All categories
Research
Research, evidence gathering, literature, reports, investigation, and synthesis
- 21,409
- 893
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse research skills
Showing 11,497–11,520 of 21,409 skills
- Layered Surprise Cascades Predictive CodingLayered Surprise Cascades framework for biologically plausible predictive coding using local contrastive learning and activity cancellation. Implements recurrent Forward-Forward algorithm with inverted objective for negative data to yield predictive representations across layers. Use when modeling cortical computation, top-down modulation, surprise signaling, or building hierarchical predictive systems without error-coding neurons.Votes: 0GitHub stars: 3
- Lattice Field Theory NeuronsLattice Field Theory (LFT) framework for interpreting BCI recordings from real neural networks. Applies physics-based formalism to neural data analysis, connecting Maximum Entropy models with Free Energy Principle.Votes: 0GitHub stars: 3
- Lateral Predictive Coding ModularLateral predictive coding (LPC) framework for feature detection in biological neural circuits with modular network structures. Analyzes response time trade-offs between modular vs non-modular architectures. Activation: predictive coding, neural circuits, modularity, feature detection, response time.Votes: 0GitHub stars: 3
- Latent Revise Zero Hit ReasoningLatentRevise — First-order latent revision method that recovers training signal from zero-hit prompts in RLVR. Optimizes input embeddings of failed reasoning prefixes under dual gradients (away from failed continuation, toward gold answer), constrained to vocabulary embedding convex hull.Votes: 0GitHub stars: 3
- Language Models Need SleepSleep paradigm for LLMs that enables continual learning through memory consolidation and dreaming phases. Use when: (1) implementing continual learning for LLMs; (2) designing memory consolidation mechanisms; (3) creating autonomous self-improvement systems; (4) addressing catastrophic forgetting in sequential tasks; (5) developing RL-based curriculum generation for synthetic data. Trigger words: sleep paradigm, memory consolidation, dreaming process, knowledge seeding, LLM sleep.Votes: 0GitHub stars: 3
- Landau Ginzburg Sleep Stage TransitionsMethodology for modeling sleep-stage transitions using Landau-Ginzburg phenomenology with spatially extended neural fields, treating different sleep boundaries as distinct phase transitions (fold, crossover, first-order-like switch).Votes: 0GitHub stars: 3
- Lacuna Llm Unlearning TestbedLACUNA testbed methodology for evaluating LLM unlearning localization precision. Use when assessing whether unlearning truly erases knowledge from model parameters or merely obfuscates it, benchmarking unlearning methods, detecting resurfacing attacks, or implementing parameter-level knowledge removal in large language models. Activation: LLM unlearning, knowledge erasure, parameter localization, resurfacing attack, post-hoc removal, PII removal, gradient-based unlearningVotes: 0GitHub stars: 3
- Unifying Dynamics Graph Neural ComputationFramework unifying dynamical systems and graph theory to mechanistically understand computation in neural networks. Uses resolvent-based multi-hop pathway analysis to recover input-output routing structure from connectivity, introduces R-RNNs with resolvent-based regularization for temporally structured sparsity. Activation: multi-hop, resolvent RNN, graph computation, neural network interpretability, structure-function mapping, temporal routing, R-RNN, network communication.Votes: 0GitHub stars: 3
- Nope Non Selfish Graph CoarseningNOPE graph coarsening methodology using non-selfishness principle for near-linear complexity graph dimensionality reduction, replacing pairwise similarity matching.Votes: 0GitHub stars: 3
- Neuron Soup Shared Neuron Temporal Graphpopulation = initialize_population(pop_size=100, genome_len=14602) for gen in range(max_generations): fitnesses = [] for genome in population: substrate = decode_genome(genome) # paths, weights, delays outputs = simulate(substrate, batch_X) loss = compute_loss(outputs, batch_y) fitnesses.append(-loss) # higher is better population = evolve(population, fitnesses) # select, crossover, mutate best_substrate = decode_genome(argmax(fitnesses)) ``` - Replace the genetic algorit...Votes: 0GitHub stars: 3
- Mpp Gnn Subject Adaptive Community DetectionMPP-GNN: Subject-Adaptive Community Detection for fMRI-Based Alzheimer's Disease ClassificationVotes: 0GitHub stars: 3
- Motif Based Filtrations Persistent Homology Framework GraphResearch methodology from paper 'Motif-based filtrations for persistent homology: A framework for graph isomorphism and property prediction'. arXiv:2604.15265v1. Covers key techniques and approaches for neuroscience research. Activation: motif, based, filtrations, math.ATVotes: 0GitHub stars: 3
