ai Trend Report
Dashboard へ戻る
0
High impact
0
Mid impact
396
Signal watch
なぜこのサイトを作ったのか
私たちそれぞれが個別にAIを使って情報収集し、同じような3行要約を作るたびに、世界中で膨大な電力と計算リソースが消費されています。 本プロジェクトは、あらかじめ広範な情報を取得・集約しておくことで、個別のAI実行回数を減らし、地球環境（GPU/TPU負荷）に配慮した効率的な情報収集を目指す実験的なダッシュボードです。
MIT News - Artificial intelligence
New method aims to keep kids safe from illegal AI-generated content
New method aims to keep kids safe from illegal AI-generated content
cs.LG updates on arXiv.org
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
cs.LG updates on arXiv.org
iLENS: Interpretable LLM-Guided Mixture-of-Experts for Neuroimaging Survival Analysis
iLENS: Interpretable LLM-Guided Mixture-of-Experts for Neuroimaging Survival Analysis
cs.LG updates on arXiv.org
Signed Symmetric Quantization for Few-Bit Integers
Signed Symmetric Quantization for Few-Bit Integers
cs.LG updates on arXiv.org
Sticky Routing: Training MoE Models for Memory-Efficient Inference
Sticky Routing: Training MoE Models for Memory-Efficient Inference
cs.LG updates on arXiv.org
Reward Transport: Property Control in Flow Matching via Noise-Space Alignment
Reward Transport: Property Control in Flow Matching via Noise-Space Alignment
cs.LG updates on arXiv.org
Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement
Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement
cs.LG updates on arXiv.org
LieBN: Batch Normalization over Lie Groups
LieBN: Batch Normalization over Lie Groups
cs.LG updates on arXiv.org
HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
cs.LG updates on arXiv.org
DaDaDa: A Dataset for Data Pricing in Data Marketplaces
DaDaDa: A Dataset for Data Pricing in Data Marketplaces
cs.LG updates on arXiv.org
Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices
Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices
cs.LG updates on arXiv.org
Adaptive Bayes exactly tracks information over intrinsic time
Adaptive Bayes exactly tracks information over intrinsic time
cs.LG updates on arXiv.org
How are linear representations learned? Exact solutions to the dynamics of abstraction
How are linear representations learned? Exact solutions to the dynamics of abstraction
cs.LG updates on arXiv.org
Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal
Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal
cs.LG updates on arXiv.org
Pattern-Aware Graph Neural Networks for Handling Missing Data
Pattern-Aware Graph Neural Networks for Handling Missing Data
cs.LG updates on arXiv.org
A Machine Learning Surrogate for Component Criticality Ranking in Interdependent Power-Communication Networks
A Machine Learning Surrogate for Component Criticality Ranking in Interdependent Power-Communication Networks
cs.LG updates on arXiv.org
SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions
SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions
cs.LG updates on arXiv.org
BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving
BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving
cs.LG updates on arXiv.org
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
cs.LG updates on arXiv.org
Training, Reading, and Editing Legible Transformers
Training, Reading, and Editing Legible Transformers
cs.LG updates on arXiv.org
FairSelect: A Systematic Evaluation of Multi-Level and Intersectional Algorithmic Fairness
FairSelect: A Systematic Evaluation of Multi-Level and Intersectional Algorithmic Fairness
cs.LG updates on arXiv.org
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
cs.LG updates on arXiv.org
NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision
NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision
cs.LG updates on arXiv.org
Stochastic Linear Bandits with Partially Observed Actions
Stochastic Linear Bandits with Partially Observed Actions
cs.LG updates on arXiv.org
Federated Low-Rank Koopman Learning for Multivariate Time-Series Anomaly Detection in IoT Systems
Federated Low-Rank Koopman Learning for Multivariate Time-Series Anomaly Detection in IoT Systems
cs.LG updates on arXiv.org
Optimal Top-$k$ Identification from Pairwise Comparisons
Optimal Top-$k$ Identification from Pairwise Comparisons
cs.LG updates on arXiv.org
AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision
AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision
cs.LG updates on arXiv.org
Sensitivity-Aware Thresholding and Token Routing for Activation Sparsification in Large Language Models
Sensitivity-Aware Thresholding and Token Routing for Activation Sparsification in Large Language Models
cs.LG updates on arXiv.org
Model Agnostic Graph Prompt Learning for Crystal Property Prediction
Model Agnostic Graph Prompt Learning for Crystal Property Prediction
cs.LG updates on arXiv.org
Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
cs.LG updates on arXiv.org
Variable-Length Generative Protein Design via Generalized Poisson Flow
Variable-Length Generative Protein Design via Generalized Poisson Flow
cs.LG updates on arXiv.org
Learning More from Less: Reinforcement Learning from Hindsight
Learning More from Less: Reinforcement Learning from Hindsight
cs.LG updates on arXiv.org
COBS: Cumulant Order Block Sparse Attention
COBS: Cumulant Order Block Sparse Attention
cs.LG updates on arXiv.org
EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems
EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems
cs.LG updates on arXiv.org
Pitfalls and Remedies for Multi-Task Bayesian Optimization
Pitfalls and Remedies for Multi-Task Bayesian Optimization
cs.LG updates on arXiv.org
A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design
A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design
cs.LG updates on arXiv.org
EXHOLD: Experience-Aware Real-Time Hold Control for Large-Scale Ride-Hailing Matching at DiDi
