AI Wiki — Knowledge Base

先日 @Nature 誌に掲載された AI Scientist 論文の主要著者の一人、Sakana AI の山田祐太朗への取材記事が日経デジタルガバナンスに掲載されました。 https://www.nikkei.com/prime/digital-governance/artic…

先日 @Nature 誌に掲載された AI Scientist 論文の主要著者の一人、Sakana AI の山田祐太朗への取材記事が日経デジタルガバナンスに掲載されました。 https://www.nikkei.com/prime/digital-governance/article/DGXZQOSG305D90Q6A330C2000000 本記事では、AIによる科学研究の現在地について、AI S

researchdavid-ha--x

14 Apr 2026

research

Locket: Robust Feature-Locking Technique for Language Models

LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectories

LOOPE: Learnable Optimal Patch Order in Positional Embeddings for Vision Transformers

Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models

Lung Cancer Detection Using Deep Learning

M^{2}SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation

Masked Contrastive Pre-Training Improves Music Audio Key Detection

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus

MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models

Membership Inference Attacks Expose Participation Privacy in ECG Foundation Encoders

Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models

METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues

Mild Over-Parameterization Benefits Asymmetric Tensor PCA

Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Models

Mitigating Privacy Risk via Forget Set-Free Unlearning

MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts

Modeling, Analysis and Activation of Planar Viscoelastically-combined Rimless Wheels

MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning

MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Multidata Causal Discovery for Statistical Hurricane Intensity Forecasting

Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex

Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy

NASA is building the first nuclear reactor-powered interplanetary spacecraft. How will it work?

先日 @Nature 誌に掲載された AI Scientist 論文の主要著者の一人、Sakana AI の山田祐太朗への取材記事が日経デジタルガバナンスに掲載されました。 https://www.nikkei.com/prime/digital-governance/artic…

Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score

Network Effects and Agreement Drift in LLM Debates

NetworkNet: A Deep Neural Network Approach for Random Networks with Sparse Nodal Attributes and Complex Nodal Heterogeneity

Neural Processes Maintain Calibrated Biomass Estimates Across Spatiotemporal Gaps and Disturbance

NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity

NeuVolEx: Implicit Neural Features for Volume Exploration

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models

Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers

NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings

On The Application of Linear Attention in Multimodal Transformers

On the Complexity of the Discussion-based Semantics in Abstraction Argumentation

On the Convergence of Gradient Descent on Learning Transformers with Residual Connections

On the Robustness of Watermarking for Autoregressive Image Generation

One-Step Score-Based Density Ratio Estimation

Ontological Trajectory Forecasting via Finite Semigroup Iteration and Lie Algebra Approximation in Geopolitical Knowledge Graphs

Optimal Kinodynamic Motion Planning Through Anytime Bidirectional Heuristic Search with Tight Termination Condition

Optimal L2 Regularization in High-dimensional Continual Linear Regression

Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification

Optimal Stability of KL Divergence under Gaussian Perturbations

PAC learning PDFA from data streams

PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion

Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow

PAS: Estimating the target accuracy before domain adaptation