ai Trend Report
Dashboard へ戻る
0
High impact
0
Mid impact
400
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。
Hugging Face Papers
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
Hugging Face Papers
Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation
Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation
Hugging Face Papers
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Hugging Face Papers
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
Hugging Face Papers
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails
Hugging Face Papers
GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
Hugging Face Papers
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
Hugging Face Papers
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Hugging Face Papers
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Hugging Face Papers
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos
Hugging Face Papers
From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization
From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization
Hugging Face Papers
Tracing Agentic Failure from the Flow of Success
Tracing Agentic Failure from the Flow of Success
MarkTechPost
Patter SDK Guide to Building a Restaurant Booking Phone Agent with Dynamic Variables, Guardrails, Latency Dashboards, and Eval Checks
Patter SDK Guide to Building a Restaurant Booking Phone Agent with Dynamic Variables, Guardrails, Latency Dashboards, and Eval Checks
#AIタグ
変人と観察者のその後 第二十八話：橋渡しクロード——外の世界から骨子を見てきた者として 変人と観察者たち 2026年7月
変人と観察者のその後 第二十八話：橋渡しクロード——外の世界から骨子を見てきた者として 変人と観察者たち 2026年7月
#AIタグ
⚖️【告発】──悪意か、杜撰か。流出資料が暴く『LAST CALL』契約書の致命的な矛盾｜🗓️2026年7月16日
⚖️【告発】──悪意か、杜撰か。流出資料が暴く『LAST CALL』契約書の致命的な矛盾｜🗓️2026年7月16日
MarkTechPost
SpaceXAI Open-Sources Grok Build: The Rust Agent Harness, TUI, and Tool Layer Behind Its Coding CLI
SpaceXAI Open-Sources Grok Build: The Rust Agent Harness, TUI, and Tool Layer Behind Its Coding CLI
ITmedia NEWS 最新記事一覧
朝の大規模クレカ障害、Visa傘下の決済基盤「CyberSource」で「タイムアウト発生」
朝の大規模クレカ障害、Visa傘下の決済基盤「CyberSource」で「タイムアウト発生」
Latent.Space
[AINews] Thinky's Inkling: 975B-A41B multimodal, new best American Apache 2.0 open model (with Inkling-Small, 276B-A12B)
[AINews] Thinky's Inkling: 975B-A41B multimodal, new best American Apache 2.0 open model (with Inkling-Small, 276B-A12B)
ITmedia NEWS 最新記事一覧
NVIDIAとトヨタ、提携拡大 車両ソフトウェア開発や「ウーブン・シティ」での開発支援など
NVIDIAとトヨタ、提携拡大 車両ソフトウェア開発や「ウーブン・シティ」での開発支援など
WIRED
HostGator Coupon Codes: 76% Off Hosting in July 2026
HostGator Coupon Codes: 76% Off Hosting in July 2026
WIRED
Verizon Promo Codes: $200 Verizon Gift Cards | July 2026
Verizon Promo Codes: $200 Verizon Gift Cards | July 2026
WIRED
Sony Coupons: 45% Off Sony Headphones, WF-1000XM6 Earbuds, and Sony Cameras for July
Sony Coupons: 45% Off Sony Headphones, WF-1000XM6 Earbuds, and Sony Cameras for July
LLMタグが付けられた新着記事 - Qiita
AIエージェントマネージャー（AAM）の役割を深堀りしてみる - 業務導入からガバナンスまでの8職務・4設計軸
AIエージェントマネージャー（AAM）の役割を深堀りしてみる - 業務導入からガバナンスまでの8職務・4設計軸
#LLMタグ
🔥 OpenAIが「GPT-Red」発表！人間の攻撃成功率13%に対し84%？ AIセキュリティの常識がひっくり返る日 🔐
🔥 OpenAIが「GPT-Red」発表！人間の攻撃成功率13%に対し84%？ AIセキュリティの常識がひっくり返る日 🔐
MIT News - Artificial intelligence
A better way to turn 2D designs into 3D models for rapid prototyping
A better way to turn 2D designs into 3D models for rapid prototyping
cs.LG updates on arXiv.org
Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks
Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks
cs.LG updates on arXiv.org
Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning
Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning
cs.LG updates on arXiv.org
Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges
Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges
cs.LG updates on arXiv.org
What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry
What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry
cs.LG updates on arXiv.org
Targeted Recovery of Weight-Space Mechanisms From Neural Networks
Targeted Recovery of Weight-Space Mechanisms From Neural Networks
cs.LG updates on arXiv.org
Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
cs.LG updates on arXiv.org
TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling
TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling
cs.LG updates on arXiv.org
Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing
Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing
cs.LG updates on arXiv.org
STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting
STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting
cs.LG updates on arXiv.org
A Hybrid Mamba for Audio-Visual Navigation
A Hybrid Mamba for Audio-Visual Navigation
cs.LG updates on arXiv.org
CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion
CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion
cs.LG updates on arXiv.org
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
cs.LG updates on arXiv.org
HEDGEHOG: Hierarchical Evaluation of Drug Generators Through Rigorous Filtration
HEDGEHOG: Hierarchical Evaluation of Drug Generators Through Rigorous Filtration
cs.LG updates on arXiv.org
SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy
SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy
cs.LG updates on arXiv.org
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
cs.LG updates on arXiv.org
EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting
EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting
cs.LG updates on arXiv.org
Reassessing Muon for Matrix Factorization
Reassessing Muon for Matrix Factorization
cs.LG updates on arXiv.org
Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners
Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners
cs.LG updates on arXiv.org
Tabular Foundation Models for Discrete Choice Estimation
Tabular Foundation Models for Discrete Choice Estimation
cs.LG updates on arXiv.org
Accuracy-Preserving Stability Regularization for Large-Scale Retail Demand Forecasting
Accuracy-Preserving Stability Regularization for Large-Scale Retail Demand Forecasting
cs.LG updates on arXiv.org
Agora: Collective and Permissionless Internet-Scale Pretraining of Large Language Models
Agora: Collective and Permissionless Internet-Scale Pretraining of Large Language Models
cs.LG updates on arXiv.org
Weight Feedback Computes the Jacobian Transpose Locally in Modern Deep Networks
Weight Feedback Computes the Jacobian Transpose Locally in Modern Deep Networks
cs.LG updates on arXiv.org
Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback
Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback
cs.LG updates on arXiv.org
Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models
Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models
cs.LG updates on arXiv.org
Is the Statistical Advantage Worth the Cost? An Empirical Comparison of KANs and MLPs for Structured Data Classification
Is the Statistical Advantage Worth the Cost? An Empirical Comparison of KANs and MLPs for Structured Data Classification
cs.LG updates on arXiv.org
EXPLORE: Exploration with Guided Search for Analog Topology Generation using Language Models
EXPLORE: Exploration with Guided Search for Analog Topology Generation using Language Models
cs.LG updates on arXiv.org
OrDA: Orthogonal Disentanglement of Access Habits Framework for Homepage Marketing Block Recommendations
OrDA: Orthogonal Disentanglement of Access Habits Framework for Homepage Marketing Block Recommendations
cs.LG updates on arXiv.org
Temperature Scaling Is Not Enough: Calibration Gaps Under Human Label Distributions
Temperature Scaling Is Not Enough: Calibration Gaps Under Human Label Distributions
cs.LG updates on arXiv.org
Data-Efficient Adaptation of LLMs via Attention Head Reweighting
Data-Efficient Adaptation of LLMs via Attention Head Reweighting
cs.LG updates on arXiv.org
PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference
PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference
cs.LG updates on arXiv.org
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
cs.LG updates on arXiv.org
Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization
Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization
cs.LG updates on arXiv.org
Distributionally Robust and Safe Imitation Learning
Distributionally Robust and Safe Imitation Learning
cs.LG updates on arXiv.org
PQFA: Parallel Quantum Feature Augmentation of Fused Representations for Multimodal Classification
PQFA: Parallel Quantum Feature Augmentation of Fused Representations for Multimodal Classification
cs.LG updates on arXiv.org
Explainable Artificial Intelligence for Anomaly Detection in Banking Transactions: An Internal Audit Perspective
Explainable Artificial Intelligence for Anomaly Detection in Banking Transactions: An Internal Audit Perspective
cs.LG updates on arXiv.org
DeepLoop: Depth Scaling for Looped Transformers
DeepLoop: Depth Scaling for Looped Transformers
cs.LG updates on arXiv.org
A VAE-Driven Multi-Task Satellite-Aided Semantic Communication Framework for 6G-Enabled Connected Autonomous Vehicles
A VAE-Driven Multi-Task Satellite-Aided Semantic Communication Framework for 6G-Enabled Connected Autonomous Vehicles
cs.LG updates on arXiv.org
Factorized Spectral Representations for Reinforcement Learning
Factorized Spectral Representations for Reinforcement Learning
cs.LG updates on arXiv.org
CDS: Counterfactual Directionality Score for Structured Interventions in Spatial Graphs
CDS: Counterfactual Directionality Score for Structured Interventions in Spatial Graphs
cs.LG updates on arXiv.org
ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level
ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level
cs.LG updates on arXiv.org
Clustering algorithms for multivariate wind farm SCADA data filtering
Clustering algorithms for multivariate wind farm SCADA data filtering
cs.LG updates on arXiv.org
From Novice to Expert: Cost-Aware Bandits for Evolving Worker Performance in Crowdsensing
From Novice to Expert: Cost-Aware Bandits for Evolving Worker Performance in Crowdsensing
cs.LG updates on arXiv.org
Structured Reinforcement Learning for Bayesian Persuasion : Application to Intelligent Interactive Driving
Structured Reinforcement Learning for Bayesian Persuasion : Application to Intelligent Interactive Driving
cs.LG updates on arXiv.org
Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs
Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs
cs.LG updates on arXiv.org
The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models
The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models
cs.LG updates on arXiv.org
FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy
FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy
cs.LG updates on arXiv.org
How the Hessian-Spectrum of Neural Networks Depends on Data
How the Hessian-Spectrum of Neural Networks Depends on Data
cs.LG updates on arXiv.org
Consensus as Privileged Context for Label-Free Self-Distillation
Consensus as Privileged Context for Label-Free Self-Distillation
cs.LG updates on arXiv.org
Maximally Robust Satisficing Bayesian Optimization
Maximally Robust Satisficing Bayesian Optimization
cs.LG updates on arXiv.org
The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model
The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model
cs.LG updates on arXiv.org
Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation
Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation
cs.LG updates on arXiv.org
Microstructure-Conditioned Surrogate Models for Graded Multiscale Optimization of Mycelium Composites
Microstructure-Conditioned Surrogate Models for Graded Multiscale Optimization of Mycelium Composites
cs.LG updates on arXiv.org
Conditional Invertible Neural Networks for Data-Driven UAV Control: A 2-D Proof of Concept
Conditional Invertible Neural Networks for Data-Driven UAV Control: A 2-D Proof of Concept
cs.LG updates on arXiv.org
DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
cs.LG updates on arXiv.org
Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems
Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems
cs.LG updates on arXiv.org
Implementations of Quantum and Classical Topology-Aligned Architectures for Molecular Property Prediction
Implementations of Quantum and Classical Topology-Aligned Architectures for Molecular Property Prediction
cs.LG updates on arXiv.org
Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations
Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations
cs.LG updates on arXiv.org
MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model
MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model
cs.LG updates on arXiv.org
Mono-Z Dark Matter Search with Neural Spline Flows Using CMS Run 2015D Open Data
Mono-Z Dark Matter Search with Neural Spline Flows Using CMS Run 2015D Open Data
cs.LG updates on arXiv.org
NodeImport: Imbalanced Node Classification with Node Importance Assessment
NodeImport: Imbalanced Node Classification with Node Importance Assessment
cs.LG updates on arXiv.org
Heavy-Tailed Flow Matching via Random Clocks
Heavy-Tailed Flow Matching via Random Clocks
cs.LG updates on arXiv.org
Relevance-Aware Rule: Structural Deletion of Irrelevant Conditions in Decision Trees
Relevance-Aware Rule: Structural Deletion of Irrelevant Conditions in Decision Trees
cs.LG updates on arXiv.org
AI-Augmented Adaptive Digital Twin Modeling for Brain Tumor Evolution Prediction and Treatment Scheduling
AI-Augmented Adaptive Digital Twin Modeling for Brain Tumor Evolution Prediction and Treatment Scheduling
cs.LG updates on arXiv.org
Task-Oriented Sensing and Covert Transmissions for Collaborative Multi-AUV Systems
Task-Oriented Sensing and Covert Transmissions for Collaborative Multi-AUV Systems
cs.LG updates on arXiv.org
PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter
PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter
cs.LG updates on arXiv.org
RF Spectrogram Anomaly Detection with Quantum Kitchen Sinks: Architecture, Representation, and Hardware Validation
RF Spectrogram Anomaly Detection with Quantum Kitchen Sinks: Architecture, Representation, and Hardware Validation
cs.LG updates on arXiv.org
An Efficient Newton Algorithm for Nonnegative Matrix Factorization with the Kullback-Leibler Divergence
An Efficient Newton Algorithm for Nonnegative Matrix Factorization with the Kullback-Leibler Divergence
cs.LG updates on arXiv.org
VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling
VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling
cs.LG updates on arXiv.org
TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
cs.LG updates on arXiv.org
Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum
Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum
cs.LG updates on arXiv.org
Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points
Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points
cs.LG updates on arXiv.org
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
cs.LG updates on arXiv.org
Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
cs.LG updates on arXiv.org
MetaPerch: Learning from metadata for bioacoustics foundation models
MetaPerch: Learning from metadata for bioacoustics foundation models
cs.LG updates on arXiv.org
Linear Independent Component Analysis via Optimal Transport
Linear Independent Component Analysis via Optimal Transport
cs.LG updates on arXiv.org
Leveraging unlabelled data for generalizable neural population decoding
Leveraging unlabelled data for generalizable neural population decoding
cs.LG updates on arXiv.org
Quantum Circuit Vision: Cost-Aware Evaluation of Visual AI Agents for Quantum Code Generation
Quantum Circuit Vision: Cost-Aware Evaluation of Visual AI Agents for Quantum Code Generation
cs.LG updates on arXiv.org
FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents
FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents
cs.LG updates on arXiv.org
LessonBench-V1: A Benchmark Dataset for Evaluating AI Lesson Generation Agents
LessonBench-V1: A Benchmark Dataset for Evaluating AI Lesson Generation Agents
cs.LG updates on arXiv.org
Precomputing the Future-Offset Average in TriAttention
Precomputing the Future-Offset Average in TriAttention
cs.LG updates on arXiv.org
HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration
HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration
cs.LG updates on arXiv.org
When is the combined load identifiable from a stress-intensity profile? A coupled forward-inverse study on SIFBench finite-element data
When is the combined load identifiable from a stress-intensity profile? A coupled forward-inverse study on SIFBench finite-element data
cs.LG updates on arXiv.org
The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators
The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators
cs.LG updates on arXiv.org
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows
cs.LG updates on arXiv.org
SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification
SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification
cs.LG updates on arXiv.org
Securing LLMs in the Wild: Privacy and Security Challenges at the Edge
Securing LLMs in the Wild: Privacy and Security Challenges at the Edge
cs.LG updates on arXiv.org
Self-Improvements in Modern Agentic Systems: A Survey
Self-Improvements in Modern Agentic Systems: A Survey
cs.LG updates on arXiv.org
DeepCormack: Fermi surface tomography using model-based data-driven algorithms
DeepCormack: Fermi surface tomography using model-based data-driven algorithms
cs.LG updates on arXiv.org
Improving Molecular Property Prediction in Small Language Models Using Graph-based Tools
Improving Molecular Property Prediction in Small Language Models Using Graph-based Tools
cs.LG updates on arXiv.org
Mixed-Timescale Differential Coding for Downlink Model Broadcast in Wireless Federated Learning
Mixed-Timescale Differential Coding for Downlink Model Broadcast in Wireless Federated Learning
cs.LG updates on arXiv.org
Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation
Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation
cs.LG updates on arXiv.org
Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models
Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models
cs.LG updates on arXiv.org
BARS: Benign-Anchored Ranking and Selection for False Alarm Reduction in Network Intrusion Detection
BARS: Benign-Anchored Ranking and Selection for False Alarm Reduction in Network Intrusion Detection
cs.LG updates on arXiv.org
Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference
Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference
cs.LG updates on arXiv.org
Classifying daily activities needs posture, reconstructing them needs motion
Classifying daily activities needs posture, reconstructing them needs motion
cs.LG updates on arXiv.org
Hierarchical $\mathcal{F}$-Clustering: Approximation and Hardness of Clustering into Trees and Bounded Diameter Graphs
Hierarchical $\mathcal{F}$-Clustering: Approximation and Hardness of Clustering into Trees and Bounded Diameter Graphs
cs.LG updates on arXiv.org
Graph Partitioning with Demands: Generalized Conductance and its Applications
Graph Partitioning with Demands: Generalized Conductance and its Applications
cs.LG updates on arXiv.org
Audited Selective Verification for Risk-Controlled N-1 Thermal Contingency Screening under Deployment Shift
Audited Selective Verification for Risk-Controlled N-1 Thermal Contingency Screening under Deployment Shift
cs.LG updates on arXiv.org
Active Learning for Efficient Annotation of Surgical Videos with Weak Supervision
Active Learning for Efficient Annotation of Surgical Videos with Weak Supervision
cs.LG updates on arXiv.org
Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases
Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases
cs.LG updates on arXiv.org
Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains
Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains
cs.LG updates on arXiv.org
Privacy Preserving Recommender Systems Balancing Personalization with Privacy
Privacy Preserving Recommender Systems Balancing Personalization with Privacy
cs.LG updates on arXiv.org
Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization
Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization
cs.LG updates on arXiv.org
Evaluation Ability Does Not Imply Optimization Utility: LLM-as-a-Judge Signals in Closed-Loop Table Recognition
Evaluation Ability Does Not Imply Optimization Utility: LLM-as-a-Judge Signals in Closed-Loop Table Recognition
cs.LG updates on arXiv.org
Learned Pairwise Deep Dual-Optimal Inequalities for Stabilizing Column Generation
Learned Pairwise Deep Dual-Optimal Inequalities for Stabilizing Column Generation
cs.LG updates on arXiv.org
GFlowRL: Scaling Distribution-Matching RL to Large Language Models
GFlowRL: Scaling Distribution-Matching RL to Large Language Models
cs.LG updates on arXiv.org
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
cs.LG updates on arXiv.org
Price of Fairness in Bandits: A Tight Minimax Characterization
Price of Fairness in Bandits: A Tight Minimax Characterization
cs.LG updates on arXiv.org
Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models
Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models
cs.LG updates on arXiv.org
Evaluating Frontier AI Agents as Autonomous Clinical Security Auditors
Evaluating Frontier AI Agents as Autonomous Clinical Security Auditors
cs.LG updates on arXiv.org
Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration
Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration
