Menu
Skills dans ce dépôt
SkillsMP a collecté 4 114 skills depuis hiyenwong/ai_collection. Ouvrez un skill pour examiner sa source et ses détails.
hiyenwong/ai_collectionAffichage de 40 skills collectés sur 4 114.
Theoretical analysis of effective target shift in online learning and methods to correct for it. Explains why online learning struggles under distributional shift and how to characterize the relationship between online and offline learning. Activation…
Langue du texte source : anglais
SR²AM (Self-Regulated Simulative Reasoning Agentic LLM) methodology from arXiv:2605.22138 (May 2026). Three-system framework decomposing agent reasoning: System II (simulative planning via world model), System III (self-regulation deciding when/how to plan),…
Langue du texte source : anglais
Extended Sompolinsky-Crisanti-Sommers (SCS) chaos theory for Excitatory-Inhibitory recurrent networks with target-specific inhibition. Derives mean-field theory for E/I networks, identifies three dynamical regimes (quiescence, asynchronous chaos, coherent…
Langue du texte source : anglais
Expert guidance for designing modular Mixture-of-Experts (MoE) architectures using emergent document-level expert grouping. Based on EMO paper (arXiv:2605.06663). Use when designing sparse LLM architectures, MoE modularity, expert specialization,…
Langue du texte source : anglais
E-SPL: Evolutionary System Prompt Learning
Langue du texte source : anglais
Evolutionary Generative Merging (EvoGM) framework for training-free LLM composition via learnable generative modeling and dual-generator architecture with cycle-consistent learning
Langue du texte source : anglais
Excitation-driven data generation and distributed control optimization for building thermal systems and district heating networks. Combines BuilDyn framework (arXiv:2605.29849) and distributed NMPC with ADMM (arXiv:2605.29841).
Langue du texte source : anglais
FCN-LLM: Empowering LLMs for Brain Functional Connectivity Network Understanding via Graph-level Multi-task Instruction Tuning. Covers the multi-scale FCN encoder, semantic projection into LLM, 19-attribute multi-paradigm instruction tuning, two-stage…
Langue du texte source : anglais
Backpropagation-free continual learning using feedback-aligned Hebbian plasticity. Replaces backpropagation with local Hebbian updates guided by random feedback connections, enabling biologically plausible continual learning without catastrophic forgetting.…
Langue du texte source : anglais
FLAME: Adaptive Mixture-of-Experts for continual multimodal multi-task learning. Handles both co-available multi-task pretraining and sequential continual adaptation. Activation triggers: FLAME MoE, continual multimodal learning, adaptive mixture of experts,…
Langue du texte source : anglais
Free Energy Principle-based Mixture-of-Experts routing methodology. Uses LIF membrane potentials (beta) for temporal memory, precision-weighted gating (Pi) for reliability assessment, and anticipatory routing to solve domain transition failures in sparse MoE.…
Langue du texte source : anglais
Free Energy Principle-based MoE routing using LIF membrane dynamics. Solves domain transition failures in sparse MoE with three mechanisms: temporal memory (beta), precision-weighted gating (Pi), and anticipatory routing. 124x improvement at transitions.…
Langue du texte source : anglais
Geno-Synthetic Algorithm: type-factored coevolutionary optimization for heterogeneous genotypes and assembled phenotypes. Use when: coevolutionary algorithms, heterogeneous genotype optimization, assembled phenotype synthesis, evolutionary computation, neural…
Langue du texte source : anglais
GFFMERGE methodology for efficient closed-form model merging in Graph Neural Networks. Exploits linear structure of message-passing layers to enable near-quantum accuracy atomistic simulations without retraining foundation models. Applicable to drug…
Langue du texte source : anglais
图神经网络与 Transformer 融合的多模态数据融合方法论。 整合非欧几里得脑影像数据与欧几里得表格数据，支持时间感知的纵向预测。 触发词：多模态融合、脑网络、GNN、Transformer、时序预测、纵向分析、 multimodal fusion, brain connectivity, GNN-TF, temporal fusion。
Langue du texte source : Plusieurs langues
Graph-based workflow management paradigm for efficient LLM agent serving using unified directed graphs (wGraph) for dynamic workflow instantiation with KV-cache optimization. Use for LLM agent serving, workflow management, agent serving optimization, agent…
Langue du texte source : anglais
GTaS Generative Spike Train Model
Langue du texte source : anglais
GyralNet Subnetwork Partitioning
Langue du texte source : anglais
Hardware-motivated noise modeling methodology for fault-tolerant quantum computing benchmarking. Uses structured noise families (Pauli bias, measurement bias, spatial non-uniformity) instead of uniform depolarizing model to faithfully reflect real device…
Langue du texte source : anglais
Benchmarking 7 local Hebbian learning rules for associative memory storage and prototype extraction. Bayesian-Hebbian rules achieve highest capacity. Activation: hebbian learning benchmark, associative memory capacity, prototype extraction, Bayesian-Hebbian…