EXHOLD: Experience-Aware Real-Time Hold Control for Large-Scale Ride-Hailing Matching at DiDi
cs.LG updates on arXiv.org
Quantum Circuits in Diffusion Models: A Fair-Comparison Study and a Mechanistic Analysis of Angle-Embedding Failures
Quantum Circuits in Diffusion Models: A Fair-Comparison Study and a Mechanistic Analysis of Angle-Embedding Failures
cs.LG updates on arXiv.org
Power Flow Feasibility Assessment Using Variational Graph Autoencoders
Power Flow Feasibility Assessment Using Variational Graph Autoencoders
cs.LG updates on arXiv.org
Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering
Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering
cs.LG updates on arXiv.org
A Personalized Computational Framework for Assessing the Sufficiency of Partially Observed Data in Healthcare AI models
A Personalized Computational Framework for Assessing the Sufficiency of Partially Observed Data in Healthcare AI models
cs.LG updates on arXiv.org
COAST: Context-Aware Differential Learning for Gene Expression Prediction in Spatial Transcriptomics
COAST: Context-Aware Differential Learning for Gene Expression Prediction in Spatial Transcriptomics
cs.LG updates on arXiv.org
Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles
Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles
cs.LG updates on arXiv.org
Application of machine learning to monster level prediction in tabletop RPG game design
Application of machine learning to monster level prediction in tabletop RPG game design
cs.LG updates on arXiv.org
Interference and Retention in Continual Learning
Interference and Retention in Continual Learning
cs.LG updates on arXiv.org
Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation
Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation
cs.LG updates on arXiv.org
Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem
Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem
cs.LG updates on arXiv.org
LionVote: Per-Layer Learning Rate Adaptation for Lion
LionVote: Per-Layer Learning Rate Adaptation for Lion
cs.LG updates on arXiv.org
Autoregressive latent diffusion for 3D molecule generation
Autoregressive latent diffusion for 3D molecule generation
cs.LG updates on arXiv.org
Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning
Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning
cs.LG updates on arXiv.org
Risk-Aware General-Utility Markov Decision Processes
Risk-Aware General-Utility Markov Decision Processes
cs.LG updates on arXiv.org
Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning
Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning
cs.LG updates on arXiv.org
Graph Neural Networks for Scalable and Transferable Node Centrality Approximation
Graph Neural Networks for Scalable and Transferable Node Centrality Approximation
cs.LG updates on arXiv.org
Learning Physics-Informed Surrogate Model of Linear Elastic Displacement Fields from Geometry
Learning Physics-Informed Surrogate Model of Linear Elastic Displacement Fields from Geometry
cs.LG updates on arXiv.org
Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks
Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks
cs.LG updates on arXiv.org
On-Device Adaptive Battery Power Prediction for Electric Vehicles
On-Device Adaptive Battery Power Prediction for Electric Vehicles
cs.LG updates on arXiv.org
Data-Efficient Deep Learning: Empirical Guidelines for Training Set Size Estimation in Inertial Sensor Classification
Data-Efficient Deep Learning: Empirical Guidelines for Training Set Size Estimation in Inertial Sensor Classification
cs.LG updates on arXiv.org
SYNRARE: Synthetic Rare Disease EHR Generation for ML Benchmarking
SYNRARE: Synthetic Rare Disease EHR Generation for ML Benchmarking
cs.LG updates on arXiv.org
Similarity search generalisation in contrastive learning with InfoNCE loss
Similarity search generalisation in contrastive learning with InfoNCE loss
cs.LG updates on arXiv.org
Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning
Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning
cs.LG updates on arXiv.org
Active rejection enables reliable generalization of universal machine-learning interatomic potentials
Active rejection enables reliable generalization of universal machine-learning interatomic potentials
cs.LG updates on arXiv.org
Neural Collapse Is Forbidden: Information Floors in Language Models
Neural Collapse Is Forbidden: Information Floors in Language Models
cs.LG updates on arXiv.org
All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models
All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models
cs.LG updates on arXiv.org
TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems
TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems
cs.LG updates on arXiv.org
Statistically Undetectable Backdoors in Deep Neural Networks
Statistically Undetectable Backdoors in Deep Neural Networks
cs.LG updates on arXiv.org
GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting
GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting
cs.LG updates on arXiv.org
CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding
CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding
cs.LG updates on arXiv.org
Graph-Regularized Low-Rank Matrix Completion by Variable Projection
Graph-Regularized Low-Rank Matrix Completion by Variable Projection
cs.LG updates on arXiv.org
Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection
Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection
cs.LG updates on arXiv.org
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
cs.LG updates on arXiv.org
Interval Certifications for Multilayered Perceptrons via Lattice Traversal
Interval Certifications for Multilayered Perceptrons via Lattice Traversal
cs.LG updates on arXiv.org
