AI Wiki — Knowledge Base

Charting the AI Perception Gap: Across 71 scenarios, AI experts (N=119) and the public (N=1100) have differing views on the risks, benefits, and value of AI. More importantly, AI experts discount the influence of risks stronger than the public does when forming their value judgments [R]

A study examining 71 AI scenarios found that AI experts (N=119) and the public (N=1100) hold differing views on AI risks, benefits, and value, with experts discounting risk influences more heavily tha

researchr-machinelearning

5 May 2026

research

Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters

An Adaptive Spatiotemporal Clustering Framework for 3D Ocean Subsurface Temperature Reconstruction

An Algorithm for On-Sensor Agnostic Detection of Changes in Human Activity for Ultra-Low-Power Applications

Anomaly Detection from a Tensor Train Perspective

Anon: Extrapolating Optimizer Adaptivity Across the Real Spectrum

AoI-Aware Multi-Robot Sensing and Transport on Connected Graphs

Application Research of a Deep Learning Model Integrating CycleGAN and YOLO in PCB Infrared Defect Detection

Argumentation for Explainable and Globally Contestable Decision Support with LLMs

ATLAS: Article Tracking, Linking, and Analysis of Swedish Encyclopedias

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse

Automated In-the-Wild Data Collection for Continual AI Generated Image Detection

Automatic Correction of Writing Anomalies in Hausa Texts

BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuron

Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech

BaldWhisper: Faster Whisper with Head Shearing and Layer Merging

Barren Plateaus as Destructive Interference: A Diagnostic Framework and Implications for Structured Ansatzes

Barriers to Counterfactual Credit Attribution for Autoregressive Models

Bayesian Neural Network Surrogates for Bayesian Optimization of Carbon Capture and Storage Operations

Benchmarking LightGBM and BiLSTM for Sentiment Analysis on Indonesian E-Commerce Reviews

Beyond ECE: Calibrated Size Ratio, Risk Assessment, and Confidence-Weighted Metrics

Beyond Structure: Revolutionising Materials Discovery via AI-Driven Synthesis Protocol-Property Relationships

Black-box optimization of noisy functions with unknown smoothness

BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion

Boundary Mass and the Soft-to-Hard Limit in Mixture-of-Experts

Breaking the Resolution Barrier: Arbitrary-resolution Deep Image Steganography Framework

Brutal montage from CNN of Trump lying about the ballroom being paid for by private donors

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction

Can professional translators identify machine-generated text?

CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimation

Causal Representation Learning with Optimal Compression under Complex Treatments

Cell-induced densification and tether formation in fibrous extracellular matrices with biomimetic physics-informed neural networks

Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining

Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation

Charting the AI Perception Gap: Across 71 scenarios, AI experts (N=119) and the public (N=1100) have differing views on the risks, benefits, and value of AI. More importantly, AI experts discount the influence of risks stronger than the public does when forming their value judgments [R]

CNNs for Vis-NIR Chemometrics: From Contradiction to Conditional Design

Code-switching in text and speech challenges information-theoretic speaker design

CoFrGeNet: Continued Fraction Architectures for Language Generation

Comparative Evaluation of Convolutional and Transformer-Based Detectors for Automated Weed Detection in Precision Agriculture

Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models

Continual Few-shot Adaptation for Synthetic Fingerprint Detection

Continuous quantification of viral plaque dynamics using ultra-large-area label-free imaging enables rapid antiviral susceptibility testing

Continuous Temporal Representations of Event-Based Signals via Interference-Based Wave Modeling

Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing

Correlates of Image Memorability in Vision Encoders: Activations, Attention Entropy, Patch Uniformity and Autoencoder Losses

Counting as a minimal probe of language model reliability

CRC-Screen: Certified DNA-Synthesis Hazard Screening Under Taxonomic Shift

CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing