Menu
Skills in this repository
SkillsMP has collected 4,114 skills from hiyenwong/ai_collection. Open a skill to review its source and details.
hiyenwong/ai_collectionShowing 40 of 4,114 collected skills.
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.
Paving the way for agents in biology
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…
"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…
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…
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
Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs
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…
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…
Framework for understanding nerve pulse propagation using soliton theory, connecting nonlinear wave dynamics to action potential generation and propagation in neurons.
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…
Federated Cognitive Digital Twin (FCDT) architecture methodology combining federation and cognition within a unified approach for distributed Cyber-Physical Systems (CPSs).
Current Injection Spiking Neural Network (CIS-Fuse) for energy-efficient infrared and visible image fusion using membrane-potential level cross-modal integration
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…
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…
Representing Entity Importance in AI Knowledge Systems: A Dual-Signal Framework of Audience Evaluati (arXiv: 2607.20925)
GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Dia (arXiv: 2607.21117)
RUMBA: Russian User Memory Benchmark (arXiv: 2607.21447)
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment (arXiv: 2607.21550)
LLMs Get Lost in Evolving User Intent (arXiv: 2607.20734)
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests (arXiv: 2607.20759)
Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs (arXiv: 2607.20814)
Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions (arXiv: 2607.20891)
Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation (arXiv: 2607.20908)
SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration (arXiv: 2607.20926)
The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning (arXiv: 2607.20952)
Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents (arXiv: 2607.20972)
GuardianAgentBench: Where Agents Fail and How to Guard Them (arXiv: 2607.20982)
HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving (arXiv: 2607.20988)
Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured (arXiv: 2607.20999)
Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers (arXiv: 2607.21010)
EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agen (arXiv: 2607.21013)
HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices (arXiv: 2607.21019)
Training Large Language Models for Self-Explanation Faithfulness (arXiv: 2607.21090)
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GN (arXiv: 2607.21094)
AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning (arXiv: 2607.21106)
TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning (arXiv: 2607.21111)
Explainability Framework for Policy-Aware Autonomous Agents (arXiv: 2607.21209)
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders (arXiv: 2607.21217)
Search Hardness-Aware LLM-Based Problem Formulation for Expensive Simulation-Driven Design (arXiv: 2607.21220)