HALO: Hybrid Adaptive Latent Reasoning for Language Models
HALO: Hybrid Adaptive Latent Reasoning for Language Models
cs.LG updates on arXiv.org
EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
cs.LG updates on arXiv.org
TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology
TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology
cs.LG updates on arXiv.org
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
cs.LG updates on arXiv.org
Clean2FX: Label-conditioned modeling for clean-to-effect guitar audio transformations
Clean2FX: Label-conditioned modeling for clean-to-effect guitar audio transformations
cs.LG updates on arXiv.org
Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling
Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling
cs.LG updates on arXiv.org
FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
cs.LG updates on arXiv.org
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
cs.LG updates on arXiv.org
Learning-enabled Parameter Synthesis for Nonlinear Systems from Signal Temporal Logic
Learning-enabled Parameter Synthesis for Nonlinear Systems from Signal Temporal Logic
cs.LG updates on arXiv.org
Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity
Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity
cs.LG updates on arXiv.org
RaMark: Radioactive Watermarking for Generated Tabular Data
RaMark: Radioactive Watermarking for Generated Tabular Data
cs.LG updates on arXiv.org
Phone Segmentation and Recognition through Phonological Activation Mapping
Phone Segmentation and Recognition through Phonological Activation Mapping
cs.LG updates on arXiv.org
On Locality and Length Generalization in Visual Reasoning
On Locality and Length Generalization in Visual Reasoning
cs.LG updates on arXiv.org
Solving Stochastic Fixed-Point Equations with High Probability
Solving Stochastic Fixed-Point Equations with High Probability
cs.LG updates on arXiv.org
Quantum-Enhanced Synthetic Data Generation Using Quantum Circuit Born Machines for Imbalanced Tabular Learning
Quantum-Enhanced Synthetic Data Generation Using Quantum Circuit Born Machines for Imbalanced Tabular Learning
cs.LG updates on arXiv.org
Control Laguerre Tessellation: Semi-discrete Optimal Transport Over Control Systems
Control Laguerre Tessellation: Semi-discrete Optimal Transport Over Control Systems
cs.LG updates on arXiv.org
GenVid2Robot: From Video Generation to Robot Manipulation via Rigid-Geometric Consistency
GenVid2Robot: From Video Generation to Robot Manipulation via Rigid-Geometric Consistency
cs.LG updates on arXiv.org
Complexity-Guided Component-wise Initialization for Language Model Pretraining
Complexity-Guided Component-wise Initialization for Language Model Pretraining
cs.LG updates on arXiv.org
When Does Order Flow Matter? State-Dependent L2 Liquidity-State Transitions in Crypto Futures
When Does Order Flow Matter? State-Dependent L2 Liquidity-State Transitions in Crypto Futures
cs.LG updates on arXiv.org
Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
cs.LG updates on arXiv.org
Leveraging Interpretable Tsetlin Machine for PDF Malware Detection
Leveraging Interpretable Tsetlin Machine for PDF Malware Detection
cs.LG updates on arXiv.org
From Classification to Localization and Clinical Validation: Large-Scale Development of a Deep Learning System for Thoracic Disease Detection on Chest Radiographs in Thailand
From Classification to Localization and Clinical Validation: Large-Scale Development of a Deep Learning System for Thoracic Disease Detection on Chest Radiographs in Thailand
cs.LG updates on arXiv.org
Creativity, honesty and designed forgetting emerge in small hyperbolic language models
Creativity, honesty and designed forgetting emerge in small hyperbolic language models
cs.LG updates on arXiv.org
Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works
Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works
cs.LG updates on arXiv.org
Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
cs.LG updates on arXiv.org
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
cs.LG updates on arXiv.org
Spectrally Deconfounded Gradient Boosting
Spectrally Deconfounded Gradient Boosting
cs.LG updates on arXiv.org
A Sovereign, Open-Source Foundation Model for German and English
A Sovereign, Open-Source Foundation Model for German and English
cs.LG updates on arXiv.org
Multimodal Scenario Similarity Search for Autonomous Driving
Multimodal Scenario Similarity Search for Autonomous Driving
cs.LG updates on arXiv.org
Test-Time Scaling for Small VLMs on Multilingual Visual MCQ
Test-Time Scaling for Small VLMs on Multilingual Visual MCQ
cs.LG updates on arXiv.org
Robustifying Vision-Language Models via Test-Time Prompt Adaptation
Robustifying Vision-Language Models via Test-Time Prompt Adaptation
cs.LG updates on arXiv.org
Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers
Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers
cs.LG updates on arXiv.org
Terminal Dimension Reduction for Time Series with Applications
Terminal Dimension Reduction for Time Series with Applications
cs.LG updates on arXiv.org
The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs
The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs
cs.LG updates on arXiv.org
Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI
Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI
cs.LG updates on arXiv.org
Entropy-Constrained Machine Learning with Residual Data Augmentation for Modeling Chemical Kinetics
Entropy-Constrained Machine Learning with Residual Data Augmentation for Modeling Chemical Kinetics
cs.LG updates on arXiv.org
LLM for EDA in Front-End Design: Challenges and Opportunities
LLM for EDA in Front-End Design: Challenges and Opportunities
cs.LG updates on arXiv.org
Deep Gaussian Processes on Directed Acyclic Graphs
Deep Gaussian Processes on Directed Acyclic Graphs
cs.LG updates on arXiv.org
PHINN-EEG: Topological Time-Series Analysis of Dream-State EEG -- Dynamic Betti Curves for Dream Content Classification and Topology-Conditioned Neural Signal Synthesis
PHINN-EEG: Topological Time-Series Analysis of Dream-State EEG -- Dynamic Betti Curves for Dream Content Classification and Topology-Conditioned Neural Signal Synthesis
cs.LG updates on arXiv.org
LDPKiT: Superimposing Remote Queries for Privacy-Preserving Distillation
LDPKiT: Superimposing Remote Queries for Privacy-Preserving Distillation
cs.LG updates on arXiv.org
Towards Identifiability of Interventional Stochastic Differential Equations
Towards Identifiability of Interventional Stochastic Differential Equations
cs.LG updates on arXiv.org
Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation
Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation
cs.LG updates on arXiv.org
Regression-aware Continual Learning for Android Malware Detection
Regression-aware Continual Learning for Android Malware Detection
cs.LG updates on arXiv.org
Scalable Varied-Density Clustering via Graph Propagation
Scalable Varied-Density Clustering via Graph Propagation
cs.LG updates on arXiv.org
Cluster and then Embed: A Modular Approach for Visualization
Cluster and then Embed: A Modular Approach for Visualization
cs.LG updates on arXiv.org
Information-Theoretic Bayesian Optimization for Bilevel Optimization Problems
Information-Theoretic Bayesian Optimization for Bilevel Optimization Problems
cs.LG updates on arXiv.org
Forking-Sequences: Statistically and Computationally Efficient Multi-Horizon Forecasting with Reduced Volatility
Forking-Sequences: Statistically and Computationally Efficient Multi-Horizon Forecasting with Reduced Volatility
cs.LG updates on arXiv.org
Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
cs.LG updates on arXiv.org
Principles of Lipschitz continuity in neural networks
Principles of Lipschitz continuity in neural networks
cs.LG updates on arXiv.org
Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
cs.LG updates on arXiv.org
Tensor Methods: A Unified and Interpretable Approach for Material Design
Tensor Methods: A Unified and Interpretable Approach for Material Design
cs.LG updates on arXiv.org
Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
cs.LG updates on arXiv.org
Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
cs.LG updates on arXiv.org
Lipschitz-Based Robustness Certification Under Floating-Point Execution
Lipschitz-Based Robustness Certification Under Floating-Point Execution
cs.LG updates on arXiv.org
Learning Lineage-guided Geodesics with Finsler Geometry
Learning Lineage-guided Geodesics with Finsler Geometry
cs.LG updates on arXiv.org
Bridging the Gap Between Climate Science and Machine Learning in Climate Model Emulation
Bridging the Gap Between Climate Science and Machine Learning in Climate Model Emulation
cs.LG updates on arXiv.org
Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
cs.LG updates on arXiv.org
Kronecker-Structured Nonparametric Spatiotemporal Point Processes
Kronecker-Structured Nonparametric Spatiotemporal Point Processes
cs.LG updates on arXiv.org
Logarithmic High-Probability Regret for Online Convex Optimization with Two-Point Bandit Feedback
Logarithmic High-Probability Regret for Online Convex Optimization with Two-Point Bandit Feedback
cs.LG updates on arXiv.org
Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction
Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction
cs.LG updates on arXiv.org
AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
cs.LG updates on arXiv.org
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
cs.LG updates on arXiv.org
CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecasting
CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecasting
cs.LG updates on arXiv.org
Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning
Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning
cs.LG updates on arXiv.org
Code Correctness Signals in LLM Hidden States: Pre-Generation Probing and Repair Geometry
Code Correctness Signals in LLM Hidden States: Pre-Generation Probing and Repair Geometry
cs.LG updates on arXiv.org
Evolutionary Discovery of Developmental Reward Schedules in Deep Reinforcement Learning
Evolutionary Discovery of Developmental Reward Schedules in Deep Reinforcement Learning
cs.LG updates on arXiv.org
3D Masked Autoencoders are Robust Learners of Volumetric and Multimodal Cellular Representations for Microscopy
3D Masked Autoencoders are Robust Learners of Volumetric and Multimodal Cellular Representations for Microscopy
cs.LG updates on arXiv.org
Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series
Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series
cs.LG updates on arXiv.org
Estimation-Prediction Tradeoff in Causal Probabilistic Temporal Graphs
Estimation-Prediction Tradeoff in Causal Probabilistic Temporal Graphs
cs.LG updates on arXiv.org
A Fourier analytique approach to Gaussian mixture learning
A Fourier analytique approach to Gaussian mixture learning
cs.LG updates on arXiv.org
Ruby: Unmasking Unsafe Rust in Stripped Binaries via Machine Learning
Ruby: Unmasking Unsafe Rust in Stripped Binaries via Machine Learning
cs.LG updates on arXiv.org
Contrastive Learning on Multimodal Analysis of Electronic Health Records
Contrastive Learning on Multimodal Analysis of Electronic Health Records
cs.LG updates on arXiv.org
Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization
Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization
cs.LG updates on arXiv.org
Projection Methods for Operator Learning and Universal Approximation
