AI Wiki — Knowledge Base

Sakana AIのオフィスが入居する麻布台ヒルズなどを運営する森ビルのウェブメディア「HILLS LIFE DAILY」に、Sakana AIリサーチサイエンティストのカラーヌワット・タリンへのインタビュー記事が掲載されました。麻布台ヒルズのデジタルサイネージで上映中の浮世絵…

Sakana AIのオフィスが入居する麻布台ヒルズなどを運営する森ビルのウェブメディア「HILLS LIFE DAILY」に、Sakana AIリサーチサイエンティストのカラーヌワット・タリンへのインタビュー記事が掲載されました。麻布台ヒルズのデジタルサイネージで上映中の浮世絵風画像生成プロジェクトを起点に、日本文化を理解するAIモデルの可能性について語っています。約12,000枚の浮世絵でフ

researchdavid-ha--x

27 May 2026

Search: “research”

Querying and Repairing Inconsistent Prioritized Knowledge Bases: Complexity Analysis and Links with Abstract Argumentation

R^3: 3D Reconstruction via Relative Regression

RadarSim: Simulating Single-Chip Radar via Multimodal Neural Fields

Rank-Learner: Orthogonal Ranking of Treatment Effects

Rapid online deep artifact suppression for real-time spiral bSSFP CMR with blipped-CAIPI simultaneous multi-slice imaging at 1.5 T

RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections

Re-M3Dr: Rebalanced MultiModal Mean Deviation Regression

ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation

Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascade

Recursive Flow Matching

Reformulation of RBM to Unify Linear and Nonlinear Dimensionality Reduction

Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage

RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations

Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models

Revealing the core dimensions underlying representations in brains, behavior and AI

Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling

Route Recommendations for Traffic Management Under Learned Partial Driver Compliance

Sampling Data with Chains of Forward-Backward Diffusion Steps

Scalable GANs with Transformers

Searching the Internet for Challenging Benchmarks at Scale

Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution

Self-Intersection-Aware 3D Human Motion Generation Using an Efficient Human Sphere Proxy

Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs

Sleep-stage efficient classification using a lightweight self-supervised model

Slide Deck Q&A Quality Assurance App: A Multi-Stage Pipeline for Pedagogical Question Generation

Small Object Detection in Industrial Recycling: A New Dataset and YOLO Performance Evaluation

SoftCap: Soft-Budget Control for Diffusion Transformer Acceleration

Sparse-LiDAR Prompting of Monocular Geometry Foundations: An Empirical Study Toward Long-Range Driving Depth

SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings

Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models

Step-Size Stability in Stochastic Optimization: A Theoretical Perspective

Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing

Stylistic Evolution and LLM Neutrality in Singlish Language

SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking

Symbolic Regression via Latent Iterative Refinement

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2

TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection

Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models

TCBiRRT: Rapid Motion Planning for Tightly Coupled Dual-arm Space Manipulator Using Task-space Random Expansion

Tetris: Tile-level Sampling for Efficient and High-Fidelity Video Object Tracking

The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context

The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation Oncology

The Download: keeping up with AI, and the future of IVF

today was a massive day for protein engineering. esmfold2 dropped—next gen of the esm series, fully open on @huggingscience. 1.1 billion pre…

Touch-R1: Reinforcing Touch Reasoning in MLLMs

Towards Controllable Image Generation through Representation-Conditioned Diffusion Models