning (arXiv: 2608.02940)Votes: 0GitHub stars: 3
- Arxiv 2608 04549 Euroexec Frontier Language Models Fall Short Of ExEuroExec: Frontier Language Models Fall Short of Expert Judgment on European Executive Decision Tasks (arXiv: 2608.04549)Votes: 0GitHub stars: 3
- Arxiv 2608 05030 From Score Matrices To Football Aware Match StateFrom Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Sco (arXiv: 2608.05030)Votes: 0GitHub stars: 3