Research

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

skills in category: 21,385
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 11,929–11,952 of 21,385 skills

Vlms Human Alignment Natural ReadingAResearch methodology comparing LLM and VLM alignment with human brain responses during natural reading. Uses controlled text-only evaluation to isolate multimodal training effects. Based on arXiv:2605.28818 (May 2026). Use when studying VLM vs LLM alignment, human brain-model comparison, natural reading fMRI, eye-tracking alignment, or visual semantic content effects on language models.researchgoangularVotes: 0GitHub stars: 3
Untrained Cnn V1 Alignment RsaASystematic RSA comparison showing that untrained CNNs achieve V1/V2 alignment comparable to backpropagation-trained networks. Reveals architecture-driven vs objective-driven cortical alignment across visual hierarchy.researchpythongoVotes: 0GitHub stars: 3
Untrained Cnn V1 Alignment ComparisonASystematic RSA comparison showing untrained CNNs match backpropagation-trained networks at V1 visual cortex representations. Activation: brain model, neural scaling, multimodal brain, fMRI, EEG, neural encoding.researchpythongoVotes: 0GitHub stars: 3
Unified Neural Scaling LawsAUnified Neural Scaling Laws (UNSL) methodology for modeling and extrapolating deep neural network scaling behaviors across multiple dimensions (parameters, data size, compute, hyperparameters). Use when analyzing or predicting model performance scaling, optimizing resource allocation across dimensions, or extrapolating training/inference costs for large models. Applicable to vision, language, math, and RL tasks.researchpythonawsVotes: 0GitHub stars: 3
Teaching Claude Why AlignmentAAlignment training methodology teaching models to explain their reasoning rather than just correct actions. Demonstrates 28x efficiency improvement through out-of-distribution training and constitution-based reasoning.researchgoperformanceVotes: 0GitHub stars: 3
Supervised Feature Selection With Neuron Evolution In Sparse Neural NetworksA**arXiv ID:** 2303.07200 **Authors:** Zahra Atashgahi, Xuhao Zhang, Neil Kichler, Shiwei Liu, Lu Yin, Mykola Pechenizkiy, Raymond Veldhuis, Decebal Constantin Mocanu **Published:** 2023-03-10T17:09:55Z **Abstract:** Feature selection that selects an informative subset of variables from data not only enhances the model interpretability and performance but also alleviates the resource demands. Recently, there has been growing attention on feature selection using neural networks. However, existi...researchgitperformanceVotes: 0GitHub stars: 3
Stochastic Configuration Machines Fpga ImplementationA**arXiv ID:** 2310.19225 **Authors:** Matthew J. Felicetti, Dianhui Wang **Published:** 2023-10-30T02:04:20Z **Abstract:** Neural networks for industrial applications generally have additional constraints such as response speed, memory size and power usage. Randomized learners can address some of these issues. However, hardware solutions can provide better resource reduction whilst maintaining the model's performance. Stochastic configuration networks (SCNs) are a prime choice in industrial a...researchgonodeVotes: 0GitHub stars: 3
Speaker Fuzzy Fingerprints Benchmarking Textbased Identification In Multiparty DialoguesA**arXiv ID:** 2504.14963 **Authors:** Rui Ribeiro, Luísa Coheur, Joao P. Carvalho **Published:** 2025-04-21T08:44:33Z **Abstract:** Speaker identification using voice recordings leverages unique acoustic features, but this approach fails when only textual data is available. Few approaches have attempted to tackle the problem of identifying speakers solely from text, and the existing ones have primarily relied on traditional methods. In this work, we explore the use of fuzzy fingerprints from ...researchperformanceVotes: 0GitHub stars: 3
Solarchain Eval A Physics Constrained Benchmark For TrustworthyASolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets. As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy markets, auton... Activation: agent, agentic, llm, benchmark, safetyresearchrustgoVotes: 0GitHub stars: 3
Self Modifying Lean Proof Agents Verifier Grounded Benchmark CoevolutionASkill derived from arXiv:2607.17352 - Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark CoevolutionresearchVotes: 0GitHub stars: 3
Scaling Laws Expressive Neurons RecurrentAInformation-theoretic framework for optimal parameter allocation between neuron count (N), per-unit complexity (k_e), and connectivity (k_c) in recurrent networks. Introduces Expressive Leaky Memory (ELM) neurons for independent tuning of complexity vs width vs connectivity.researchpythongoVotes: 0GitHub stars: 3
Robust Evaluation Neural Encoding Models GroundtruthAEncoding models enable measurement of how our brains represent sensory inputs using electro-and magneto-encephalography (MEEG). Evaluating how closely encoding models reflect the underlying brain functions is a crucial premise for model interpretatio Activation: brain, neural, eeg, encoding, codingresearchgotestingVotes: 0GitHub stars: 3
Retrieval Based Brain Decoding AlignmentARetrieval-Based Brain Decoding by Alignment, not Complexity. Linear contrastive decoders outperform ridge regression and non-linear alternatives across images, text, and sound. Decoding gains arise from training objective choice, not architectural complexity.researchpythonperformanceVotes: 0GitHub stars: 3
Recurrent Neural Networks Learn To Store And Generate Sequences Using Nonlinear RepresentationsA**arXiv ID:** 2408.10920 **Authors:** Róbert Csordás, Christopher Potts, Christopher D. Manning, Atticus Geiger **Published:** 2024-08-20T15:04:37Z **Abstract:** The Linear Representation Hypothesis (LRH) states that neural networks learn to encode concepts as directions in activation space, and a strong version of the LRH states that models learn only such encodings. In this paper, we present a counterexample to this strong LRH: when trained to repeat an input token sequence, gated recurrent...researchVotes: 0GitHub stars: 3
Project Glasswing Vulnerability DiscoveryAMethodology from Anthropic's Project Glasswing — using frontier AI models for large-scale cybersecurity vulnerability discovery and remediation. Based on May 22, 2026 initial update.researchgosecurityVotes: 0GitHub stars: 3
Proevent Event Centric Benchmark Proactive AgentsASkill derived from arXiv:2607.17701 - ProEvent: An Event-centric Benchmark for Proactive AgentsresearchVotes: 0GitHub stars: 3
Personal Guidance SycophancyAMethodology from Anthropic research studying how users seek personal guidance from AI and implications for sycophancy — based on analysis of 1M claude.ai conversations.researchgoVotes: 0GitHub stars: 3
Open Ended Science BenchmarkABenchmark design methodology for evaluating AI scientific capabilities in open-ended, generative research contexts. Covers qualitative data collection, longitudinal tracking, and expectation measurement.researchgitapiVotes: 0GitHub stars: 3
Oblique Retrieval BenchmarkAOBLIQ-Bench methodology for exposing overlooked bottlenecks in modern retrievers with latent and implicit queries. Identifies oblique queries seeking documents that instantiate latent patterns. Reveals retrieval-verification asymmetry where LLMs recognize relevance but pipelines fail to surface documents. Activation: oblique retrieval, latent pattern search, implicit query, OBLIQ-Bench, retrieval bottleneck, verification asymmetry.researchpythonexpressVotes: 0GitHub stars: 3
Neuralbench Unified Neuroai BenchmarkANeuralBench unified benchmarking framework for NeuroAI models. Standardized evaluation across EEG/MEG/fMRI tasks with 36 tasks, 14 architectures, 94 datasets. Covers foundation model evaluation, task-specific baselines, cross-modal extension. Activation: neuralbench, neuroai benchmark, brain model evaluation, EEG benchmark, fMRI benchmark, MEG benchmark, NeuroAI evaluation.researchpythontestingVotes: 0GitHub stars: 3
Neural Code Language InterpretabilityANatural language hypothesis generation and verification for single-neuron selectivity. Combines vision-language models, neural digital twins, and text-to-image generation to automatically characterize what individual neurons encode across the visual hierarchy. Use for neuron interpretability, automated neuroscience discovery, digital twin validation, language-based neural characterization, closed-loop hypothesis testing.researchexpresstestingVotes: 0GitHub stars: 3
Iit Fep Maxcaliber BridgeAMaximum-Caliber Deviation framework bridging Integrated Information Theory (IIT) with the Free Energy Principle (FEP). Defines information as deviation from constrained maximum-caliber path ensembles, re-derives IIT cause/effect repertoires from variational principles, connects to active inference. Activation: iit fep bridge, maximum caliber, integrated information theory free energy, consciousness framework, constrained entropy maximization.researchVotes: 0GitHub stars: 3
Gnn Drug Toxicity ExplainabilityAGNN-based drug toxicity prediction explainability methodology with Gap Taxonomy (GAP-1 to GAP-4) for systematic analysis of explainability limitations. Uses GNNExplainer on MPNN models trained on Tox21 benchmark.researchpythongoVotes: 0GitHub stars: 3
Glasswing Vulnerability DiscoveryAAI-powered vulnerability discovery methodology from Anthropic's Project Glasswing - using frontier models (Mythos Preview) to find critical security vulnerabilities in open-source and enterprise software.researchgotestingVotes: 0GitHub stars: 3