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
AREX: Towards a Recursively Self-Improving Agent for Deep Research
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Hugging Face Papers
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
Hugging Face Papers
ReferTrack: Referring Then Tracking for Embodied Visual Tracking
ReferTrack: Referring Then Tracking for Embodied Visual Tracking
Hugging Face Papers
Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
Hugging Face Papers
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Hugging Face Papers
Color Pass-Through via Camera-Display Coupling
Color Pass-Through via Camera-Display Coupling
Hugging Face Papers
Sample-Efficient Learning from Agent Experience
Sample-Efficient Learning from Agent Experience
Hugging Face Papers
Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation
Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation
Hugging Face Papers
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
Hugging Face Papers
TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation
TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation
Hugging Face Papers
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
Hugging Face Papers
GraphVid: Interactive Graph-Controllable Video Generation
GraphVid: Interactive Graph-Controllable Video Generation
#AIタグ
AIを「使いこなす」と「使われる」の違い：AI時代に守るべき「主体性」(問いのデザイン#47)
AIを「使いこなす」と「使われる」の違い：AI時代に守るべき「主体性」(問いのデザイン#47)
#AIタグ
Googleマップから営業リストは作れた。でも受注はゼロだった——「見つかる客」と「届く客」は別だった
Googleマップから営業リストは作れた。でも受注はゼロだった——「見つかる客」と「届く客」は別だった
#AIタグ
#91 【AIの完成を見た目で決めない】「どこまでできたら終わり？」を合格条件へ変える受け取りレシピ🍀
#91 【AIの完成を見た目で決めない】「どこまでできたら終わり？」を合格条件へ変える受け取りレシピ🍀
#AIタグ
【常識反転仮説 Season2 AI編 No.6】AIは、「信じる」という能力を理解できなかった⁉――人類は、証拠よりも希望を未来へ残す生き物だった！
【常識反転仮説 Season2 AI編 No.6】AIは、「信じる」という能力を理解できなかった⁉――人類は、証拠よりも希望を未来へ残す生き物だった！
#AIタグ
パランティアとＸそのものが国政を揺るがしている脅威になってるとする事実を、日本の政治家はしっかりと理解し把握してるのだろうか
パランティアとＸそのものが国政を揺るがしている脅威になってるとする事実を、日本の政治家はしっかりと理解し把握してるのだろうか
LLMタグが付けられた新着記事 - Qiita
同じAnthropic製で乗っ取り率32%対79%: AgentRedBenchが暴いた「エージェント防御の急所」
同じAnthropic製で乗っ取り率32%対79%: AgentRedBenchが暴いた「エージェント防御の急所」
#AIタグ
AI時代に問い直す「人間の価値」-高校生が全国優勝・アメリカへの挑戦・豊洲市場から学んだこと-
AI時代に問い直す「人間の価値」-高校生が全国優勝・アメリカへの挑戦・豊洲市場から学んだこと-
#AIタグ
Notebooklmを活用！「貯蓄から投資」の先へ！2026年・日本経済をアップグレードする新金融戦略とは？
Notebooklmを活用！「貯蓄から投資」の先へ！2026年・日本経済をアップグレードする新金融戦略とは？
ITmedia NEWS 最新記事一覧
総務省、Google・Xなど5社に勧告 誹謗中傷対策の報告義務を怠る 情プラ法違反で
総務省、Google・Xなど5社に勧告 誹謗中傷対策の報告義務を怠る 情プラ法違反で
LLMタグが付けられた新着記事 - Qiita
Codexで「Request blocked」が出て会話を続けられなくなった話
Codexで「Request blocked」が出て会話を続けられなくなった話
MarkTechPost
How to Build an End-to-End OCR Pipeline with Baidu’s Unlimited-OCR for High-Resolution Images and Multi-Page PDF Parsing
How to Build an End-to-End OCR Pipeline with Baidu’s Unlimited-OCR for High-Resolution Images and Multi-Page PDF Parsing
ITmedia NEWS 最新記事一覧
ChatGPTとClaude、そろって音声機能強化 Codexでエージェントに“声だけで指示”も可能に
ChatGPTとClaude、そろって音声機能強化 Codexでエージェントに“声だけで指示”も可能に
