AI Wiki — Knowledge Base

VLMは人間のような創造性を持てるか？ケネス・スタンレー教授らの『目標という幻想（Why Greatness Cannot Be Planned）』は、明確な目標を設定することが、かえって真に偉大な発見を遠ざけてしまうという逆説を論じた書籍です。その議論の中核にあったのが「Pi…

VLMは人間のような創造性を持てるか？ケネス・スタンレー教授らの『目標という幻想（Why Greatness Cannot Be Planned）』は、明確な目標を設定することが、かえって真に偉大な発見を遠ざけてしまうという逆説を論じた書籍です。その議論の中核にあったのが「PicBreeder」の実験でした。 PicBreeder では、ユーザーが「面白い」と感じた画像を選び、それを少しずつ進化

researchdavid-ha--x

11 Jul 2026

Search: “models”

A Collaborative Reasoning Framework for Anomaly Diagnostics in Underwater Robotics

A Quantum Reservoir Architecture for Chaotic Forecasting and a Test of Whether Its High Dimension Helps

Applying JEPA-Style Predictive Learning to JA4-Derived Network Fingerprints

ArtMine: Discovering and Formalizing Artistic Processes

Contrastive Order Learning: A General Framework for Ordinal Regression

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

Efficient Partitioning Method of Large-Scale Public Safety Spatio-Temporal Data based on Information Loss Constraints

Evaluating the Effect of Frame Rate in Sequence-Based Classification of Autism-Related Self-Stimulatory Hand Idiosyncrasies

FunHOI: Annotation-Free 3D Hand-Object Interaction Generation via Functional Text Guidance

Geometry-Aware Deep Congruence Networks for Manifold Learning in Cross-Subject Motor Imagery

Grounded Event Extraction from SEC 8-K Filings with a Fine-Grained Taxonomy

Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents

(heta_l, heta_u)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces

Holographic Neural PCFG for Unsupervised Parsing

How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism

HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition

Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment

INTENT: An LSTM Framework for Vehicle Intention Prediction in Intersection Scenarios with Comprehensive Ablation Analysis

Introducing Feature Views

𝕏 is a great platform for product announcements, especially if done by the CEO directly. Way more interesting to the public than generic pr…

Koopman-informed recurrent neural networks

MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction

MLQENABLER: Enabling Secure Machine Learning Queries over Encrypted Database in Cloud Computing

Monocular Vision Based Control Framework for Grasping

Neural non-canonical Hamiltonian dynamics for long-time simulations

PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimation

SAGA: Stable Acceleration Guidance for Autoregressive Video Generation

SPL: Orchestrating Workflows with Declarative Deterministic-Probabilistic Composition

SpO_2 Predictor-Guided Stage-Wise Time-Frequency Reconstruction of Low-Quality Dual-Wavelength PPG for Oxygen Saturation Estimation

Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning

Structure Learning on Clustered Data

The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of Agentic Inequality

The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis

Towards Soft Robotic Exogloves for Musculoskeletal Manipulation to Reduce Pain and Spasticity

Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution

v0.32.0-rc0

AA-ViT: Anatomically Aware Vision Transformer with Structural and Frequency Guidance for Contrast Enhanced Brain MRI Synthesis

ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation

An Edge-aware Prompt-enhanced SAM for Ultrasound Image Segmentation

CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training

Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning

ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching

CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views

Compass: Prostate Cancer Detection Needs Multi-View Context

Continuous and large-scale: ELEANOR, the soft architected arm inspired by the elephant trunk

Creating Power Distribution Network Layouts Using Generative Adversarial Networks and Image-Based Representations

Creativity from Friction: Human-AI Interaction for Exploratory Structural Design