AI Wiki — Knowledge Base

先週末シンガポールにて行われた@AIDotEngineerにて、Sakana AIのResearch Scientistである@Stefania_DrugaがソブリンAIをテーマに登壇しました。ソブリンAIというと、「各国が自前の基盤モデルを持つこと」が語られがちですが、Sak…

先週末シンガポールにて行われた@AIDotEngineerにて、Sakana AIのResearch Scientistである@Stefania_DrugaがソブリンAIをテーマに登壇しました。ソブリンAIというと、「各国が自前の基盤モデルを持つこと」が語られがちですが、Sakana AIはこれをもう少し広く捉えています。世界中の優れたモデルを取り入れながら、その出力やふるまいを自国の文化・制

researchdavid-ha--x

19 May 2026

research

A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?

A Novel Model for 3D Motion Planning for a Generalized Dubins Vehicle with Pitch and Yaw Rate Constraints

A Practical Noise2Noise Denoising Pipeline for High-Throughput Raman Spectroscopy

A Readiness-Driven Runtime for Pipeline-Parallel Training under Runtime Variability

A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks

A Scalable Tool for Measuring Manner and Result Verbs in Developmental Language Research

A semantic mutation metric for metamorphic relation adequacy in scientific computing programs

A simple approach for biometrics: Finger-knuckle prints recognition based on a Sobel filter and similarity measures

A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning

A Systematic Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation

A Theory of Training Profit-Optimal LLMs

A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows

A Unified Framework for Structured Flow Modeling: From Continuous Fields to Data-Driven Representations

AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge

Accelerating AI-Powered Research: The PuppyChatter Framework for Usable and Flexible Tooling

Accelerating Inference for Multilayer Neural Networks with Quantum Computers

Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization

Achieving Linear Speedup with ProxSkip in Distributed Stochastic Optimization

ACIL: Auto Chain of Thoughts for In-Context Learning

Active Defense Against False Data Injection Attacks in Robotic Manipulators

Active learning for photonic crystals

Adaptive double-phase Rudin--Osher--Fatemi denoising model

Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction

先週末シンガポールにて行われた@AIDotEngineerにて、Sakana AIのResearch Scientistである@Stefania_DrugaがソブリンAIをテーマに登壇しました。 ソブリンAIというと、「各国が自前の基盤モデルを持つこと」が語られがちですが、Sak…

AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning

AMORE: Adaptive Multi-Output Operator Network for Stiff Chemical Kinetics

AMS-HD: Hyperdimensional Computing for Real-Time and Energy-Efficient Acute Mountain Sickness Detection

An AI system to help scientists write expert-level empirical software

An Approximation Algorithm for Graph Label Selection

An Efficient Machine Learning-based Framework for Detection and Prevention of Frauds in Telecom Networks

An Information-Theoretic Criterion for Efficient Data Synthesis

Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades

Anchor-Based Heteroscedastic Noise for Preferential Bayesian Optimization

Are Researchers Being Replaced by Artificial Intelligence?

Are Sparse Autoencoder Benchmarks Reliable?

Artificial Intelligence can Recognize Whether a Job Applicant is Selling and/or Lying According to Facial Expressions and Head Movements Much More Correctly Than Human Interviewers

AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents

Atoms as Language: VQ-Atom: Semantic Discretization for Molecular Representation Learning

Attacking the First-Principle: A Black-Box, Query-Free Targeted Mimicry Attack on Binary Function Classifiers

Attention-Aware Transformer-Based Aggregation Network for Video Periocular Recognition

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models

Automated Coding of Communication Data Using ChatGPT: Consistency Across Subgroups

AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code

Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization

Bayesian Networks for Path-Based Sensors: Gathering Information and Path Planning in Communication Denied Environments

BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering

Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives

先週末シンガポールにて行われた@AIDotEngineerにて、Sakana AIのResearch Scientistである@Stefania_DrugaがソブリンAIをテーマに登壇しました。ソブリンAIというと、「各国が自前の基盤モデルを持つこと」が語られがちですが、Sak…