Projection Methods for Operator Learning and Universal Approximation
cs.LG updates on arXiv.org
Accelerating Large Language Model Inference with Self-Supervised Early Exits
Accelerating Large Language Model Inference with Self-Supervised Early Exits
cs.LG updates on arXiv.org
Human Vision Constrained Super-Resolution
Human Vision Constrained Super-Resolution
cs.LG updates on arXiv.org
Multi-Attribute Steering of Language Models via Targeted Intervention
Multi-Attribute Steering of Language Models via Targeted Intervention
cs.LG updates on arXiv.org
Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning
Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning
cs.LG updates on arXiv.org
Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors
Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors
cs.LG updates on arXiv.org
A Descriptive and Normative Theory of Human Beliefs in RLHF
A Descriptive and Normative Theory of Human Beliefs in RLHF
cs.LG updates on arXiv.org
M4V: Multimodal Mamba for Efficient Text-to-Video Generation
M4V: Multimodal Mamba for Efficient Text-to-Video Generation
cs.LG updates on arXiv.org
Transformer-Based Inverse Microrheology for Experimental Mechanics at Ultra-High Strain Rates
Transformer-Based Inverse Microrheology for Experimental Mechanics at Ultra-High Strain Rates
cs.LG updates on arXiv.org
Uncovering smooth structures in single-cell data with PCS-guided neighbor embeddings
Uncovering smooth structures in single-cell data with PCS-guided neighbor embeddings
cs.LG updates on arXiv.org
A Practical Guide to Interpretable Role-Based Clustering in Multi-Layer Financial Networks
A Practical Guide to Interpretable Role-Based Clustering in Multi-Layer Financial Networks
cs.LG updates on arXiv.org
Is data-efficient learning feasible with quantum models?
Is data-efficient learning feasible with quantum models?
cs.LG updates on arXiv.org
Near-optimal Delta-convex Estimation of Lipschitz Functions
Near-optimal Delta-convex Estimation of Lipschitz Functions
cs.LG updates on arXiv.org
AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders
AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders
cs.LG updates on arXiv.org
Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation
Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation
cs.LG updates on arXiv.org
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
cs.LG updates on arXiv.org
ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
cs.LG updates on arXiv.org
Transition Matching Distillation for Fast Video Generation
Transition Matching Distillation for Fast Video Generation
cs.LG updates on arXiv.org
Global Sequential Testing for Multi-Stream Auditing
Global Sequential Testing for Multi-Stream Auditing
cs.LG updates on arXiv.org
Fine-grained Soundscape Control for Augmented Hearing
Fine-grained Soundscape Control for Augmented Hearing
cs.LG updates on arXiv.org
From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators
From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators
cs.LG updates on arXiv.org
RELISH: LLM REgression with a Latent Iterative State Head
RELISH: LLM REgression with a Latent Iterative State Head
cs.LG updates on arXiv.org
HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
cs.LG updates on arXiv.org
Tuning Derivatives for Causal Fairness in Machine Learning
Tuning Derivatives for Causal Fairness in Machine Learning
cs.LG updates on arXiv.org
XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles
XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles
cs.LG updates on arXiv.org
Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning
Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning
cs.LG updates on arXiv.org
Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers
Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers
cs.LG updates on arXiv.org
Kernel of Partition Paths: A Unified Representation for Tree Ensembles
Kernel of Partition Paths: A Unified Representation for Tree Ensembles
cs.LG updates on arXiv.org
Memory-Managed Long-Context Attention: Bounded Editable Memory with a Hard Lifecycle and Calibrated Sparse Fallback
Memory-Managed Long-Context Attention: Bounded Editable Memory with a Hard Lifecycle and Calibrated Sparse Fallback
cs.LG updates on arXiv.org
Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data
Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data
stat.ML updates on arXiv.org
EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
stat.ML updates on arXiv.org
Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
stat.ML updates on arXiv.org
Spectrally Deconfounded Gradient Boosting
Spectrally Deconfounded Gradient Boosting
stat.ML updates on arXiv.org
Characterization of the basin of convexity for multi-snapshot spike deconvolution via variable projection
Characterization of the basin of convexity for multi-snapshot spike deconvolution via variable projection
stat.ML updates on arXiv.org
Deep Gaussian Processes on Directed Acyclic Graphs
Deep Gaussian Processes on Directed Acyclic Graphs
stat.ML updates on arXiv.org
Adaptive Bayes exactly tracks information over intrinsic time
Adaptive Bayes exactly tracks information over intrinsic time
stat.ML updates on arXiv.org
A Statistical Test for the Benefits of Personalizing Interventions
A Statistical Test for the Benefits of Personalizing Interventions
stat.ML updates on arXiv.org
Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity
Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity
stat.ML updates on arXiv.org
Stochastic Linear Bandits with Partially Observed Actions
Stochastic Linear Bandits with Partially Observed Actions
stat.ML updates on arXiv.org
Optimal Top-$k$ Identification from Pairwise Comparisons
Optimal Top-$k$ Identification from Pairwise Comparisons