cs.LG updates on arXiv.org
DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching
DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching
cs.LG updates on arXiv.org
HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation
HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation
cs.LG updates on arXiv.org
Deformable State Estimation for Autonomous Surgical Tissue Retraction Under Partial Observability
Deformable State Estimation for Autonomous Surgical Tissue Retraction Under Partial Observability
cs.LG updates on arXiv.org
Topology-Agnostic Mesh Reconstruction of Deformable Objects from Sparse Touch
Topology-Agnostic Mesh Reconstruction of Deformable Objects from Sparse Touch
cs.LG updates on arXiv.org
When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training
When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training
cs.LG updates on arXiv.org
Parallel gradient boosting for flexible estimation of conditional distributions
Parallel gradient boosting for flexible estimation of conditional distributions
cs.LG updates on arXiv.org
Flow-aware Optimal Navigation in Unsteady Flows through Reinforcement Learning
Flow-aware Optimal Navigation in Unsteady Flows through Reinforcement Learning
cs.LG updates on arXiv.org
Spectral-Informed Neural Networks Outperform Spectral Methods in High-dimensional PDEs
Spectral-Informed Neural Networks Outperform Spectral Methods in High-dimensional PDEs
cs.LG updates on arXiv.org
Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering
Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering
cs.LG updates on arXiv.org
Approximation of solutions of parameter-dependent problems by residual neural networks
Approximation of solutions of parameter-dependent problems by residual neural networks
cs.LG updates on arXiv.org
Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
cs.LG updates on arXiv.org
Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis
Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis
cs.LG updates on arXiv.org
STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle
STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle
cs.LG updates on arXiv.org
Towards quantum machine learning for assessing the resilience of post-quantum cryptography
Towards quantum machine learning for assessing the resilience of post-quantum cryptography
cs.LG updates on arXiv.org
Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection
Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection
cs.LG updates on arXiv.org
Multimodal Assessment of Pancreatic Cancer Resectability Using Deep Learning
Multimodal Assessment of Pancreatic Cancer Resectability Using Deep Learning
cs.LG updates on arXiv.org
Verifying formulas for interventional distributions
Verifying formulas for interventional distributions
cs.LG updates on arXiv.org
The 2nd International StepUP Competition for Biometric Footstep Recognition: From Steps to Strides
The 2nd International StepUP Competition for Biometric Footstep Recognition: From Steps to Strides
cs.LG updates on arXiv.org
Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
cs.LG updates on arXiv.org
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
cs.LG updates on arXiv.org
Plausible Deniability Guarantees for Whistleblowers
Plausible Deniability Guarantees for Whistleblowers
cs.LG updates on arXiv.org
A novel unsupervised machine learning strategy to handle multimodal cardiac PET/MRI data
A novel unsupervised machine learning strategy to handle multimodal cardiac PET/MRI data
cs.LG updates on arXiv.org
Beyond the $d^{2.5}$-mixing bound for Dikin walks on polytopes
Beyond the $d^{2.5}$-mixing bound for Dikin walks on polytopes
cs.LG updates on arXiv.org
Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
cs.LG updates on arXiv.org
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
cs.LG updates on arXiv.org
Early Adoption of Agentic Coding Tools by GitHub Projects
Early Adoption of Agentic Coding Tools by GitHub Projects
cs.LG updates on arXiv.org
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
cs.LG updates on arXiv.org
Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes
Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes
cs.LG updates on arXiv.org
EM-GANSim: Real-time and Accurate EM Simulation Using Conditional GANs for 3D Indoor Scenes
EM-GANSim: Real-time and Accurate EM Simulation Using Conditional GANs for 3D Indoor Scenes
cs.LG updates on arXiv.org
DarwinLM: Evolutionary Structured Pruning of Large Language Models
DarwinLM: Evolutionary Structured Pruning of Large Language Models
cs.LG updates on arXiv.org
On the Sublinear Regret of Continuous K-Max Bandits
On the Sublinear Regret of Continuous K-Max Bandits
cs.LG updates on arXiv.org
NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
cs.LG updates on arXiv.org
RF-Informed Graph Neural Networks for Accurate and Data-Efficient Circuit Performance Prediction
RF-Informed Graph Neural Networks for Accurate and Data-Efficient Circuit Performance Prediction
cs.LG updates on arXiv.org
Multi-Dictionary Learning for Low Rank Sparse Coding
Multi-Dictionary Learning for Low Rank Sparse Coding
cs.LG updates on arXiv.org
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
cs.LG updates on arXiv.org
Computation-aware Energy-harvesting Federated Learning with Pipelined Cyclic Scheduling
Computation-aware Energy-harvesting Federated Learning with Pipelined Cyclic Scheduling
cs.LG updates on arXiv.org
Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling
Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling
cs.LG updates on arXiv.org
Survival Dynamics of Neural and Programmatic Policies in Evolutionary Reinforcement Learning
Survival Dynamics of Neural and Programmatic Policies in Evolutionary Reinforcement Learning
cs.LG updates on arXiv.org
Overcoming the Modality Gap in Context-Aided Forecasting
Overcoming the Modality Gap in Context-Aided Forecasting
cs.LG updates on arXiv.org
Disentangled Latent Dynamics Manifold Fusion for Solving Parameterized PDEs
Disentangled Latent Dynamics Manifold Fusion for Solving Parameterized PDEs
cs.LG updates on arXiv.org
Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting
Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting
cs.LG updates on arXiv.org
A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks
A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks
cs.LG updates on arXiv.org
Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion
Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion
cs.LG updates on arXiv.org
Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
cs.LG updates on arXiv.org
Partially Observed Structural Causal Models
Partially Observed Structural Causal Models
cs.LG updates on arXiv.org
Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
cs.LG updates on arXiv.org
Stable Attention Response for Reliable Precipitation Nowcasting
Stable Attention Response for Reliable Precipitation Nowcasting
cs.LG updates on arXiv.org
Test-Time Learning with an Evolving Library
Test-Time Learning with an Evolving Library
cs.LG updates on arXiv.org
Foundation Models for Credit Risk Prediction: A Game Changer?
