AI Wiki — Knowledge Base

Sakana AIは、SMBCグループと共同で「提案書自動生成アプリケーション」を開発。三井住友銀行にて実務への適用を開始します。 https://sakana.ai/smbc-proposal-ai/ 複数の「AIエージェント」が自律的に連携し、情報収集から仮説構築、提案構成ま…

Sakana AIは、SMBCグループと共同で「提案書自動生成アプリケーション」を開発。三井住友銀行にて実務への適用を開始します。 https://sakana.ai/smbc-proposal-ai/ 複数の「AIエージェント」が自律的に連携し、情報収集から仮説構築、提案構成までを支援。日本を支える基幹産業のDXを、独自の技術で強力に後押しします。 2025年のパートナーシップ締結以来、検討を

researchdavid-ha--x

30 Apr 2026

Search: “research”

Layer-wise Lipschitz-Product Control for Deep Kolmogorov--Arnold Network Representations of Compositionally Structured Functions

Learning to Route Electric Trucks Under Operational Uncertainty

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation

MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese

MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification

Meta-Learning and Targeted Differential Privacy to Improve the Accuracy-Privacy Trade-off in Recommendations

Mining Negative Sequential Patterns to Improve Viral Genomic Feature Representation and Classification

ml-intern is fully on mobile now you can launch 8 A100s from your phone. while on the couch. while commuting. wherever I just did this while…

Momentum-Conserving Graph Neural Networks for Deformable Objects

Motion-Driven Multi-Object Tracking of Model Organisms in Space Science Experiments

MTCurv: Deep learning for direct microtubule curvature mapping in noisy fluorescence microscopy images

Multi-Periodogram Velocity Estimation with Irregular Reference Signals for Robot-Aided ISAC

Multi-Stage Bi-Atrial Segmentation Framework from 3D Late Gadolinium-Enhanced MRI using V-Net Family Models

Neural-Geometric Tunnel Traversal: Localization-free UAV Flight with Tilted LiDARs

NeuralEmu: in situ Measurement-Driven, ML-based, High-Fidelity 5G Network Emulation

NeuralFLoC: Neural Flow-Based Joint Registration and Clustering of Functional Data

Occam's Razor is Only as Sharp as Your ELBO

OmniTrend: Content-Context Modeling for Scalable Social Popularity Prediction

On the Learning Curves of Revenue Maximization

One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech

Optimal differentially private kernel learning with random projection

Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective

Persona-Based Process Design for Assistive Human-Robot Workplaces for Persons with Disabilities

PiGGO: Physics-Guided Learnable Graph Kalman Filters for Virtual Sensing of Nonlinear Dynamic Structures under Uncertainty

PPG-Based Affect Recognition with Long-Range Deep Models: A Measurement-Driven Comparison of CNN, Transformer, and Mamba Architectures

Privacy-Preserving Clothing Classification using Vision Transformer for Thermal Comfort Estimation

ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python

q3-MuPa: Quick, Quiet, Quantitative Multi-Parametric MRI using Physics-Informed Diffusion Models

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch

Quantum Gatekeeper: Multi-Factor Context-Bound Image Steganography with VQC Based Key Derivation on Quantum Hardware

[R] Joint Embedding Variational Bayes (TMLR ’26)

Reactive Motion Generation via Phase-varying Neural Potential Functions

Real-time Global Illumination for Dynamic 3D Gaussian Scenes

Recent Advances in mm-Wave and Sub-THz/THz Oscillators for FutureG Technologies

Recurrence-Based Nonlinear Vocal Dynamics as Digital Biomarkers for Depression Detection from Conversational Speech

ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs

Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding

Resume-ing Control: (Mis)Perceptions of Agency Around GenAI Use in Recruiting Workflows

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective

Rethinking the Harmonic Loss via Non-Euclidean Distance Layers

Revisiting Human-in-the-Loop Object Retrieval with Pre-Trained Vision Transformers

Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts

Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data

Seamless Indoor-Outdoor Mapping for INGENIOUS First Responders

Semantic Embeddings of Chemical Elements for Enhanced Materials Inference and Discovery

Semantic Foam: Unifying Spatial and Semantic Scene Decomposition