Design & UX

Uncertainty-Guided Hypergraph Refinement (UGHR) methodology for medical image segmentation. Uses entropy-based uncertainty maps from coarse predictions to spatially guide targeted refinement in boundary/transition regions. Decouples foreground/background hyperedge prototypes to prevent noise propagation. Use when performing medical image segmentation with ambiguous boundaries, small lesions, or ill-defined edges.

TurboVLA architecture for real-time vision-language-action models achieving 32 Hz inference with <1 GB VRAM. Reformulates conventional V→L→A pathway as direct V+L→A mapping with lightweight bidirectional vision-language interaction. Use when building efficient robotic manipulation systems, real-time VLA policies, or low-resource embodied AI agents.

A skill for understanding and applying the computational phenomenology of focused-attention meditation based on the arXiv paper "Thoughtseeds as Latent Causes: A Dual-Process Computational Phenomenology of Focused-Attention Meditation" (arXiv:2607.14833v1).

Hierarchical control design via approximate simulation relations (ε-gAAS). Enables abstraction-based controller synthesis for continuous-time nonlinear systems with formal error bounds and control refinement guarantees. Use when: (1) designing controllers for complex continuous-time systems via model abstraction, (2) needing formal guarantees that abstract controllers transfer to concrete systems, (3) working with simulation relations for control refinement, (4) building hierarchical control ...

Efficient fault-tolerant ancilla preparation for quantum BCH codes via cyclic symmetry. Two-stage approach using non-fault-tolerant preparation + entanglement distillation with cyclic symmetry exploitation. arXiv: 2605.19471.

Arbitrary temporal waveform control of single photons during spontaneous emission. Methodology for shaping photon wavepackets to optimize quantum state transfer in hybrid quantum systems. Applicable to quantum networking, atom-photon interfaces, and quantum memory protocols.

Programmable superconducting neuron with intrinsic in-memory computation and dual-timescale plasticity for ultra-efficient neuromorphic computing using Josephson junctions.

神经突触可塑性随机模型框架。基于STDP规则的突触权重演化数学模型，引入塑性核概念表示不同STDP规则，使用随机过程分析神经元-突触系统动力学。适用于计算神经科学、突触可塑性建模、STDP学习规则。触发词：突触可塑性、STDP、塑性核、突触权重、随机模型、synaptic plasticity、STDP、plasticity kernel、Hebbian learning。

STAMBRIDGE: Spectral-Temporal Amplitude-aware Mid-Feature Bridge for EEG Visual Decoding. Two-stage framework combining Spectral-Temporal Amplitude-aware Modulation (STAM) and Mid-Feature Semantic Bridge (MFSB) for zero-shot EEG-to-image retrieval and reconstruction. Achieves 34.50% Top-1 on THINGS-EEG. Activation: EEG visual decoding, EEG-to-image, zero-shot EEG retrieval, spectral-temporal modulation, brain-computer interface

Spiking neural network control framework based on the Free Energy Principle (FEP) and Active Inference. Neurons fire only when they reduce free energy of internal representation, achieving highly sparse activity with robust control. Matches performance of non-spiking frameworks while offering resilience against sensory noise, synaptic noise, delays, and neuron silencing. Use when designing spiking control systems, neuromorphic control algorithms, active inference with SNNs, energy-efficient r...

Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks. Activation: neuronal, selfadaptation, enhances, capacity, robustness

Skill summarizing the 32-channel event-based bio-signal analog front-end with adaptive delta and pulse frequency encoding for neuromorphic signal processing.

Spiking neural network control framework based on the Free Energy Principle (FEP) and Active Inference. Neurons fire only when they reduce free energy of internal representation, achieving highly sparse activity with robust control. Matches performance of non-spiking frameworks while offering resilience against sensory noise, synaptic noise, delays, and neuron silencing. Use when designing spiking control systems, neuromorphic control algorithms, active inference with SNNs, energy-efficient r...