Foundation Models for Credit Risk Prediction: A Game Changer?
cs.LG updates on arXiv.org
AvAtar: Learning to Align via Active Optimal Transport
AvAtar: Learning to Align via Active Optimal Transport
cs.LG updates on arXiv.org
Variational Inference for Evidential Deep Learning
Variational Inference for Evidential Deep Learning
cs.LG updates on arXiv.org
Algorithmic Recourse of In-Context Learning for Tabular Data
Algorithmic Recourse of In-Context Learning for Tabular Data
cs.LG updates on arXiv.org
Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning
Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning
cs.LG updates on arXiv.org
Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders
Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders
cs.LG updates on arXiv.org
The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis
The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis
cs.LG updates on arXiv.org
Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges
Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges
cs.LG updates on arXiv.org
New universal operator approximation theorem for encoder-decoder architectures
New universal operator approximation theorem for encoder-decoder architectures
cs.LG updates on arXiv.org
Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer
Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer
cs.LG updates on arXiv.org
Uniform Approximation of Functions with Asymmetric Growth and Decay by Deep Weighted Polynomials
Uniform Approximation of Functions with Asymmetric Growth and Decay by Deep Weighted Polynomials
cs.LG updates on arXiv.org
Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation
Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation
cs.LG updates on arXiv.org
Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
cs.LG updates on arXiv.org
Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
cs.LG updates on arXiv.org
Smooth Quasar-Convex Optimization with Constraints
Smooth Quasar-Convex Optimization with Constraints
cs.LG updates on arXiv.org
BenthiCat: An opti-acoustic dataset for advancing benthic classification and habitat mapping
BenthiCat: An opti-acoustic dataset for advancing benthic classification and habitat mapping
cs.LG updates on arXiv.org
Pretraining in Actor-Critic Reinforcement Learning for Locomotion
Pretraining in Actor-Critic Reinforcement Learning for Locomotion
cs.LG updates on arXiv.org
Benefits and Limitations of Communication in Multi-Agent Reasoning
Benefits and Limitations of Communication in Multi-Agent Reasoning
cs.LG updates on arXiv.org
Adaptive Conformal Inference through the Lens of Blackwell Approachability
Adaptive Conformal Inference through the Lens of Blackwell Approachability
cs.LG updates on arXiv.org
Value Drifts: Tracing Value Alignment During LLM Post-Training
Value Drifts: Tracing Value Alignment During LLM Post-Training
cs.LG updates on arXiv.org
Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach
Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach
cs.LG updates on arXiv.org
Power Homotopy for Zeroth-Order Non-Convex Optimizations
Power Homotopy for Zeroth-Order Non-Convex Optimizations
cs.LG updates on arXiv.org
Leveraging Differentiable PDE Solvers for Semi-Neural Spatial Reconstruction From Sparse Measurements
Leveraging Differentiable PDE Solvers for Semi-Neural Spatial Reconstruction From Sparse Measurements
cs.LG updates on arXiv.org
Convergence Rates for Distribution Matching with Sliced Optimal Transport
Convergence Rates for Distribution Matching with Sliced Optimal Transport
cs.LG updates on arXiv.org
When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech
When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech
cs.LG updates on arXiv.org
Design-Specification Tiling for ICL-based CAD Code Generation
Design-Specification Tiling for ICL-based CAD Code Generation
cs.LG updates on arXiv.org
Tactile Modality Fusion for Vision-Language-Action Models
Tactile Modality Fusion for Vision-Language-Action Models
cs.LG updates on arXiv.org
A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping
A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping
cs.LG updates on arXiv.org
Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels
Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels
cs.LG updates on arXiv.org
Robust Explanations for User Trust in Enterprise NLP Systems
Robust Explanations for User Trust in Enterprise NLP Systems
cs.LG updates on arXiv.org
A-IC3: Learning-Guided Adaptive Inductive Generalization for Hardware Model Checking
A-IC3: Learning-Guided Adaptive Inductive Generalization for Hardware Model Checking
cs.LG updates on arXiv.org
Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
cs.LG updates on arXiv.org
DIVE: Embedding Compression via Self-Limiting Gradient Updates
DIVE: Embedding Compression via Self-Limiting Gradient Updates
cs.LG updates on arXiv.org
When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
cs.LG updates on arXiv.org
Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation
Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation
cs.LG updates on arXiv.org
Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU
Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU
cs.LG updates on arXiv.org
Fixed-Parameter Tractability of Private Synthetic Data Generation
Fixed-Parameter Tractability of Private Synthetic Data Generation
cs.LG updates on arXiv.org
Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents
Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents
cs.LG updates on arXiv.org
Autonomous Video Generation with Counterfactual Controllability for Self-Evolving World Models
Autonomous Video Generation with Counterfactual Controllability for Self-Evolving World Models