- Kg Research WorkflowEnd-to-end academic research workflow using knowledge graphs. Searches papers from arxiv/web, imports to KG database, generates embeddings, runs graph algorithms (PageRank, vector search), and extracts patterns for skill creation. Use for: automated research workflows, paper analysis pipelines, KG-based literature review.Votes: 0GitHub stars: 3
- Explicit World Model Based Data First Ontology Daoql Multimodal Storage Validation CounteSkill derived from arXiv:2607.17269 - An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and CounteVotes: 0GitHub stars: 3
- Kinematic Zero Shot Bci DecodingZero-shot handwriting BCI decoding via conserved kinematic representations. Aligns neural activity to imagined kinematics for open-vocabulary character decoding without per-character training data. Activation: zero-shot BCI, handwriting decoding, kinematic primitives, intracortical BCI, logographic language BCI, motor cortex representation, imagined handwriting.Votes: 0GitHub stars: 3
- Kg Research WorkflowEnd-to-end academic research workflow using knowledge graphs. Searches papers from arxiv/web, imports to KG database, generates embeddings, runs graph algorithms (PageRank, vector search), and extracts patterns for skill creation. Use for: automated research workflows, paper analysis pipelines, KG-based literature review.Votes: 0GitHub stars: 3
- Jedi Neural Dynamics InferenceJEDI: Jointly Embedded Inference of Neural Dynamics - learning shared embeddings of RNN weights to infer neural population dynamics across tasks and contexts. Triggers: neural dynamics inference, RNN embedding, meta-learning, neural population, cross-task generalization.Votes: 0GitHub stars: 3
- Jaynes Cummings Oscillator ControlUniversal Jaynes-Cummings (JC) based oscillator control methodology for bosonic quantum processors. Compiles arbitrary unitary gates into JC interaction sequences and qubit rotations for universal qudit control.Votes: 0GitHub stars: 3
- Intrinsic Noise Consolidation DoobDoob-Barrier-Conditioned Diffusion methodology for turning analog neuromorphic device noise into a continual-learning consolidation resource. Casts per-synapse consolidation as a Doob h-transform: condition each weight's stochastic dynamics on never crossing a memory-critical barrier. Activation: intrinsic noise consolidation, Doob barrier diffusion, noise as continual learning resource, neuromorphic consolidation, Doob h-transform synaptic, analog noise memory consolidation.Votes: 0GitHub stars: 3
- Intrinsic Neuro Synaptic MemristiveMemristive networks intrinsic neuro-synaptic spiking dynamics methodology. Self-organizing circuits generating neuronal population dynamics similar to biological systems with nonlinear resonance phenomena. Trigger words: memristive, neuro-synaptic, spiking dynamics, resonance.Votes: 0GitHub stars: 3
- Interpretable Meg Decoding Perceived SpeechInterpretable MEG decoding framework for perceived speech that combines spherical harmonics spatial attention, source-space mapping, and stimulus feature analysis to reveal what drives neural-to-audio retrieval. Use when implementing or analyzing MEG-based brain decoding systems, particularly for speech perception, neural source localization, or interpretable brain-computer interfaces.Votes: 0GitHub stars: 3
- Interpretable Eeg Biomarkers ParkinsonsInterpretable EEG biomarkers for Parkinson's disease detection using interpretable electrophysiological features of resting-state EEG. Captures cortical neural dynamics alterations for reliable non-invasive diagnosis and monitoring. Activation: EEG biomarker Parkinson's, interpretable EEG features, resting-state EEG, cortical neural dynamics, PD diagnosis.Votes: 0GitHub stars: 3
- Interdisciplinary DiscoveryDiscover interdisciplinary research connections using knowledge graph analysis (PageRank, Louvain, vector similarity). Use when analyzing cross-domain research, finding unexpected connections, or exploring interdisciplinary patterns. Keywords: 跨学科发现, interdisciplinary discovery, kg analysis, 知识图谱分析, find research connections, discover cross-domain patterns.Votes: 0GitHub stars: 3
- Interbrain Networks GeometryGeometric framework for analyzing inter-brain networks in social neuroscience. Uses discrete geometry and curvature distributions to identify critical transitions in neural connectivity during social interactions, moving beyond correlation-based synchrony metrics. Activation: inter-brain networks, hyperscanning, social neuroscience, discrete geometry, curvature, network topology, synchrony, social interaction, EEG, fNIRSVotes: 0GitHub stars: 3