Uncertainty-Guided Hypergraph Refinement (UGHR) methodology for medical image segmentation. Uses entropy-based uncertainty maps from coarse predictions to spatially guide targeted refinement in boundary/transition regions. Decouples foreground/background hyperedge prototypes to prevent noise propagation. Use when performing medical image segmentation with ambiguous boundaries, small lesions, or ill-defined edges.

Spatiotemporal TDANN for modeling self-organized MT direction selectivity maps in the dorsal stream. Uses 3D ResNet with Momentum Contrast (MoCo) self-supervised learning and biological spatial loss to produce direction-selective pinwheel structures matching macaque MT physiology. Use when modeling cortical topographic self-organization, dorsal stream computation, direction selectivity, or spatiotemporal contrastive learning for visual neuroscience. arXiv: 2605.11718 (q-bio.NC, cs.AI, cs.NE)....

Hierarchical control design via approximate simulation relations (ε-gAAS). Enables abstraction-based controller synthesis for continuous-time nonlinear systems with formal error bounds and control refinement guarantees. Use when: (1) designing controllers for complex continuous-time systems via model abstraction, (2) needing formal guarantees that abstract controllers transfer to concrete systems, (3) working with simulation relations for control refinement, (4) building hierarchical control ...

Efficient fault-tolerant ancilla preparation for quantum BCH codes via cyclic symmetry. Two-stage approach using non-fault-tolerant preparation + entanglement distillation with cyclic symmetry exploitation. arXiv: 2605.19471.

Coupling-phase engineering methodology for giant-atom waveguide QED systems. Uses coupling phase to control bound states in the continuum (BICs) and quantum dynamics in nonlocal light-matter interfaces. Applicable to quantum information processing, giant-atom quantum networks, and interference-based quantum state control.

**arXiv ID:** 1803.09760 **Authors:** Andrew Jaegle, Oleh Rybkin, Konstantinos G. Derpanis, Kostas Daniilidis **Published:** 2018-03-26T18:00:07Z **Abstract:** An intelligent observer looks at the world and sees not only what is, but what is moving and what can be moved. In other words, the observer sees how the present state of the world can transform in the future. We propose a model that predicts future images by learning to represent the present state and its transformation given only a s...

**arXiv ID:** 1707.06992 **Authors:** S. Hossein Hosseini, Afshin Ebrahimi **Published:** 2017-07-21T17:53:04Z **Abstract:** A population-based optimization algorithm was designed, inspired by two main thinking modes in philosophy, both based on dialectic concept and thesis-antithesis paradigm. They impose two different kinds of dialectics. Idealistic and materialistic antitheses are formulated as optimization models. Based on the models, the population is coordinated for dialectical interact...

REVE (Representation for EEG with Versatile Embeddings) - EEG foundation model trained on 60,000 hours from 25,000 subjects with novel 4D positional encoding for arbitrary electrode configurations. Achieves SOTA on 10 downstream tasks. Activation triggers: EEG foundation model, REVE, versatile embeddings, 4D positional encoding, cross-dataset EEG, brain-computer interface.

Skill Reward Model (Skill-RM) framework for unified reward modeling in RL pipelines. Treats reward computation as structured agentic task orchestrating heterogeneous evaluation criteria.

Uncertainty-Guided Hypergraph Refinement (UGHR) methodology for medical image segmentation. Uses entropy-based uncertainty maps from coarse predictions to spatially guide targeted refinement in boundary/transition regions. Decouples foreground/background hyperedge prototypes to prevent noise propagation. Use when performing medical image segmentation with ambiguous boundaries, small lesions, or ill-defined edges.

Topological quantum gate design using Majorana fermion motion methodology. Develops planar Pauli stabilizer codes and logical gate protocols via point-like Majorana fermions. Information stored in pairwise fermion parity, enabling fault-tolerant quantum computation through topological protection. Activation: Majorana fermion, topological quantum computing, Pauli stabilizer, logical gate design, quantum error correction, topological protection