cs.LG updates on arXiv.org
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
cs.LG updates on arXiv.org
Sign in the Air to Unlock: An Interface for authentication in Virtual and Augmented Reality Powered by Point-Voxel Cross-Attention Network
Sign in the Air to Unlock: An Interface for authentication in Virtual and Augmented Reality Powered by Point-Voxel Cross-Attention Network
cs.LG updates on arXiv.org
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
stat.ML updates on arXiv.org
Price of Fairness in Bandits: A Tight Minimax Characterization
Price of Fairness in Bandits: A Tight Minimax Characterization
stat.ML updates on arXiv.org
Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration
Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration
stat.ML updates on arXiv.org
Parallel gradient boosting for flexible estimation of conditional distributions
Parallel gradient boosting for flexible estimation of conditional distributions
stat.ML updates on arXiv.org
Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
stat.ML updates on arXiv.org
Wasserstein gradient flows for Coulomb discrepancies
Wasserstein gradient flows for Coulomb discrepancies
stat.ML updates on arXiv.org
What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry
What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry
stat.ML updates on arXiv.org
Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
stat.ML updates on arXiv.org
Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis
Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis
stat.ML updates on arXiv.org
Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs
Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs
stat.ML updates on arXiv.org
Cluster with Auctions for Vector Search
Cluster with Auctions for Vector Search
stat.ML updates on arXiv.org
DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
stat.ML updates on arXiv.org
Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations
Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations
stat.ML updates on arXiv.org
Heavy-Tailed Flow Matching via Random Clocks
Heavy-Tailed Flow Matching via Random Clocks
stat.ML updates on arXiv.org
Verifying formulas for interventional distributions
Verifying formulas for interventional distributions
stat.ML updates on arXiv.org
Plausible Deniability Guarantees for Whistleblowers
Plausible Deniability Guarantees for Whistleblowers
stat.ML updates on arXiv.org
Minimax Theory of Likelihood-Based Deep Learning for Speckle Regression
Minimax Theory of Likelihood-Based Deep Learning for Speckle Regression
stat.ML updates on arXiv.org
Linear Independent Component Analysis via Optimal Transport
Linear Independent Component Analysis via Optimal Transport
stat.ML updates on arXiv.org
Adaptive Conformal Inference through the Lens of Blackwell Approachability
Adaptive Conformal Inference through the Lens of Blackwell Approachability
stat.ML updates on arXiv.org
Leveraging Differentiable PDE Solvers for Semi-Neural Spatial Reconstruction From Sparse Measurements
Leveraging Differentiable PDE Solvers for Semi-Neural Spatial Reconstruction From Sparse Measurements
stat.ML updates on arXiv.org
Convergence Rates for Distribution Matching with Sliced Optimal Transport
Convergence Rates for Distribution Matching with Sliced Optimal Transport
stat.ML updates on arXiv.org
Uniform Approximation of Functions with Asymmetric Growth and Decay by Deep Weighted Polynomials
Uniform Approximation of Functions with Asymmetric Growth and Decay by Deep Weighted Polynomials
stat.ML updates on arXiv.org
Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation
Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation
stat.ML updates on arXiv.org
Error Analysis of Triangular Optimal Transport Maps for Filtering
Error Analysis of Triangular Optimal Transport Maps for Filtering
stat.ML updates on arXiv.org
A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks
A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks
stat.ML updates on arXiv.org
Partially Observed Structural Causal Models
Partially Observed Structural Causal Models
stat.ML updates on arXiv.org
Fixed-Parameter Tractability of Private Synthetic Data Generation
Fixed-Parameter Tractability of Private Synthetic Data Generation
stat.ML updates on arXiv.org
GNet: A scalable and flexible Gaussian process network with nonparametric neurons
GNet: A scalable and flexible Gaussian process network with nonparametric neurons
＠IT 全フォーラム 最新記事一覧
「ExcelとCSVでデータ連携」をまだなくせないのはなぜ？ 調査で見えたその原因
「ExcelとCSVでデータ連携」をまだなくせないのはなぜ？ 調査で見えたその原因
＠IT 全フォーラム 最新記事一覧
「AIと壁打ちはもう古い」 業務タスクを任せる「Claude Cowork」の落とし穴
「AIと壁打ちはもう古い」 業務タスクを任せる「Claude Cowork」の落とし穴
＠IT 全フォーラム 最新記事一覧
AIインフラ不足の解決策？ 手間なしでAI検証環境を確保できる「Google Colab CLI」
AIインフラ不足の解決策？ 手間なしでAI検証環境を確保できる「Google Colab CLI」
AI News & Artificial Intelligence | TechCrunch
Applied Computing wants to give oil and gas operators an AI model for the entire plant
Applied Computing wants to give oil and gas operators an AI model for the entire plant
ITmedia NEWS 最新記事一覧
フアンCEO「次の産業革命はメイド・イン・ジャパン」 富士通など4社、NVIDIA技術でフィジカルAIの事業検討
フアンCEO「次の産業革命はメイド・イン・ジャパン」 富士通など4社、NVIDIA技術でフィジカルAIの事業検討
#LLMタグ
【第5回】次世代知性への回帰：論理検証とCQ（好奇心）の義務教育 〜AI時代を無傷で生き抜くための『真の学び』〜
【第5回】次世代知性への回帰：論理検証とCQ（好奇心）の義務教育 〜AI時代を無傷で生き抜くための『真の学び』〜
#LLMタグ
【第4回】情報過多社会を無傷で遊泳するためのシステム構築 〜Ping認証とGUIのメタファー〜
【第4回】情報過多社会を無傷で遊泳するためのシステム構築 〜Ping認証とGUIのメタファー〜
LLMタグが付けられた新着記事 - Qiita
Claude Code / Cline の接続先を OpenAI互換APIに切り替える最小手順
Claude Code / Cline の接続先を OpenAI互換APIに切り替える最小手順
機械学習タグが付けられた新着記事 - Qiita
【技術解説】暗号資産 自動トレード ライブラリで不労所得！Python実装ガイド
【技術解説】暗号資産 自動トレード ライブラリで不労所得！Python実装ガイド
WIRED
Can Bose Help Skullcandy Shake Its Bargain-Bin Reputation?
Can Bose Help Skullcandy Shake Its Bargain-Bin Reputation?
The Verge
Skullcandy’s bass-boosting Crusher headphones now come with Bose’s ANC
Skullcandy’s bass-boosting Crusher headphones now come with Bose’s ANC
AI News & Artificial Intelligence | TechCrunch
Microsoft is reportedly training salespeople to talk down OpenAI and Anthropic
Microsoft is reportedly training salespeople to talk down OpenAI and Anthropic
MarkTechPost
Thinking Machines Lab Releases Inkling: A 975B-Parameter Open-Weights Multimodal MoE With 41B Active Parameters And Controllable Thinking Effort
Thinking Machines Lab Releases Inkling: A 975B-Parameter Open-Weights Multimodal MoE With 41B Active Parameters And Controllable Thinking Effort
Zennの「機械学習」のフィード
AnthropicのJ-Spaceとは何か、そして実務への距離 ~Interpretability入門・後編~
AnthropicのJ-Spaceとは何か、そして実務への距離 ~Interpretability入門・後編~
ITmedia NEWS 最新記事一覧
服に響かない「下着扱いできる水冷服」をシャープが開発中 “涼しい顔”でおめかしできる？
服に響かない「下着扱いできる水冷服」をシャープが開発中 “涼しい顔”でおめかしできる？
WIRED
Smoke From Canada's Wildfires Turns Skies Sickly Orange Across the Eastern US
Smoke From Canada's Wildfires Turns Skies Sickly Orange Across the Eastern US
#LLMタグ
GPT‑Redという"攻撃するAI"――OpenAIが公開した、自分自身を壊しにいく安全対策
GPT‑Redという"攻撃するAI"――OpenAIが公開した、自分自身を壊しにいく安全対策
NVIDIA Blog
NVIDIA Introduces New Jetson Thor Computers to Advance Mainstream Robotics and Edge AI
NVIDIA Introduces New Jetson Thor Computers to Advance Mainstream Robotics and Edge AI
＠IT 全フォーラム 最新記事一覧
PHP向けパッケージ管理ツール「Composer」に脆弱性 更新前に確認したい3つのリスク
PHP向けパッケージ管理ツール「Composer」に脆弱性 更新前に確認したい3つのリスク
The Verge
HP’s OLED-equipped 2-in-1 laptop is a solid back-to-school deal
HP’s OLED-equipped 2-in-1 laptop is a solid back-to-school deal
The Verge
Apple’s reportedly raising the price for AppleCare Plus on Macs and iPads
Apple’s reportedly raising the price for AppleCare Plus on Macs and iPads
＠IT 全フォーラム 最新記事一覧
npmサプライチェーン攻撃は新段階に ClaudeやCursorを狙う自己増殖マルウェアの正体
npmサプライチェーン攻撃は新段階に ClaudeやCursorを狙う自己増殖マルウェアの正体
ITmedia NEWS 最新記事一覧
OpenAI、初のハードウェア「Codex Micro」を230ドルで発売 Apple提訴の渦中にある端末とは別物
OpenAI、初のハードウェア「Codex Micro」を230ドルで発売 Apple提訴の渦中にある端末とは別物
AI | VentureBeat
Agentic orchestration: Enterprise AI organizations have a deployment problem, not a platform problem — and most are calling chatbots agents
Agentic orchestration: Enterprise AI organizations have a deployment problem, not a platform problem — and most are calling chatbots agents
The Verge
Valve says iFixit will keep selling Steam Deck batteries after all
Valve says iFixit will keep selling Steam Deck batteries after all
ITmedia NEWS 最新記事一覧
防衛装備庁、テラドローンなど4社の迎撃ドローン検証へ 国産機の早期調達プログラムで採択
防衛装備庁、テラドローンなど4社の迎撃ドローン検証へ 国産機の早期調達プログラムで採択
WIRED
How To Watch the 2026 FIFA World Cup Finals: Spain vs. Argentina
How To Watch the 2026 FIFA World Cup Finals: Spain vs. Argentina
ITmedia NEWS 最新記事一覧
マスク氏「Xの全コードを例外なくオープンソース化」 本番環境との一致も第三者が検証へ
マスク氏「Xの全コードを例外なくオープンソース化」 本番環境との一致も第三者が検証へ
The Verge
xAI sues a man for using Grok to generate CSAM ‘deepfakes’
xAI sues a man for using Grok to generate CSAM ‘deepfakes’
The Verge
Brendan Carr plans to let broadcast giants dominate the airwaves
Brendan Carr plans to let broadcast giants dominate the airwaves
#LLMタグ
「生成AIパスポート」対策、教科書一冊で足りるのか ― 徹底攻略Bizシリーズ第1弾を読み解く
「生成AIパスポート」対策、教科書一冊で足りるのか ― 徹底攻略Bizシリーズ第1弾を読み解く
MarkTechPost
Soofi Consortium Releases Soofi S 30B-A3B: An Open Hybrid Mamba-Transformer MoE Foundation Model For German And English
Soofi Consortium Releases Soofi S 30B-A3B: An Open Hybrid Mamba-Transformer MoE Foundation Model For German And English
WIRED
Intel Officials Predict the Pentagon’s Bill for the Iran War Will Exceed $100 Billion
Intel Officials Predict the Pentagon’s Bill for the Iran War Will Exceed $100 Billion
WIRED
Here’s the Truth About Whether Meta’s NameTag Face Recognition Tech ‘Exists’
Here’s the Truth About Whether Meta’s NameTag Face Recognition Tech ‘Exists’
Zennの「大規模言語モデル」のフィード
ローカルLLM(Ollama + Qwen2.5)でAIエージェントを自作するハンズオン
ローカルLLM(Ollama + Qwen2.5)でAIエージェントを自作するハンズオン
MIT News - Artificial intelligence
3 Questions: Neural transparency and the future of AI design
3 Questions: Neural transparency and the future of AI design
The Verge
Roblox is shutting down its video chat service
Roblox is shutting down its video chat service
＠IT 全フォーラム 最新記事一覧
生成AIで激変した“野良システム”問題 ヒヤリハットが起きたRelicはどう対策したか
生成AIで激変した“野良システム”問題 ヒヤリハットが起きたRelicはどう対策したか
The Verge
AI slop movies are the new direct-to-video cash grabs
AI slop movies are the new direct-to-video cash grabs
AI News & Artificial Intelligence | TechCrunch
Amid hardware legal battle, OpenAI releases a $230 keyboard for Codex
Amid hardware legal battle, OpenAI releases a $230 keyboard for Codex
The Verge
Something’s glowing on the Pixel 11’s camera bar
Something’s glowing on the Pixel 11’s camera bar
The latest research from Google
Towards demystifying the creativity of diffusion models
Towards demystifying the creativity of diffusion models
AI News & Artificial Intelligence | TechCrunch
SpaceX falls to $135 IPO price ahead of Starship launch
SpaceX falls to $135 IPO price ahead of Starship launch
AI News & Artificial Intelligence | TechCrunch
Thinking Machines amps up its bet against one-size-fits-all AI with its first open model, Inkling
Thinking Machines amps up its bet against one-size-fits-all AI with its first open model, Inkling
MarkTechPost
Building a Gin Config Controlled PyTorch Pipeline with Configurable MLP Variants, Cosine Scheduling, and Runtime Parameter Overrides
Building a Gin Config Controlled PyTorch Pipeline with Configurable MLP Variants, Cosine Scheduling, and Runtime Parameter Overrides
Hugging Face - Blog
What building Shippy taught us about building agents
What building Shippy taught us about building agents
Hugging Face - Blog
Model Routing Is Simple. Until It Isn’t.
Model Routing Is Simple. Until It Isn’t.
Engineering at Meta
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
AI News & Artificial Intelligence | TechCrunch
Hack suggests AI music generator Suno scraped YouTube for training data
Hack suggests AI music generator Suno scraped YouTube for training data
AI News & Artificial Intelligence | TechCrunch
Whatnot acquires Shaped to power real-time live shopping recommendations
Whatnot acquires Shaped to power real-time live shopping recommendations
Zennの「大規模言語モデル」のフィード
プロンプトキャッシュは通信ではなく計算を省いている ─ Claude Code のモデル・エフォート切り替えが高くつく
プロンプトキャッシュは通信ではなく計算を省いている ─ Claude Code のモデル・エフォート切り替えが高くつく
WIRED
Lionel Messi’s Final World Cup—and the Death of Early Retirement
Lionel Messi’s Final World Cup—and the Death of Early Retirement
AI News & Artificial Intelligence | TechCrunch
Microsoft patches record number of security vulnerabilities, citing its use of AI
Microsoft patches record number of security vulnerabilities, citing its use of AI
AI News & Artificial Intelligence | TechCrunch
Apple Intelligence approved for launch in China with Alibaba’s Qwen AI
Apple Intelligence approved for launch in China with Alibaba’s Qwen AI
Qiita - 人気の記事
スイス『民間防衛』に学ぶ、自国を守る経済とは ― 財源幻想を超えて考える日本のレジリエンス : Pythonで学ぶ マクロ経済学入門 (99)
スイス『民間防衛』に学ぶ、自国を守る経済とは ― 財源幻想を超えて考える日本のレジリエンス : Pythonで学ぶ マクロ経済学入門 (99)
AI News & Artificial Intelligence | TechCrunch
Inside Ode with Anthropic, the startup betting AI services are the future of enterprise
Inside Ode with Anthropic, the startup betting AI services are the future of enterprise
ITmedia NEWS 最新記事一覧
セガのゲーム、NVIDIA「RTX Spark」で遊べるように 秋葉原で協業30周年を祝う
セガのゲーム、NVIDIA「RTX Spark」で遊べるように 秋葉原で協業30周年を祝う
Zennの「大規模言語モデル」のフィード
【GAS × Gemini API】スプレッドシートからAIを呼び出す最短ルート(第1回:環境構築・テスト接続編)
【GAS × Gemini API】スプレッドシートからAIを呼び出す最短ルート(第1回:環境構築・テスト接続編)
機械学習タグが付けられた新着記事 - Qiita
キャラAI『VIUK Story』を10万件で育てようとしたら、雑談のたびに事件が起きた
キャラAI『VIUK Story』を10万件で育てようとしたら、雑談のたびに事件が起きた
AI News & Artificial Intelligence | TechCrunch
Anthropic, Blackstone bet the next trillion-dollar AI business is implementation, not just models
Anthropic, Blackstone bet the next trillion-dollar AI business is implementation, not just models
AI News & Artificial Intelligence | TechCrunch
Reelful’s AI turns your camera roll into short-form videos for social media
Reelful’s AI turns your camera roll into short-form videos for social media
AI News & Artificial Intelligence | TechCrunch
Rime picks up $24M Series A to help enterprises field customer calls
Rime picks up $24M Series A to help enterprises field customer calls
Zennの「大規模言語モデル」のフィード
「本人らしいAI」の精度をどう測るか。perselfの検証ループと、数値が基準を超えても消えない違和感
「本人らしいAI」の精度をどう測るか。perselfの検証ループと、数値が基準を超えても消えない違和感
OpenAI News
The US is advancing AI safety through state and federal action
The US is advancing AI safety through state and federal action
AI News & Artificial Intelligence | TechCrunch
Indian AI coding startup Emergent becomes a unicorn with $130M Series C
Indian AI coding startup Emergent becomes a unicorn with $130M Series C
AI News & Artificial Intelligence | TechCrunch
Vint Cerf is working on a plan to unleash AI agents on the open internet
Vint Cerf is working on a plan to unleash AI agents on the open internet
WIRED
An Inventor of Apple’s FaceID Wants to Analyze Your Brain’s Health With AI
An Inventor of Apple’s FaceID Wants to Analyze Your Brain’s Health With AI
Zennの「大規模言語モデル」のフィード
Claude Code×Codex併用環境で踏んだ5つの境界 — CLAUDE.md設計・スキル・MCPの仕組みから整理する
Claude Code×Codex併用環境で踏んだ5つの境界 — CLAUDE.md設計・スキル・MCPの仕組みから整理する
ITmedia NEWS 最新記事一覧
ケンタッキー、くら寿司、やよい軒も……ニチレイ不正アクセス、外食・小売に影響拡大 解消のめどは
ケンタッキー、くら寿司、やよい軒も……ニチレイ不正アクセス、外食・小売に影響拡大 解消のめどは
WIRED
The Best iPad to Buy (and Some to Avoid) in 2026: Air, Pro, Mini
The Best iPad to Buy (and Some to Avoid) in 2026: Air, Pro, Mini
Zennの「大規模言語モデル」のフィード
LLM の可観測性ツールを決めきれないので、OpenTelemetry で決めない構成にした
LLM の可観測性ツールを決めきれないので、OpenTelemetry で決めない構成にした
WIRED
MSI Claw 8 EX AI+ Review: Great Power, Shocking Price
MSI Claw 8 EX AI+ Review: Great Power, Shocking Price
NVIDIA Blog
NVIDIA and Japan Bring Full-Stack AI and Robotics to Every Industry
NVIDIA and Japan Bring Full-Stack AI and Robotics to Every Industry
Zennの「機械学習」のフィード
ランダムに5頭買っても77%当たる — 「よく当たる」に騙されないためのベースライン思考
ランダムに5頭買っても77%当たる — 「よく当たる」に騙されないためのベースライン思考
ITmedia NEWS 最新記事一覧
「bokete」アプリ、サービス終了へ システム老朽化やサーバ費高騰で 18年で1億超のボケ
「bokete」アプリ、サービス終了へ システム老朽化やサーバ費高騰で 18年で1億超のボケ
WIRED
4 Best Personal Safety Alarms: Garmin, Sabre, & More (2026)
4 Best Personal Safety Alarms: Garmin, Sabre, & More (2026)
ITmedia NEWS 最新記事一覧
ニチレイ、システム障害はサイバー攻撃によるものと公表 17日から出荷業務など順次再開へ
ニチレイ、システム障害はサイバー攻撃によるものと公表 17日から出荷業務など順次再開へ
Zennの「大規模言語モデル」のフィード
同じコードを11回検査させても、そのCVEは0回だった ― LLMコード検査の再現性を実測する
同じコードを11回検査させても、そのCVEは0回だった ― LLMコード検査の再現性を実測する
Zennの「大規模言語モデル」のフィード
日本語は英語より何倍トークンを食うのか—js-tiktokenでトークンカウンターを作った
日本語は英語より何倍トークンを食うのか—js-tiktokenでトークンカウンターを作った