AI Wiki — Knowledge Base

【採用情報】Sakana AIで「Public Sector Specialist」を募集🐟 https://sakana.ai/careers/#public-sector-specialist Sakana AIの最先端技術を官公庁と連携し社会実装していくためのドキュメン…

【採用情報】Sakana AIで「Public Sector Specialist」を募集🐟 https://sakana.ai/careers/#public-sector-specialist Sakana AIの最先端技術を官公庁と連携し社会実装していくためのドキュメンテーション戦略の立案・実行を担っていただきます。 👉 このようなご経験をお持ちの方を募集・政府機関での予算要求・政策立案

researchdavid-ha--x

14 May 2026

Search: “research”

Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data

Partial Optimality in the Preordering Problem

Perceptrons and localization of attention's mean-field landscape

Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Super-Resolution for Snapshot Compressive Imaging

Physics Guided Generative Optimization for Trotter Suzuki Decomposition

Physics-informed neural particle flow for the Bayesian update step

Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models

Plug-In Classification of Drift Functions in Diffusion Processes Using Neural Networks

Polyhedral Instability Governs Regret in Online Learning

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise

Posterior Bayesian Neural Networks with Dependent Weights

Potential and challenges of generative adversarial networks for super-resolution in 4D Flow MRI

Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference

Preconditioned Flow Matching

Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints

Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy

Prime Successor Irreducibility: Turing Machine Complexity, Kolmogorov Complexity, and Weakness-Based Formulations

PRISM: Perinuclear Ring-based Image Segmentation Method for Acute Lymphoblastic Leukemia Classification

Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems

Profit Maximization in Bilateral Trade against a Smooth Adversary

Provable Quantization with Randomized Hadamard Transform

Pyramid Self-contrastive Learning Framework for Test-time Ultrasound Image Denoising

QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling

QSMOTE-PGM/kPGM: QSMOTE Based PGM and kPGM for Imbalanced Dataset Classification

Radial Compensation: Fixing Radius Distortion in Chart-Based Generative Models on Riemannian Manifolds

Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Recurrent Transformer-Based Near- and Far-Field THz Wideband Channel Estimation for UM-MIMO

Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation

Relative Pose-Velocity Estimation Using Dual IMU Measurements and Relative Position Sensing

Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrograms

Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation

RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization

Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography

【採用情報】Sakana AIで「Public Sector Specialist」を募集🐟 https://sakana.ai/careers/#public-sector-specialist Sakana AIの最先端技術を官公庁と連携し社会実装していくための ドキュメン…

Sample-Efficient Optimisation over the Outputs of Generative Models

Sampling from Flow Language Models via Marginal-Conditioned Bridges

Saturation-Aware Angular Velocity Estimation: Extending the Robustness of SLAM to Aggressive Motions

Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale

Scaling Laws for Mixture Pretraining Under Data Constraints

SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models

Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation

Separating Shortcut Transition from Cross-Family OOD Failure in a Minimal Model

Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators

sketch2symm: Symmetry-aware sketch-to-shape generation via semantic bridging

Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence

Stable Attention Response for Reliable Precipitation Nowcasting

State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives

【採用情報】Sakana AIで「Public Sector Specialist」を募集🐟 https://sakana.ai/careers/#public-sector-specialist Sakana AIの最先端技術を官公庁と連携し社会実装していくためのドキュメン…