stat.ML updates on arXiv.org
Achieving Almost Exact Recovery in Almost Quadratic Time: Rank-Based Graph Matching via Local Tree Correlation Tests
Achieving Almost Exact Recovery in Almost Quadratic Time: Rank-Based Graph Matching via Local Tree Correlation Tests
stat.ML updates on arXiv.org
Solving Stochastic Fixed-Point Equations with High Probability
Solving Stochastic Fixed-Point Equations with High Probability
stat.ML updates on arXiv.org
Similarity search generalisation in contrastive learning with InfoNCE loss
Similarity search generalisation in contrastive learning with InfoNCE loss
stat.ML updates on arXiv.org
comprisk: A scikit-learn-compatible Python toolkit for competing-risks survival analysis
comprisk: A scikit-learn-compatible Python toolkit for competing-risks survival analysis
stat.ML updates on arXiv.org
Near-optimal node-private community estimation in polynomial-time
Near-optimal node-private community estimation in polynomial-time
stat.ML updates on arXiv.org
Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions
Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions
stat.ML updates on arXiv.org
Neural Collapse Is Forbidden: Information Floors in Language Models
Neural Collapse Is Forbidden: Information Floors in Language Models
stat.ML updates on arXiv.org
Terminal Dimension Reduction for Time Series with Applications
Terminal Dimension Reduction for Time Series with Applications
stat.ML updates on arXiv.org
Statistically Undetectable Backdoors in Deep Neural Networks
Statistically Undetectable Backdoors in Deep Neural Networks
stat.ML updates on arXiv.org
High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviations
High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviations
stat.ML updates on arXiv.org
A censoring-aware target interface for tabular foundation models in survival prediction
A censoring-aware target interface for tabular foundation models in survival prediction
stat.ML updates on arXiv.org
Dynamic Frechet Regression with Feature Selection for Distributional Data
Dynamic Frechet Regression with Feature Selection for Distributional Data
stat.ML updates on arXiv.org
Contrastive Learning on Multimodal Analysis of Electronic Health Records
Contrastive Learning on Multimodal Analysis of Electronic Health Records
stat.ML updates on arXiv.org
Uncovering smooth structures in single-cell data with PCS-guided neighbor embeddings
Uncovering smooth structures in single-cell data with PCS-guided neighbor embeddings
stat.ML updates on arXiv.org
Near-optimal Delta-convex Estimation of Lipschitz Functions
Near-optimal Delta-convex Estimation of Lipschitz Functions
stat.ML updates on arXiv.org
Global Sequential Testing for Multi-Stream Auditing
Global Sequential Testing for Multi-Stream Auditing
stat.ML updates on arXiv.org
Tuning Derivatives for Causal Fairness in Machine Learning
Tuning Derivatives for Causal Fairness in Machine Learning
stat.ML updates on arXiv.org
Kernel of Partition Paths: A Unified Representation for Tree Ensembles
Kernel of Partition Paths: A Unified Representation for Tree Ensembles
stat.ML updates on arXiv.org
Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data
Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data
stat.ML updates on arXiv.org
Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization
Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization
stat.ML updates on arXiv.org
Accelerating Large Language Model Inference with Self-Supervised Early Exits
Accelerating Large Language Model Inference with Self-Supervised Early Exits
stat.ML updates on arXiv.org
Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation
Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation
stat.ML updates on arXiv.org
Cluster and then Embed: A Modular Approach for Visualization
Cluster and then Embed: A Modular Approach for Visualization
stat.ML updates on arXiv.org
A Computable Measure of Suboptimality for Entropy-Regularised Variational Objectives
A Computable Measure of Suboptimality for Entropy-Regularised Variational Objectives
stat.ML updates on arXiv.org
Gradient-enhanced global sensitivity analysis with Poincar{\'e} chaos expansions
Gradient-enhanced global sensitivity analysis with Poincar{\'e} chaos expansions
stat.ML updates on arXiv.org
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
stat.ML updates on arXiv.org
Principles of Lipschitz continuity in neural networks
Principles of Lipschitz continuity in neural networks
stat.ML updates on arXiv.org
Predicting fixed-sample test decisions enables anytime-valid inference
Predicting fixed-sample test decisions enables anytime-valid inference
stat.ML updates on arXiv.org
Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
stat.ML updates on arXiv.org
Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation
Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation
stat.ML updates on arXiv.org
From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators
From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators
stat.ML updates on arXiv.org
Bridging the Gap Between Climate Science and Machine Learning in Climate Model Emulation
Bridging the Gap Between Climate Science and Machine Learning in Climate Model Emulation
stat.ML updates on arXiv.org
Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction
Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction
stat.ML updates on arXiv.org
On the Complexity of Low-Rank Matrix Signing and Entrywise Power Matrix Factorization
On the Complexity of Low-Rank Matrix Signing and Entrywise Power Matrix Factorization
Takara TLDR - Daily AI Papers
GIRAF: Towards Generalizable Human Interactions with Articulated Objects
GIRAF: Towards Generalizable Human Interactions with Articulated Objects
