Menu
Skills neste repositório
O SkillsMP coletou 4.114 skills de hiyenwong/ai_collection. Abra uma skill para revisar a origem e os detalhes.
hiyenwong/ai_collectionMostrando 40 de 4.114 skills coletadas.
Eigenspectral decomposition framework for analyzing how information processing capacity (IPC) is distributed across reservoir state-space modes, with degree-wise representation energy and noise-aware capacity metrics for physical reservoir computers.
Idioma do texto original: inglês
Paving the way for agents in biology
Idioma do texto original: inglês
Structure-aware lightweight 3D CNN pre-decoder for scalable surface code quantum error correction. Use when designing or benchmarking neural QEC decoders for surface codes, implementing spatio-temporal syndrome processing, replacing dense 3D convolutions with…
Idioma do texto original: inglês
"Skill for understanding and applying quantum reservoir computing theory based on quantum magic and non-commutativity as computational resources. Use when analyzing QRC architectures, designing quantum reservoir systems, or studying quantum advantages in…
Idioma do texto original: inglês
Real-time optimal control framework using SHallow REcurrent Decoder networks-based Reduced Order Modeling (SHRED-ROM) for high-dimensional and parametric dynamical systems. Enables synthesis of closed-loop controllers from limited state sensor readings with…
Idioma do texto original: inglês
Scalable Training of Continuous-Time Spiking Neural Networks with Differentiable Spike-Time Discretization (DSTD) — reduces memory and training time for deep SNNs via fixed-time discretization and synfire-chain-inspired regularization
Idioma do texto original: inglês
Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs
Idioma do texto original: inglês
SpikingMOT framework for spike-driven multi-object tracking using spiking neural networks. Implements activation sparsity preference (ASP) with adaptive sparse trajectory dynamics modeling, achieving state-of-the-art performance while reducing parameters by…
Idioma do texto original: inglês
A skill for modeling subjective experiences as emergent properties of neural processes based on the mathematical framework of subjective functions. Use this skill when you need to bridge objective neural measurements with subjective reports, model endogenous…
Idioma do texto original: inglês
Framework for understanding nerve pulse propagation using soliton theory, connecting nonlinear wave dynamics to action potential generation and propagation in neurons.
Idioma do texto original: inglês
Search Hardness-Aware LLM-Based Problem Formulation (SHA-PF) framework for expensive simulation-driven design. Prioritizes formulations that guide efficient search by focusing on rare samples with greater progress potential, reducing evaluation requirements…
Idioma do texto original: inglês
Federated Cognitive Digital Twin (FCDT) architecture methodology combining federation and cognition within a unified approach for distributed Cyber-Physical Systems (CPSs).
Idioma do texto original: inglês
Current Injection Spiking Neural Network (CIS-Fuse) for energy-efficient infrared and visible image fusion using membrane-potential level cross-modal integration
Idioma do texto original: inglês
Spectral theory framework for analyzing population density dynamics of spiking neurons with finite refractory time. Provides rigorous operator-theoretic methods for studying neuronal population stability, oscillatory modes, and transfer functions. Use when…
Idioma do texto original: inglês
Spectral theory framework for analyzing population density dynamics of spiking neurons with refractoriness. Provides rigorous mathematical foundation for spectral decomposition methods in computational neuroscience by formulating the problem as a…
Idioma do texto original: inglês
Representing Entity Importance in AI Knowledge Systems: A Dual-Signal Framework of Audience Evaluati (arXiv: 2607.20925)
Idioma do texto original: inglês
GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Dia (arXiv: 2607.21117)
Idioma do texto original: inglês
RUMBA: Russian User Memory Benchmark (arXiv: 2607.21447)
Idioma do texto original: inglês
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment (arXiv: 2607.21550)
Idioma do texto original: inglês
LLMs Get Lost in Evolving User Intent (arXiv: 2607.20734)
Idioma do texto original: inglês
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests (arXiv: 2607.20759)
Idioma do texto original: inglês
Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs (arXiv: 2607.20814)
Idioma do texto original: inglês
Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions (arXiv: 2607.20891)
Idioma do texto original: inglês
Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation (arXiv: 2607.20908)
Idioma do texto original: inglês
SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration (arXiv: 2607.20926)
Idioma do texto original: inglês
The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning (arXiv: 2607.20952)
Idioma do texto original: inglês
Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents (arXiv: 2607.20972)
Idioma do texto original: inglês
GuardianAgentBench: Where Agents Fail and How to Guard Them (arXiv: 2607.20982)
Idioma do texto original: inglês
HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving (arXiv: 2607.20988)
Idioma do texto original: inglês
Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured (arXiv: 2607.20999)
Idioma do texto original: inglês
Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers (arXiv: 2607.21010)
Idioma do texto original: inglês
EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agen (arXiv: 2607.21013)
Idioma do texto original: inglês
HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices (arXiv: 2607.21019)
Idioma do texto original: inglês
Training Large Language Models for Self-Explanation Faithfulness (arXiv: 2607.21090)
Idioma do texto original: inglês
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GN (arXiv: 2607.21094)
Idioma do texto original: inglês
AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning (arXiv: 2607.21106)
Idioma do texto original: inglês
TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning (arXiv: 2607.21111)
Idioma do texto original: inglês
Explainability Framework for Policy-Aware Autonomous Agents (arXiv: 2607.21209)
Idioma do texto original: inglês
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders (arXiv: 2607.21217)
Idioma do texto original: inglês
Search Hardness-Aware LLM-Based Problem Formulation for Expensive Simulation-Driven Design (arXiv: 2607.21220)
Idioma do texto original: inglês