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: “papers”

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

Stochastic Quantum Spiking Neural Networks with Quantum Memory and Local Learning

The Geometry of Memorization: Finite-Time Spectral Sensitivity as a Diagnostic for Flow Matching Models

The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication

The Model Knows Your Project, Not You: Measuring Recognition in LLMs with NameRank

Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysis

Toward Localizing and Repairing Bias in Transformer Attention Heads

Toward Metaphor-Fluid Conversation Design for Voice User Interfaces

Toward Production-Ready Federated Learning in Healthcare: Privacy, Orchestration, and Governance in MLOps

Towards Vision-Free CIR: Attribute-Augmented Scoring and LLM-Based Reranking for Zero-Shot Composed Image Retrieval

UMSS: Towards Unsupervised Multi-modal Semantic Segmentation

Unveiling Complex Collective Behaviors from Simple Rewards

Vertical Standardisation for High-Risk AI Systems under the EU AI Act: A Domain-Specific Framework for Algorithmic Hiring

Virtual Chromoendscopy with Tunable Visibility Enhancement

Weakly Supervised Spatio-Temporal Candidate Discovery of Dairy Farm Sites from Seasonal Satellite Imagery

Highly-recommended overview of metacognition in LLMs. (bookmark it) Interesting behaviors in LLMs like confidence calibration, self-verifica…

I want to have this in writing so I can refer back to this tweet before it inevitably becomes a consensus view on twitter and say 'I told yo…

New research from Google DeepMind on effective model routing. LLM routers get judged on accuracy and cost. Both can look great while the rou…

Parse any PDF into agent-ready context. Fully local, free desktop app. No model / internet connection required!

Standard RL benchmarks are episodic and stationary, so they don't capture the the characteristics of real-world deployment. Morpheus is a ne…

Another big reason to use combination of frontier models. Chain-of-thought monitoring is treated as a reliable safety layer for agents. This…

3D Reconstruction of deciduous Trees using low-cost UAV- and Crane-based Photogrammetry for Monitoring Shoot Elongation across entire Canopies

A Graph Neural Network Model for Real-Time Gesture Recognition Based on sEMG Signals

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

A Sliced-Wasserstein Framework on Correlation Matrices for EEG Decoding

Accurate Portraits of Scientific Resources and Knowledge Service Components

Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting

Aleena: Alignment Agent for Research Software Engineering Collaborations

Beyond Backpropagation: Monte Carlo Method Can Train Deep Neural Networks

BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression

CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency

Closed-Loop Dynamic Validator Node Scaling in Private Substrate Blockchains Using Takagi-Sugeno Fuzzy Inference

Closing the Null Space: Guidance-Aware Quantization for Classifier-Free Diffusion

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation

Computation, Condensation, and the Incompleteness Between Them: A Coupled Foundation of Intelligence

Context Graphs for Proactive Enterprise Agents

Conversational AI for Rapid Scientific Prototyping: A Case Study on ESA's ELOPE Competition

D-CLIPSE: Distributed Consensus-based Localization with Passive Listening on Shared State Exchange

Deep Learning Method for Stationary Distribution of Reflected Brownian Motion

Diagnosing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry

Drift-Aware Temporal Graph Rewiring (DATGR) for Adaptive Semantic Modeling in Biomedical Text

Dynamics of Gradient Descent with Large Step Size Near a Manifold of Flat Minima

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

Equivariant Quantum Clustering with Differential Privacy: Parameter-Efficient Privacy-Preserving Analysis Across Heterogeneous Sensitive Datasets

Expressivity and Statistical Trade-offs in Diffusion Policy Learning

FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning

FedTR: Federated Learning Framework with Transfer Learning for Industrial Visual Inspection