Langue du texte source : anglais
分层 MoE 架构技能 - 用于对象检测的分层实例条件化混合专家模型 (HI-MoE)。通过两级路由机制实现稀疏计算与实例中心结构的匹配。基于论文 HI-MoE: Hierarchical Instance-Conditioned Mixture-of-Experts (arXiv 2604.04908)。激活关键词: MoE, mixture of experts, object detection MoE, instance routing, 分层路由, 实例条件化。
Langue du texte source : chinois
Web-scale LLM-based multi-agent system architecture for the Agentic Web. Focuses on five-layer coordination architecture, heterogeneous agent interaction, and open-world scaling challenges. Use when: (1) Designing large-scale multi-agent systems, (2)…
Langue du texte source : anglais
Modern Hopfield Networks for continual learning in diffusion models via energy-based intrinsic forgetting and replay selection
Langue du texte source : anglais
Hippocampal-Entorhinal (HPC-MEC) inspired hierarchical world model for structure abstraction and generalization from video sequences. Based on arXiv:2605.15733 (May 2026). Use when: designing brain-inspired world models, HPC-MEC cognitive architecture,…
Langue du texte source : anglais
Integrative neurocybernetic modeling framework for large-scale neuroscience. Treats brain as controller pursuing latent objectives in closed-loop coupling with body and environment. Keywords: neurocybernetics, closed-loop modeling, large-scale neuroscience,…
Langue du texte source : anglais
Bayesian modeling methodology for ion channel gating with missed event correction. Integrates temporal resolution limitations of patch clamp recordings into hierarchical Markov chain likelihood functions, enabling unbiased kinetic parameter inference and…
Langue du texte source : anglais
DMOSOPT — scalable optimization framework using jointly learned surrogate models for constrained multi-objective optimization of neural dynamical systems. Learns smooth approximations of objective landscapes and feasibility boundaries to guide search with…
Langue du texte source : anglais
Kinetic energy in random recurrent neural networks - links chaotic dynamics and unstable fixed points through dynamical mean-field theory. Cubic scaling at critical point, shell-like chaotic manifold geometry. Activation: kinetic energy, random RNN, chaos,…
Langue du texte source : anglais
Neuro-inspired phase encoding using Kuramoto oscillators (KoPE) applied to Vision Transformers, combining oscillatory dynamics with attention mechanisms for improved learning efficiency. Based on ICLR 2025 paper by Xiao et al. (Microsoft Research).
Langue du texte source : anglais
基于格论的RNN剪枝方法论。将RNN建模为偏序集，构建依赖格，识别不可约元进行选择性剪枝。相比传统幅度剪枝更好地保留功能连接性。触发词：RNN剪枝、格剪枝、偏序集、依赖格、不可约元、网络压缩、lattice pruning、poset、meet irreducible。
Langue du texte source : chinois
Distributionally robust free energy principle for reliable robotic control. Jointly learns environment dynamics and rewards while ensuring robustness to epistemic uncertainties. Validated on Franka Research 3 arm manipulation tasks.
Langue du texte source : anglais
Developmental scaffoldings methodology for guiding self-organisation through learned pre-patterns. Joint NCA+SIREN model that offloads information to initial conditions, enabling robustness, encoding capacity, and symmetry breaking improvements. Activation:…
Langue du texte source : anglais
Learning Dynamic Stability Landscapes in Synchronization Networks methodology - graph-to-image prediction paradigm for predicting stability landscapes from network topology. Pioneers image-like per-node stability landscapes beyond scalar indices. Applicable…
Langue du texte source : anglais
Long Context Pre-Training with Lighthouse Attention — NousResearch 提出的对称选择式分层注意力算法。面向超长上下文预训练，通过对称 Q/K/V 金字塔池化、无参数打分 top-K 选择、选择与注意力解耦、两阶段训练，实现 O(N·d) 复杂度。触发词：lighthouse attention, long context pretraining, hierarchical attention, symmetric pooling, sparse…
Langue du texte source : chinois
Design LLM agent systems using the externalization framework from cognitive artifacts theory (Norman). Covers memory externalization (state across time), skills externalization (procedural expertise), protocol externalization (interaction structure), and…
Langue du texte source : anglais
Decision-Centric framework for LLM systems that separates decision signals from action policies. Apply this when designing LLM control flow, routing, adaptive inference, or building diagnosable agent systems.
Langue du texte source : anglais
Methodology for identifying and analyzing functional emotion representations in LLM internals. Covers finding emotion-related neural activity patterns, testing their causal influence via activation steering, and understanding how abstract emotion concepts…
Langue du texte source : anglais
Neuroscience-inspired geometric account of in-context learning (ICL) in LLMs — how representational geometry reshapes to support online untangling and classification without parameter updates.
Langue du texte source : anglais
大型语言模型通过内部置信度信号检测和纠正自身错误的研究。基于决策神经科学二阶置信度模型。
Langue du texte source : chinois
大型语言模型通过内部置信度信号检测和纠正自身错误的研究。基于决策神经科学二阶置信度模型和PANL token机制。
Langue du texte source : chinois