AI Wiki — Knowledge Base

“Marcus's repeated warnings about the 'wall of generalization' since 1998 have once again been proven true.”

“Marcus's repeated warnings about the 'wall of generalization' since 1998 have once again been proven true.” Marcus氏が1998年から繰り返す'汎化の壁'の警告。またも証明された。完璧なAIを待つより、今の限界を熟知して使いこなすチームが勝つ。少人数ゆえの意思決定の速さとリスク許容度が

safetygary-marcus--x

12 May 2026

All entries

Lost in Volume: The CT-SpatialVQA Benchmark for Evaluating Semantic-Spatial Understanding of 3D Medical Vision-Language Models

love seeing my discord stay in sync with Hermes Kanban..everything here was done in plain English. I just asked my coordinator to check if w…

Low-Cost Neural Radiance Fields

Low-Cost Stereo Vision for Robust 3D Positioning of Thin Radiata Pine Branches in Autonomous Drone Pruning

LPT: Less-overfitting Prompt Tuning for Vision-Language Model

M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models

M^2E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection

M^3: Reframing Training Measures for Discretized Physical Simulations

Machine Learning-Based Graph Simplification for Symbolic Accelerators

Machine Learning Research Has Outpaced Its Communication Norms and NeurIPS Should Act

Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA

MaD Physics: Evaluating information seeking under constraints in physical environments

MAG-VLAQ: Multi-modal Aerial-Ground Query Aggregation for Cross-View Place Recognition

MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs

Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction

Majority Bit-Aware Watermarking For Large Language Models

Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction

Manage Vercel Firewall in the CLI

Manifold scores 7,700 MCP servers in Manifest expansion aimed at agent security teams

Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments

MapFormer: Self-Supervised Learning of Cognitive Maps with Input-Dependent Positional Embeddings

MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation

“Marcus's repeated warnings about the 'wall of generalization' since 1998 have once again been proven true.”

MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection

Markerless Head Tracking for Accurate and Accessible Neuronavigation

MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service

Marrying Generative Model of Healthcare Events with Digital Twin of Social Determinants of Health for Disease Reasoning

MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL

Masked Generative Transformer Is What You Need for Image Editing

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke

MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs

MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics

MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study

Matrix Factorization for Practical Continual Mean Estimation Under User-Level Differential Privacy

Max-pooling Network Revisited: Analyzing the Role of Semantic Probability in Multiple Instance Learning for Hallucination Detection

Mazocarta: A Seeded Procedural Deckbuilder for Instrumented Game Development

MBP-KT: Learning Global Collaborative Information from Meta-Behavioral Pattern for Enhanced Knowledge Tracing

MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching

MC^2: Monte Carlo Correction for Fast Elliptic PDE Solving

MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments

MDGYM: Benchmarking AI Agents on Molecular Simulations

MDL-GBG: A Non-parametric and Interpretable Granular-Ball Generation Method for Clustering

MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems

Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests

Measurement-Adapted Eigentask Representations for Photon-Limited Optical Readout

Measuring and Decomposing Mode Separation via the Canonical Diffusion