Research

Research, evidence gathering, literature, reports, investigation, and synthesis

skills in category: 21,402
pages available: 892

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 browser

Browse research skills

Showing 10,369–10,392 of 21,402 skills

Karma Mechanisms Decentralised CooperativeAMulti-Agent Path Finding (MAPF) is a fundamental coordination problem in large-scale robotic and cyber-physical systems, where multiple agents must compute conflict-free trajectori... Activation: multi-agentresearchgoVotes: 0GitHub stars: 3
Arxiv 2608 06262v1 Hypothesis Testing With Conditional Queries LearnaA**arXiv ID:** 2608.06262v1 **Authors:** Zonghuan Xu **URL:** http://arxiv.org/abs/2608.06262v1 **Utility Score:** 1.00researchtestingVotes: 0GitHub stars: 3
Snn Elephant ReinforcementASpiking Neural Networks with Elephant Reinforcement — finite stochastic SNN with memory-dependent threshold that modifies future excitability based on past firing activity.researchVotes: 0GitHub stars: 3
State Space Ntk Collapse BifurcationsALocal theory of gradient descent near bifurcations via state-space neural tangent kernel (sNTK). Bifurcations collapse sNTK to rank-one operators corresponding to classical normal forms, funneling gradient descent into critical dynamical directions. Use when: analyzing RNN learning dynamics near bifurcations, studying NTK collapse, understanding gradient-based training of recurrent systems, bifurcation analysis in deep learning, neural tangent kernel for temporal tasks, normal form learning t...researchgonodeVotes: 0GitHub stars: 3
Score Matching Gradient DecompositionAGeometric decomposition of score matching errors in diffusion models using Helmholtz-Hodge decomposition. Proves that only gradient components affect marginal distribution quality, while solenoidal components are structurally invisible to Fokker-Planck dynamics.researchgoVotes: 0GitHub stars: 3
Scalable Memristivefriendly Reservoir Computing Time SeriesAdynamics memristive reservoir computing methodology from arXiv:2604.19343. Memristive devices present a promising foundation for next-generation information processing by combining memory and computation within a single physi... Activation: dynamics, memristive, reservoir computingresearchpythongoVotes: 0GitHub stars: 3
Scalable Memristive Friendly Reservoir Computing Time SeriesAScalable memristor-friendly reservoir computing for time series classification. Optimized for hardware implementation with memristor crossbar arrays. Triggers: memristive, reservoir computing, time series, hardware-friendly, memristor crossbar.researchpythongoVotes: 0GitHub stars: 3
Safe Large Scale Robust Nonlinear MpcAWe present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC) that scales to high-dimensional uncertain robotic systems and long planni... Activation: safe, large, scale, robust, nonlinearresearchgoVotes: 0GitHub stars: 3
Reasoning Models Struggle To Control Their ChainsASkill for AI agent capabilitiesresearchpythongoVotes: 0GitHub stars: 3
Pruning By Active Attention ManipulationA**arXiv ID:** 2210.11114 **Authors:** Zahra Babaiee, Lucas Liebenwein, Ramin Hasani, Daniela Rus, Radu Grosu **Published:** 2022-10-20T09:17:02Z **Abstract:** Filter pruning of a CNN is typically achieved by applying discrete masks on the CNN's filter weights or activation maps, post-training. Here, we present a new filter-importance-scoring concept named pruning by active attention manipulation (PAAM), that sparsifies the CNN's set of filters through a particular attention mechanism, during-...researchVotes: 0GitHub stars: 3
Prediction And Control With Temporal Segment ModelASkill for AI agent capabilitiesresearchpythongoVotes: 0GitHub stars: 3
Observer World CryptographyACryptographic extension of Impagliazzo's Five Worlds introducing the observational axis — models how restricted observation hierarchies affect cryptographic primitive existence and security guarantees.researchgogitVotes: 0GitHub stars: 3
