Menú
Skills en este repositorio
SkillsMP ha recopilado 4114 skills de hiyenwong/ai_collection. Abre una skill para revisar su origen y sus detalles.
hiyenwong/ai_collectionMostrando 40 de 4114 skills recopiladas.
Skill generated from arXiv paper 2607.19962: EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.20382: FMRP-LEAN: A HIPAA-Compliant AI-Augmented LIMS Architecture for End-to-End Clinical Assay Workflow Optimization
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.19913: JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.19592: Knowledge-Centric Self-Improvement
Idioma del texto original: inglés
Skill for applying the methods from the arXiv paper: Structured Fluctuations and the Information Dynamics of Self-Maintenance in Growing Neural Cellular Automata (arXiv:2607.12403). This skill provides a framework for analyzing internal fluctuations in neural…
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.19739: Personalized Recommendation Tool Learning via Autonomous Language Agents
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.20002: Post-Training in Time Series Foundation Models: A Unifying Framework
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.20064: PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
Idioma del texto original: inglés
Methodology for evaluating autonomous AI capability progression across phases — measuring when models transition from human-assisted to autonomous execution using robotics tasks as a benchmark.
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.19949: SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.20145: SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.20216: Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis
Idioma del texto original: inglés
Spatial Neighboring Scattering Transform (SNST) — a wavelet-scattering-based cross-channel amplitude-coupling measure for EEG connectivity that captures amplitude-envelope and cross-frequency coupling, robust to volume conduction where phase-sync fails. Use…
Idioma del texto original: inglés
SpectralOT — a geometry-aware, spectral optimal-transport functional alignment method for fMRI that embeds cortical surface geometry (Laplace-Beltrami eigenmodes) into the alignment cost to regularize cross-subject alignment while preserving anatomical…
Idioma del texto original: inglés
Method for geometry-aware functional alignment of fMRI data using SpectralOT to improve cross-subject decoding by embedding cortical geometry into Laplace-Beltrami eigenmodes.
Idioma del texto original: inglés
Synthesize parameters for nonlinear dynamical systems that robustly satisfy continuous-time Signal Temporal Logic (STL) specifications over uncertain initial conditions. Combines gradient-based optimization with set-based reachability verification for…
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.20174: StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.19524: SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.19749: The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
Idioma del texto original: inglés
Skill generated from arXiv paper 2607.19967: When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Markets
Idioma del texto original: inglés
Methodology for universal quantum computation using dissipatively stabilized multi-mode Schrödinger cat states via non-local dissipation engineering, based on arXiv:2607.13975.
Idioma del texto original: inglés
A skill for implementing efficient and robust spiking neural networks for surface electromyography (sEMG) based muscle fatigue detection, based on arXiv:2607.11065
Idioma del texto original: inglés
Spiking Neural Network (SNN) architecture for generating polar trajectories on neuromorphic hardware, using a winner-take-all (WTA) core with accessory populations that induce controlled transitions in neural activity. Interpretable at the level of system…
Idioma del texto original: inglés
Non-equilibrium thermodynamic framework linking quantum reservoir computing performance to energetic costs, establishing fundamental limits for quantum neuromorphic hardware.
Idioma del texto original: inglés
Skill derived from arXiv:2607.17015 - Alignment of a Total Automation Economy
Idioma del texto original: inglés
Skill derived from arXiv:2607.17701 - ProEvent: An Event-centric Benchmark for Proactive Agents
Idioma del texto original: inglés
Skill derived from arXiv:2607.17352 - Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution
Idioma del texto original: inglés
Skill derived from arXiv:2607.17149 - A Diagnostic Framework for AI Agent Behavior
Idioma del texto original: inglés
Skill derived from arXiv:2607.17780 - ETAS: An Effect-Typed Language for Agent Systems
Idioma del texto original: inglés
Skill derived from arXiv:2607.18147 - LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications
Idioma del texto original: inglés
Skill derived from arXiv:2607.17621 - Mechanistic Attention Guidance for Agent Memory Refinement
Idioma del texto original: inglés
Skill derived from arXiv:2607.17917 - PEARL: Auditable Repair for Scientific Reasoning Graph Extraction
Idioma del texto original: inglés
Skill derived from arXiv:2607.16989 - Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries
Idioma del texto original: inglés
Skill derived from arXiv:2607.17560 - Reinforcement Learning: From Algorithms To Foundation Models
Idioma del texto original: inglés
Skill derived from arXiv:2607.17951 - RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control
Idioma del texto original: inglés
Skill derived from arXiv:2607.17288 - SAGA: Synthetic Agentic Graph Architecture for Temporal Benchmark Generation
Idioma del texto original: inglés
Skill derived from arXiv:2607.18161 - TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization
Idioma del texto original: inglés
Skill derived from arXiv:2607.17299 - WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning
Idioma del texto original: inglés
Skill derived from arXiv:2607.18063 - Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
Idioma del texto original: inglés
Skill derived from arXiv:2607.17247 - Distilled Reinforcement Learning for LLM Post-training
Idioma del texto original: inglés