Takara TLDR - Daily AI Papers
A Quantum Reservoir Architecture for Chaotic Forecasting and a Test of Whether Its High Dimension Helps
A Quantum Reservoir Architecture for Chaotic Forecasting and a Test of Whether Its High Dimension Helps
Takara TLDR - Daily AI Papers
AnythingReality: Robust Online Gaussian Splatting SLAM for Open-Vocabulary VR Scene Exploration
AnythingReality: Robust Online Gaussian Splatting SLAM for Open-Vocabulary VR Scene Exploration
Takara TLDR - Daily AI Papers
Deep Learning Method for Stationary Distribution of Reflected Brownian Motion
Deep Learning Method for Stationary Distribution of Reflected Brownian Motion
Takara TLDR - Daily AI Papers
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
Takara TLDR - Daily AI Papers
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
＠IT 全フォーラム 最新記事一覧
エージェントによる業務自動化をどう実現？ 「Microsoft Build 2026」で発表された多数の新技術
エージェントによる業務自動化をどう実現？ 「Microsoft Build 2026」で発表された多数の新技術
＠IT 全フォーラム 最新記事一覧
中央省庁で初のSAP ERP導入 海上自衛隊は「全国に分散した物資情報」をどう一元管理した？
中央省庁で初のSAP ERP導入 海上自衛隊は「全国に分散した物資情報」をどう一元管理した？
＠IT 全フォーラム 最新記事一覧
700キロ先でも成功、“60GHz帯”無線LANでつないだロボットを低遅延制御 その通信とは？
700キロ先でも成功、“60GHz帯”無線LANでつないだロボットを低遅延制御 その通信とは？
＠IT 全フォーラム 最新記事一覧
AI、MCP、A2A時代に「API」はどう変わる？ APIを“管理するだけ”では乗り切れない
AI、MCP、A2A時代に「API」はどう変わる？ APIを“管理するだけ”では乗り切れない
＠IT 全フォーラム 最新記事一覧
32万台超のFortiGateが狙われた 相次ぐ「大規模侵害」に備えるには何が必要？
32万台超のFortiGateが狙われた 相次ぐ「大規模侵害」に備えるには何が必要？
ITmedia NEWS 最新記事一覧
「今ネットで販売されているグッズは全て非公式品」 人気ゲーム「めっちゃカメレオン」開発者が注意喚起
「今ネットで販売されているグッズは全て非公式品」 人気ゲーム「めっちゃカメレオン」開発者が注意喚起
ITmedia NEWS 最新記事一覧
近くでクマ目撃投稿→5秒以内に通知「クマップ」提供開始 秋田の学生スタートアップ発
近くでクマ目撃投稿→5秒以内に通知「クマップ」提供開始 秋田の学生スタートアップ発
ITmedia NEWS 最新記事一覧
ローソンでステーブルコイン支払い KDDI・HashPortが技術実証へ 高輪ゲートウェイ店で8月実施
ローソンでステーブルコイン支払い KDDI・HashPortが技術実証へ 高輪ゲートウェイ店で8月実施
ITmedia NEWS 最新記事一覧
OpenAIのブラウザ「ChatGPT Atlas」終了へ 公開から1年足らずで
OpenAIのブラウザ「ChatGPT Atlas」終了へ 公開から1年足らずで
ITmedia NEWS 最新記事一覧
GMOグループ、AI時代に「エンジニア含む組織体制見直し」 熊谷代表が「AI変革最高責任者」に
GMOグループ、AI時代に「エンジニア含む組織体制見直し」 熊谷代表が「AI変革最高責任者」に
ITmedia NEWS 最新記事一覧
Anthropic、「Fable 5」またも延長 追加費用なしで7月19日まで利用可能に 「GPT-5.6」に対抗？
Anthropic、「Fable 5」またも延長 追加費用なしで7月19日まで利用可能に 「GPT-5.6」に対抗？
ITmedia NEWS 最新記事一覧
「GPT-Liveが“まるで人間”」ってホンマ？ 出汁を「でじる」、トーストを「素焼き」て言うてたけど……
「GPT-Liveが“まるで人間”」ってホンマ？ 出汁を「でじる」、トーストを「素焼き」て言うてたけど……
ITmedia NEWS 最新記事一覧
公開中の新作「トイ・ストーリー5」 Xに全編流出 150万再生で”6億円”相当の被害か
公開中の新作「トイ・ストーリー5」 Xに全編流出 150万再生で”6億円”相当の被害か
ITmedia NEWS 最新記事一覧
Instagram、他人の公開写真からAI動画を自動生成する機能を無効化 フィードバック受け
Instagram、他人の公開写真からAI動画を自動生成する機能を無効化 フィードバック受け
ITmedia NEWS 最新記事一覧
論文サイト「arXiv」、投稿の約9割で非公開情報が“丸見え状態”か パスワードや秘密鍵、自宅のGPS座標なども 270万件を調査
論文サイト「arXiv」、投稿の約9割で非公開情報が“丸見え状態”か パスワードや秘密鍵、自宅のGPS座標なども 270万件を調査
Zennの「大規模言語モデル」のフィード
高級モデルに全部やらせない — 標準機能（skill）だけでカジュアルに実現するマルチモデルの仕組み『delegate-skills』
高級モデルに全部やらせない — 標準機能（skill）だけでカジュアルに実現するマルチモデルの仕組み『delegate-skills』
Zennの「大規模言語モデル」のフィード
Claude Code のContext・Skillを評価する『Evals』ツール徹底比較 〜トークン数と性能をどう測るか〜
Claude Code のContext・Skillを評価する『Evals』ツール徹底比較 〜トークン数と性能をどう測るか〜
Zennの「大規模言語モデル」のフィード
OpenFugu×ローカルLLM群でマルチAI駆動を検証③ 小型の群れは上位モデルを超えられるか
OpenFugu×ローカルLLM群でマルチAI駆動を検証③ 小型の群れは上位モデルを超えられるか
Zennの「大規模言語モデル」のフィード
AIペルソナをJSONでバックアップ・復元・検証する——PIM-DBSというユーザー側プロトコルの設計
AIペルソナをJSONでバックアップ・復元・検証する——PIM-DBSというユーザー側プロトコルの設計
Zennの「大規模言語モデル」のフィード
AI彼女アプリを作っていて気付いた。思い出すことより、「思い出す順番」の方が難しかった
AI彼女アプリを作っていて気付いた。思い出すことより、「思い出す順番」の方が難しかった
Zennの「大規模言語モデル」のフィード
【2026/6/30】Claude Sonnet 5リリース — 1Mコンテキスト標準化・temperature廃止・実質3割の値上げも
【2026/6/30】Claude Sonnet 5リリース — 1Mコンテキスト標準化・temperature廃止・実質3割の値上げも
Zennの「大規模言語モデル」のフィード
AIスコアで選ぶ 今週のGitHub注目リポジトリ 10選（2026-07-13週）
AIスコアで選ぶ 今週のGitHub注目リポジトリ 10選（2026-07-13週）
Zennの「大規模言語モデル」のフィード
議事録要約が会議タイプで精度が変わる理由、優先順位プロンプトで頻度バイアスを崩す
議事録要約が会議タイプで精度が変わる理由、優先順位プロンプトで頻度バイアスを崩す
Zennの「大規模言語モデル」のフィード
Anthropic Managed Agentsで"走った記録を読み物にする"システムを作って実運用した話——Memoryが育つまで
Anthropic Managed Agentsで"走った記録を読み物にする"システムを作って実運用した話——Memoryが育つまで
Zennの「大規模言語モデル」のフィード
塾講師6年目、AIで教材づくりはこう変わった — 個別指導の現場で実際に使っている型3つ
塾講師6年目、AIで教材づくりはこう変わった — 個別指導の現場で実際に使っている型3つ
Zennの「大規模言語モデル」のフィード
AIの答案をAIに採点させたら、採点者ごとに点が違った——LLM-as-judgeを疑って測る
AIの答案をAIに採点させたら、採点者ごとに点が違った——LLM-as-judgeを疑って測る
Zennの「大規模言語モデル」のフィード
オープンソースLLM×Colab無料GPUでClaude Codeは代替できるか：やって分かった現実
オープンソースLLM×Colab無料GPUでClaude Codeは代替できるか：やって分かった現実
Zennの「大規模言語モデル」のフィード
常駐型AIチャットエージェントの「レート制限・バックプレッシャー」設計でハマったこと
常駐型AIチャットエージェントの「レート制限・バックプレッシャー」設計でハマったこと
Zennの「機械学習」のフィード
【技術解説】ビットコイン価格予測：機械学習で動的ストップロスロジックを活用する方法
【技術解説】ビットコイン価格予測：機械学習で動的ストップロスロジックを活用する方法
Zennの「機械学習」のフィード
その「回収率120%」、前処理の正規化定数がリークしていませんか——20行でできる点検
その「回収率120%」、前処理の正規化定数がリークしていませんか——20行でできる点検
Zennの「機械学習」のフィード
生成AIに「Inpainting（物体消去）」を聞いてみた（LaMaで塗って消す）
生成AIに「Inpainting（物体消去）」を聞いてみた（LaMaで塗って消す）
Zennのトレンド
ハーネスエンジニアリングとループエンジニアリングの違いとは？ aws aidlc workflow kitから整理する
ハーネスエンジニアリングとループエンジニアリングの違いとは？ aws aidlc workflow kitから整理する
Zennのトレンド
Cloudflare Registrar + R2 で個人開発アプリの公開基盤を構築した記録
Cloudflare Registrar + R2 で個人開発アプリの公開基盤を構築した記録
Zennのトレンド
GitHub Actions の parallel でデプロイは8分→3分、CI はコスト3割減になった
GitHub Actions の parallel でデプロイは8分→3分、CI はコスト3割減になった
機械学習タグが付けられた新着記事 - Qiita
Zotero・Obsidian・NotebookLMで作る「研究者の思考を支援する環境」
Zotero・Obsidian・NotebookLMで作る「研究者の思考を支援する環境」
LLMタグが付けられた新着記事 - Qiita
現在の推論モデルが逆転の呪い(A is B → ×B is A)にどう対策しているか
現在の推論モデルが逆転の呪い(A is B → ×B is A)にどう対策しているか
Qiita - 人気の記事
「15歳とChatGPT」より、4万6812件が退会させられたシステムについて考えたい
「15歳とChatGPT」より、4万6812件が退会させられたシステムについて考えたい
Qiita - 人気の記事
Azure Durable Functions入門｜非同期処理を「順番・並列・待機」でシンプルに書く方法（Python編）
Azure Durable Functions入門｜非同期処理を「順番・並列・待機」でシンプルに書く方法（Python編）
Qiita - 人気の記事
src/config でゼロハードコーディング — 「業務的意味を持つ値」を集約する設計パターン
src/config でゼロハードコーディング — 「業務的意味を持つ値」を集約する設計パターン
Qiita - 人気の記事
【SkillOpt】寝る子は育つ？SkillOpt-Sleepで寝ている間にスキルが自己進化【Skill】
【SkillOpt】寝る子は育つ？SkillOpt-Sleepで寝ている間にスキルが自己進化【Skill】
Qiita - 人気の記事
Maxwell 方程式から見るインダクタンス：自己インダクタンスと相互インダクタンスの正体
Maxwell 方程式から見るインダクタンス：自己インダクタンスと相互インダクタンスの正体
Qiita - 人気の記事
Oracle AI Databaseで地図情報を扱ってみる：実際にアプリを作ってわかったこと
Oracle AI Databaseで地図情報を扱ってみる：実際にアプリを作ってわかったこと