Learning Adaptive Solvers For Distributed Factor Graph OptimizationALearning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups. Modern robotic perception increasingly involves large-scale geometric optimization problems distributed across multiple robots or sessions. However, existing distributed solvers often depend on brittl... Activation: graph, self-supervised, benchmark, alignment, optimizationresearchgoperformanceVotes: 0GitHub stars: 3
Highfidelity Networkbased Spatiotemporal Mathematical Models AlzAHigh-fidelity network-based spatio-temporal PDE mathematical models for Alzheimer's disease progression with amyloid-beta and tau propagation. Activation: brain model, neural scaling, multimodal brain, fMRI, EEG, neural encoding.researchpythongoVotes: 0GitHub stars: 3
Firing Rate Nn Model Predictive ControlASkill for firing rate nn model predictive controlresearchgoperformanceVotes: 0GitHub stars: 3
Ei Network Chaos Synchrony TheoryAExtended Sompolinsky-Crisanti-Sommers (SCS) chaos theory framework for excitatory-inhibitory (E-I) recurrent networks with target-specific inhibition. Covers dynamical mean-field analysis, phase diagrams, mean-driven and fluctuation-driven instabilities, and the suppression of chaos by coherent oscillations. Use when analyzing E/I balance in neural networks, studying chaos-to-order transitions in recurrent networks, modeling target-specific inhibition effects, extending SCS theory to structur...researchpythonVotes: 0GitHub stars: 3
Dmosopt Neural Dynamical SystemsADMOSOPT: Joint surrogate learning framework for multi-objective optimization of neural dynamical systems. Learns objectives, constraints, and sensitivities simultaneously. Activation: multi-objective optimization, neural dynamics, surrogate model, parameter optimizationresearchgoVotes: 0GitHub stars: 3
Data Driven Distributed Mpc BuildingsAData-driven methodology for scalable distributed MPC in heterogeneous building aggregation - feature selection to convex optimizationresearchpythonVotes: 0GitHub stars: 3
Arxiv 2608 20337 Information On Trajectories Martingales And RandomAInformation on trajectories: martingales and random times (arXiv: 2608.20337)researchgotestingVotes: 0GitHub stars: 3
Arxiv 2608 20290 Phantom Gains Auditing Self Improvement Against AAPhantom Gains: Auditing Self-Improvement Against a Measured Null (arXiv: 2608.20290)researchgotestingVotes: 0GitHub stars: 3
Arxiv 2608 20123 Discrete Diffusion Inference Time Control With NesADiscrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo (arXiv: 2608.20123)researchgoVotes: 0GitHub stars: 3
Arxiv 2608 19879 A Repeated Measurements Approach To Soh Battery MoAA Repeated Measurements Approach to $SoH$ Battery Modelling of Cyclic Aged Data in a Laboratory Environment (arXiv: 2608.19879)researchgoexpressVotes: 0GitHub stars: 3
Toward A Neuroinspired Creative DecoderA**arXiv ID:** 1902.02399 **Authors:** Payel Das, Brian Quanz, Pin-Yu Chen, Jae-wook Ahn, Dhruv Shah **Published:** 2019-02-06T21:06:58Z **Abstract:** Creativity, a process that generates novel and meaningful ideas, involves increased association between task-positive (control) and task-negative (default) networks in the human brain. Inspired by this seminal finding, in this study we propose a creative decoder within a deep generative framework, which involves direct modulation of the neuronal...researchVotes: 0GitHub stars: 3
Temporally Coherent Video Anonymization Through Gan InpaintingA**arXiv ID:** 2106.02328 **Authors:** Thangapavithraa Balaji, Patrick Blies, Georg Göri, Raphael Mitsch, Marcel Wasserer, Torsten Schön **Published:** 2021-06-04T08:19:44Z **Abstract:** This work tackles the problem of temporally coherent face anonymization in natural video streams.We propose JaGAN, a two-stage system starting with detecting and masking out faces with black image patches in all individual frames of the video. The second stage leverages a privacy-preserving Video Generative Ad...researchVotes: 0GitHub stars: 3