ITmedia NEWS 最新記事一覧
性的表現に誤タップ誘導――ネットの“不快な広告”への苦情が1年で2倍に 件数も過去最多
性的表現に誤タップ誘導――ネットの“不快な広告”への苦情が1年で2倍に 件数も過去最多
NVIDIA Blog
At AI Summit, South Korea Outlines Its AI Future With NVIDIA and Partners
At AI Summit, South Korea Outlines Its AI Future With NVIDIA and Partners
Latent.Space
[AINews] Black Forest Labs FLUX 3 - Multimodal Flow Models that beat Seedance 2.0, Gemini Omni and Grok Imagine, and FLUX-mimic video-action robotics model
[AINews] Black Forest Labs FLUX 3 - Multimodal Flow Models that beat Seedance 2.0, Gemini Omni and Grok Imagine, and FLUX-mimic video-action robotics model
#LLMタグ
AIエージェントは「1回拒否できた」だけでは安全とは言えない——適応型15ラウンド評価で集計攻撃成功率が最大14.0％
AIエージェントは「1回拒否できた」だけでは安全とは言えない——適応型15ラウンド評価で集計攻撃成功率が最大14.0％
MIT News - Artificial intelligence
Working to automate nuclear plant operations
Working to automate nuclear plant operations
cs.LG updates on arXiv.org
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators
cs.LG updates on arXiv.org
PhantomFill: When the Form Demands an Answer, Language Models Invent One
PhantomFill: When the Form Demands an Answer, Language Models Invent One
cs.LG updates on arXiv.org
The Active Ingredient in Muon's Grokking
The Active Ingredient in Muon's Grokking
cs.LG updates on arXiv.org
Scaling Closed-Loop Feature Channel Configuration with LLMs
Scaling Closed-Loop Feature Channel Configuration with LLMs
cs.LG updates on arXiv.org
Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs
Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs
cs.LG updates on arXiv.org
Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts
Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts
cs.LG updates on arXiv.org
Generative Bayesian Filtering for State Estimation
Generative Bayesian Filtering for State Estimation
cs.LG updates on arXiv.org
Do Active SAE Feature Planes Carry More Holonomy? A Preregistered Reversal in Gemma
Do Active SAE Feature Planes Carry More Holonomy? A Preregistered Reversal in Gemma
cs.LG updates on arXiv.org
Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement
Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement
cs.LG updates on arXiv.org
CLOE: Christoffel Loss Autoencoder for Anomaly Detection
CLOE: Christoffel Loss Autoencoder for Anomaly Detection
cs.LG updates on arXiv.org
Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development
Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development
cs.LG updates on arXiv.org
Grounding Investor Views: Neural Predicates in the Black-Litterman Model
Grounding Investor Views: Neural Predicates in the Black-Litterman Model
cs.LG updates on arXiv.org
A Graph Neural Network approach to zero-shot Digital Twins
A Graph Neural Network approach to zero-shot Digital Twins
cs.LG updates on arXiv.org
ReliableTableQA:How Much Supervision Does Reliability Annotation Need?
ReliableTableQA:How Much Supervision Does Reliability Annotation Need?
cs.LG updates on arXiv.org
Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches
Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches
cs.LG updates on arXiv.org
Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling
Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling
cs.LG updates on arXiv.org
From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime
From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime
cs.LG updates on arXiv.org
HypNO: A Graph-Based Neural Operator with Physics-Informed Message Passing for Hyperbolic Conservation Laws
HypNO: A Graph-Based Neural Operator with Physics-Informed Message Passing for Hyperbolic Conservation Laws
cs.LG updates on arXiv.org
Improving Access to Essential Medicines via Decision-Aware Machine Learning
Improving Access to Essential Medicines via Decision-Aware Machine Learning
cs.LG updates on arXiv.org
When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion
When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion
cs.LG updates on arXiv.org
Conflict Resolution under Degraded Surveillance in Air Corridors Using Multi-Agent Reinforcement Learning
Conflict Resolution under Degraded Surveillance in Air Corridors Using Multi-Agent Reinforcement Learning
cs.LG updates on arXiv.org
SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales
SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales
cs.LG updates on arXiv.org
SevDiff: Severity-Conditioned Diffusion for Long-Tail Conflict Trajectory Generation
SevDiff: Severity-Conditioned Diffusion for Long-Tail Conflict Trajectory Generation
cs.LG updates on arXiv.org
Beyond SBDD: Geometric Deep Learning in Polypharmacology and Multi-target Drug Design
Beyond SBDD: Geometric Deep Learning in Polypharmacology and Multi-target Drug Design
cs.LG updates on arXiv.org
SenCos-GEM: SENet-Calibrated and Law-of-Cosines-Constrained Geometry-Enhanced Molecular Representation for Property Prediction
SenCos-GEM: SENet-Calibrated and Law-of-Cosines-Constrained Geometry-Enhanced Molecular Representation for Property Prediction
cs.LG updates on arXiv.org
Thermodynamic Weight Decay: Exploring Grokking Acceleration via Attention Specific Heat
Thermodynamic Weight Decay: Exploring Grokking Acceleration via Attention Specific Heat
cs.LG updates on arXiv.org
Double-Scoring: Reliable Extraction of Strong Lottery Tickets
Double-Scoring: Reliable Extraction of Strong Lottery Tickets
cs.LG updates on arXiv.org
Monkey King Bang: A Unified Scientific Multimodal Foundation Model
Monkey King Bang: A Unified Scientific Multimodal Foundation Model
cs.LG updates on arXiv.org
StabilityBench: Benchmarking Instability in LLMs
StabilityBench: Benchmarking Instability in LLMs
cs.LG updates on arXiv.org
Joint Utilization of Geospatial and census proxies for Autoencoder-Assisted Downscaling (JUGAAD) of socioeconomic indicators in India
Joint Utilization of Geospatial and census proxies for Autoencoder-Assisted Downscaling (JUGAAD) of socioeconomic indicators in India
cs.LG updates on arXiv.org
Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation
Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation
cs.LG updates on arXiv.org
CT-Merging: Consensus Directions and Task-Level Scaling for LoRA Adapter Merging
CT-Merging: Consensus Directions and Task-Level Scaling for LoRA Adapter Merging
cs.LG updates on arXiv.org
AI-Driven Surrogate Models for Predicting Electrode-Scale Discharge Behavior in Lithium-Ion Batteries
AI-Driven Surrogate Models for Predicting Electrode-Scale Discharge Behavior in Lithium-Ion Batteries
cs.LG updates on arXiv.org
Fisher Widths: Local Learning Geometry and Anisotropic Recovery
Fisher Widths: Local Learning Geometry and Anisotropic Recovery
cs.LG updates on arXiv.org
Bayesian uncertainty estimation improves clinical decision making in medical AI agents
Bayesian uncertainty estimation improves clinical decision making in medical AI agents
cs.LG updates on arXiv.org
Exact ReLU realization of affine one-dimensional refinement iterates via residual memory and offset frames
Exact ReLU realization of affine one-dimensional refinement iterates via residual memory and offset frames
cs.LG updates on arXiv.org
Detecting Neural Network Failures through Spectral Analysis of Internal Activations
Detecting Neural Network Failures through Spectral Analysis of Internal Activations
cs.LG updates on arXiv.org
STeMP: Spatio-Temporal Modelling Protocol
STeMP: Spatio-Temporal Modelling Protocol
cs.LG updates on arXiv.org