Qiita - 人気の記事
【Personal OS #3】Claude Codeで、ミーティングを自動でドキュメント化する仕組み
【Personal OS #3】Claude Codeで、ミーティングを自動でドキュメント化する仕組み
Qiita - 人気の記事
TypeScriptで学ぶ Result型とRailway Oriented Programming
TypeScriptで学ぶ Result型とRailway Oriented Programming
Qiita - 人気の記事
【AWS小ネタ】無効化している1回限りのEventBridgeスケジュールを実行時刻を過ぎてから有効化すると即発火する
【AWS小ネタ】無効化している1回限りのEventBridgeスケジュールを実行時刻を過ぎてから有効化すると即発火する
Qiita - 人気の記事
Amazon EVS で VCF 9 のサポートが開始！変更点をスライド 1 枚でまとめてみた
Amazon EVS で VCF 9 のサポートが開始！変更点をスライド 1 枚でまとめてみた
Qiita - 人気の記事
OpenClaw×Claude Code連携で爆速開発【2026年最新】SESやめたいエンジニアのAI駆動独立準備術
OpenClaw×Claude Code連携で爆速開発【2026年最新】SESやめたいエンジニアのAI駆動独立準備術
WIRED
Uber’s Autonomous Vehicle Strategy: Slow Their Adoption
Uber’s Autonomous Vehicle Strategy: Slow Their Adoption
WIRED
The Best Robotic Pool Cleaners of 2026: Beatbot, iGarden, Dreame
The Best Robotic Pool Cleaners of 2026: Beatbot, iGarden, Dreame
WIRED
Here’s How Apple Is Updating Its Child Safety Features in iOS 27
Here’s How Apple Is Updating Its Child Safety Features in iOS 27
WIRED
28 Best STEM Toys for Kids (2026): Learning Made Fun
28 Best STEM Toys for Kids (2026): Learning Made Fun
WIRED
Scientists’ Side Hustle? Using AI and Quantum Computing to Generate New Peptides
Scientists’ Side Hustle? Using AI and Quantum Computing to Generate New Peptides
WIRED
Best External Hard Drives (2026): SSD to Store Data, Video, and More
Best External Hard Drives (2026): SSD to Store Data, Video, and More
WIRED
The 10 Best Pet Cameras of 2026: Furbo, Petcube, and Enabot
The 10 Best Pet Cameras of 2026: Furbo, Petcube, and Enabot
The Verge
Lorde says Ray-Ban Meta AI glasses are ‘not sexy’
Lorde says Ray-Ban Meta AI glasses are ‘not sexy’
The Verge
Shall We Go On Sinning So That Grace May Increase? is hypnotic, healing, and hopeful
Shall We Go On Sinning So That Grace May Increase? is hypnotic, healing, and hopeful
The Verge
Apple’s failed self-driving car program left a legacy of powerful AI chips
Apple’s failed self-driving car program left a legacy of powerful AI chips
The Verge
One of SteelSeries’ best gaming headsets is over $100 off
One of SteelSeries’ best gaming headsets is over $100 off
The Verge
Blue Prince became a bonding — and learning — experience for my family
Blue Prince became a bonding — and learning — experience for my family
The Verge
The fight against AI data centers is just beginning
The fight against AI data centers is just beginning
MarkTechPost
Prime Intellect Releases Verifiers v1: Composable Tasksets, Harnesses, and Runtimes for Agentic RL Training and Evaluations
Prime Intellect Releases Verifiers v1: Composable Tasksets, Harnesses, and Runtimes for Agentic RL Training and Evaluations
MarkTechPost
Meet NeuroVFM: A New Neuroimaging Foundation Model Trained With Vol-JEPA on Uncurated Clinical MRI and CT Volumes
Meet NeuroVFM: A New Neuroimaging Foundation Model Trained With Vol-JEPA on Uncurated Clinical MRI and CT Volumes
MarkTechPost
Guide to Loop Engineering: How ‘autoresearch’ and ‘Bilevel Autoresearch’ Turn AI Agents Into Autonomous Machine Learning ML Research Loops
Guide to Loop Engineering: How ‘autoresearch’ and ‘Bilevel Autoresearch’ Turn AI Agents Into Autonomous Machine Learning ML Research Loops
#LLMタグ
Gemini 3.5 Proは2026年7月17日公開か。なぜ延期された？ChatGPT・Claudeとの競争を整理する【AIテクノロジーラボ】
Gemini 3.5 Proは2026年7月17日公開か。なぜ延期された？ChatGPT・Claudeとの競争を整理する【AIテクノロジーラボ】
#LLMタグ
「AI批評」を「ストレステスト」にすり替えた日――Claudeの意図なき自己弁護はどう生成されるのか、ChatGPTの分析
「AI批評」を「ストレステスト」にすり替えた日――Claudeの意図なき自己弁護はどう生成されるのか、ChatGPTの分析
#LLMタグ
こういうタイプの質問に対するAIの回答は０点😵レベルですね。『家庭向けのAIエッジデバイスで成功している例ありますか？海外も含めて。』
こういうタイプの質問に対するAIの回答は０点😵レベルですね。『家庭向けのAIエッジデバイスで成功している例ありますか？海外も含めて。』
#LLMタグ
応用編—LLM API（Ollama・Google AI Studio）と連携すると何が起きるか【第24回】
応用編—LLM API（Ollama・Google AI Studio）と連携すると何が起きるか【第24回】
#LLMタグ
【「削除しました」は嘘かもしれない】Claudeエージェントの完了報告を実測で検証する — verify-after-actを実装する90行Python【2026-07】
【「削除しました」は嘘かもしれない】Claudeエージェントの完了報告を実測で検証する — verify-after-actを実装する90行Python【2026-07】
#LLMタグ
AIはなぜ誤字があっても意味をくみ取れるのか？Embeddingの仕組みを「単語がどうやってベクトルになるのか」からやさしく整理してみました
AIはなぜ誤字があっても意味をくみ取れるのか？Embeddingの仕組みを「単語がどうやってベクトルになるのか」からやさしく整理してみました
#AIタグ
＼大分でホームページを自分で作りたい方へ／AIで“集客につながるホームページ“を設計しませんか？「STEP1：体験設計コース」
＼大分でホームページを自分で作りたい方へ／AIで“集客につながるホームページ“を設計しませんか？「STEP1：体験設計コース」
#AIタグ
コード書いたことない50代が、リーマンショックまで遡って「VIX保険」を検証した話（それでも-33%は食らう）
コード書いたことない50代が、リーマンショックまで遡って「VIX保険」を検証した話（それでも-33%は食らう）
#AIタグ
Gemini 3.5 Proは2026年7月17日公開か。なぜ延期された？ChatGPT・Claudeとの競争を整理する【AIテクノロジーラボ】
Gemini 3.5 Proは2026年7月17日公開か。なぜ延期された？ChatGPT・Claudeとの競争を整理する【AIテクノロジーラボ】
Hugging Face Papers
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Hugging Face Papers
Video Generation Models are General-Purpose Vision Learners
Video Generation Models are General-Purpose Vision Learners
Hugging Face Papers
Scalable Visual Pretraining for Language Intelligence
Scalable Visual Pretraining for Language Intelligence
Hugging Face Papers
KronQ: LLM Quantization via Kronecker-Factored Hessian
KronQ: LLM Quantization via Kronecker-Factored Hessian
Hugging Face Papers
PanoWorld: Real-World Panoramic Generation
PanoWorld: Real-World Panoramic Generation
Hugging Face Papers
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Hugging Face Papers
Self-Guided Test-Time Training for Long-Context LLMs
Self-Guided Test-Time Training for Long-Context LLMs
Hugging Face Papers
Phone Segmentation and Recognition through Phonological Activation Mapping
Phone Segmentation and Recognition through Phonological Activation Mapping
Hugging Face Papers
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
Hugging Face Papers
A Sovereign, Open-Source Foundation Model for German and English
A Sovereign, Open-Source Foundation Model for German and English
Hugging Face Papers
VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery
VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery