AI Wiki — Knowledge Base

A Sampling Complexity-aware Framework for Discrete-time Fractional-Order Dynamical System Identification

arXiv:2501.17499v1 Announce Type: cross Abstract: A variety of complex biological, natural and man-made systems exhibit non-Markovian dynamics that can be modeled through fractional order differential

model-releasesarxiv-cs-lg

12 Oct 2026

All entries

A Baseline Assessment for the Agentic Web Technology Stack

A Better Metric Will Not Save You: What You Compare Beats How You Compare It

A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and Gauges

A Critical Look at Power Sampling when Test Time Sharpening LLMs

A Distributional Framework for Behavioral Characterization and Risk Management of Large Language Models

A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics

A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance

A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models

A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning

A Sampling Complexity-aware Framework for Discrete-time Fractional-Order Dynamical System Identification

A Scalable Learned Iterative Solver for Nonlinear MPC via Temporal Decomposition

A small cognitive core explains human behavior at scale

A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO

A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)

ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios

Accelerating Linear Bandits with Persistent Candidate Sets

Acoustic Biomarkers for Alzheimer's Disease Detection from Spontaneous Speech

Activating the Annotator: Operationalising Lived Experience in Data Annotation

AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning

Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy

Adaptive Variance Reduction without Knowing Oracle Smoothness

Adaptive Whole-Body MPC with Optimal Posture Planning for Humanoid Robots under Unknown Payloads

Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis

Agentic Large Language Models

Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing

AgentSWE: Can Coding Agents Build the Agent You Actually Want?

AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents

Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans

AI-Mediation in Retail Markets: Revenue Effects and Assortment Optimization

AI Models Can Provably Hide Arbitrary Capabilities

Algebraic Integer Quantization for Machine Learning Applications

AlphaNIST: Emergent Assembly Skills from Binary Task Rewards

AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

Amortised Inference through One-Step Implicit Sampling

Amortized Counterfactual Prediction with Graph Neural Networks

An all-transistor physical-learning transformer can be trained to perform in-context learning

An Input-Dependent Readout Phase for Resonant Sequence Models

APEX: Asynchronous Prefix Denoising for Extreme Compression

APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

Approximation of differential entropy in Bayesian optimal experimental design

ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation

Asymptotic Analysis of Discrete-Time Self-Attention Dynamics in Transformers

ATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching

Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs

AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs

Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal

AutoBio+: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation