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

safety

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization

Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning

Learning When to Jump for Off-road Navigation

Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift

Let the Target Select for Itself: Data Selection via Target-Aligned Paths

LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training

Liouville PDE-based sliced-Wasserstein flow

LLM Advertisement based on Neuron Auctions

LLM-Agnostic Semantic Representation Attack

LLM-Driven Performance-Space Augmentation for Meta-Learning-Based Algorithm Selection

Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities

LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models

M^3: Reframing Training Measures for Discretized Physical Simulations

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

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

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

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

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

MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service

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

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

Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI

MedFL-Stress: A Systematic Robustness Evaluation of Federated Brain Tumor Segmentation under Cross-Hospital MRI Appearance Shift

Mem-W: Latent Memory-Native GUI Agents

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs

Mental Health AI Safety Claims Must Preserve Temporal Evidence

MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning

Meta offers to give rival AI chatbots free access to WhatsApp for a month while it discusses commitments with EU antitrust regulators to address their concerns (Foo Yun Chee/Reuters)

Meta-reinforcement learning with minimum attention

Metropolis-Adjusted Diffusion Models

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models

Mismatch-Aware Adaptive Constraint Tightening for Bicycle-Model Trajectory Optimization

Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration

MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning

Monocular Biomechanical Tracking of Fingers with Inverse Kinematics to Foundation Models

Morphology-Aware Graph Reinforcement Learning for Tensegrity Robot Locomotion

MTA-RL: Robust Urban Driving via Multi-modal Transformer-based 3D Affordances and Reinforcement Learning

Multi-layer attentive probing improves transfer of audio representations for bioacoustics

Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning

Multimodal Representation Learning Conditioned on Semantic Relations

Muninn: Your Trajectory Diffusion Model But Faster

MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation

Mutual Information Optimal Density Control of Linear Systems and Generalized Schrodinger Bridges with Reference Refinement

MVB-Grasp: Minimum-Volume-Box Filtering of Diffusion-based Grasps for Frontal Manipulation

Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework

Navigating EU AI Act requirements for LLM fine-tuning on Amazon SageMaker AI

Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers