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.
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.
Langue du texte source : anglais
Paving the way for agents in biology
Langue du texte source : anglais
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…
Langue du texte source : anglais
"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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
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
Langue du texte source : anglais
Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Framework for understanding nerve pulse propagation using soliton theory, connecting nonlinear wave dynamics to action potential generation and propagation in neurons.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Federated Cognitive Digital Twin (FCDT) architecture methodology combining federation and cognition within a unified approach for distributed Cyber-Physical Systems (CPSs).
Langue du texte source : anglais
Current Injection Spiking Neural Network (CIS-Fuse) for energy-efficient infrared and visible image fusion using membrane-potential level cross-modal integration
Langue du texte source : anglais
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…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Representing Entity Importance in AI Knowledge Systems: A Dual-Signal Framework of Audience Evaluati (arXiv: 2607.20925)
Langue du texte source : anglais
GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Dia (arXiv: 2607.21117)
Langue du texte source : anglais
RUMBA: Russian User Memory Benchmark (arXiv: 2607.21447)
Langue du texte source : anglais
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment (arXiv: 2607.21550)
Langue du texte source : anglais
LLMs Get Lost in Evolving User Intent (arXiv: 2607.20734)
Langue du texte source : anglais
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests (arXiv: 2607.20759)
Langue du texte source : anglais
Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs (arXiv: 2607.20814)
Langue du texte source : anglais
Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions (arXiv: 2607.20891)
Langue du texte source : anglais
Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation (arXiv: 2607.20908)
Langue du texte source : anglais
SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration (arXiv: 2607.20926)
Langue du texte source : anglais
The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning (arXiv: 2607.20952)
Langue du texte source : anglais
Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents (arXiv: 2607.20972)
Langue du texte source : anglais
GuardianAgentBench: Where Agents Fail and How to Guard Them (arXiv: 2607.20982)
Langue du texte source : anglais
HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving (arXiv: 2607.20988)
Langue du texte source : anglais
Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured (arXiv: 2607.20999)
Langue du texte source : anglais
Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers (arXiv: 2607.21010)
Langue du texte source : anglais
EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agen (arXiv: 2607.21013)
Langue du texte source : anglais
HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices (arXiv: 2607.21019)
Langue du texte source : anglais
Training Large Language Models for Self-Explanation Faithfulness (arXiv: 2607.21090)
Langue du texte source : anglais
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GN (arXiv: 2607.21094)
Langue du texte source : anglais
AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning (arXiv: 2607.21106)
Langue du texte source : anglais
TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning (arXiv: 2607.21111)
Langue du texte source : anglais
Explainability Framework for Policy-Aware Autonomous Agents (arXiv: 2607.21209)
Langue du texte source : anglais
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders (arXiv: 2607.21217)
Langue du texte source : anglais
Search Hardness-Aware LLM-Based Problem Formulation for Expensive Simulation-Driven Design (arXiv: 2607.21220)
Langue du texte source : anglais