When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers
When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers
cs.LG updates on arXiv.org
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects
cs.LG updates on arXiv.org
One Round Is All You Need: Analytic Federated Learning for Task-Heterogeneous Multi-Label Medical Image Classification
One Round Is All You Need: Analytic Federated Learning for Task-Heterogeneous Multi-Label Medical Image Classification
cs.LG updates on arXiv.org
Scaling Interpretable Transformers with Parity Bottleneck Layers
Scaling Interpretable Transformers with Parity Bottleneck Layers
cs.LG updates on arXiv.org
SalesLoop: Reinforcement Learning from Performance Feedback for Sales Lead Ranking
SalesLoop: Reinforcement Learning from Performance Feedback for Sales Lead Ranking
cs.LG updates on arXiv.org
Adaptive Multi-Horizon Reinforcement Learning
Adaptive Multi-Horizon Reinforcement Learning
cs.LG updates on arXiv.org
End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers
End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers
cs.LG updates on arXiv.org
Explanation-Based Runtime Verification for Trustworthy ML-driven Optical Networks
Explanation-Based Runtime Verification for Trustworthy ML-driven Optical Networks
cs.LG updates on arXiv.org
Attribution Markets: A Fisher-Market Formulation for Fractional Credit Assignment Between Planned Tasks and Performed Actions
Attribution Markets: A Fisher-Market Formulation for Fractional Credit Assignment Between Planned Tasks and Performed Actions
cs.LG updates on arXiv.org
CEDAR: Causal Edge Discovery for Autoregressive Processes
CEDAR: Causal Edge Discovery for Autoregressive Processes
cs.LG updates on arXiv.org
Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents
Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents
cs.LG updates on arXiv.org
LLMs Get Lost in Evolving User Intent
LLMs Get Lost in Evolving User Intent
cs.LG updates on arXiv.org
Cardinality-Decomposed Loss: Matching Training Objectives to Relation Structure in Heterogeneous Recommendation Graphs
Cardinality-Decomposed Loss: Matching Training Objectives to Relation Structure in Heterogeneous Recommendation Graphs
cs.LG updates on arXiv.org
Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion
Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion
cs.LG updates on arXiv.org
GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries
GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries
cs.LG updates on arXiv.org
Memory-Computation Tradeoffs in Semi Amortized Parametric Optimization
Memory-Computation Tradeoffs in Semi Amortized Parametric Optimization
cs.LG updates on arXiv.org
Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry
Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry
cs.LG updates on arXiv.org
Synthetic minority data is redundant or invalid: a data-dependent validity theory and a de-biased test
Synthetic minority data is redundant or invalid: a data-dependent validity theory and a de-biased test
cs.LG updates on arXiv.org
Memoir: Should a Model Write to Its Memory While It Thinks?
Memoir: Should a Model Write to Its Memory While It Thinks?
cs.LG updates on arXiv.org
External Clustering Validation by the Homogeneity-Parsimony Trade-off
External Clustering Validation by the Homogeneity-Parsimony Trade-off
cs.LG updates on arXiv.org
New Complexity-Theoretic Frontiers of Tractability for Neural Network Training
New Complexity-Theoretic Frontiers of Tractability for Neural Network Training
cs.LG updates on arXiv.org
Robust Asynchronous Q-Learning under Reward and State Corruption via Batching
Robust Asynchronous Q-Learning under Reward and State Corruption via Batching
cs.LG updates on arXiv.org
Beyond Heavy Log Curation: Perplexity-Based APT Detection via Unsupervised, Context-Augmented Language Models
Beyond Heavy Log Curation: Perplexity-Based APT Detection via Unsupervised, Context-Augmented Language Models
cs.LG updates on arXiv.org
Offline RL with Hierarchical Action Chunking
Offline RL with Hierarchical Action Chunking
cs.LG updates on arXiv.org
Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery
Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery
cs.LG updates on arXiv.org
Position Bias is Hidden Behind Ceiling Effects: A Permutation Diagnostic for LLM Benchmarks
Position Bias is Hidden Behind Ceiling Effects: A Permutation Diagnostic for LLM Benchmarks
cs.LG updates on arXiv.org
TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging
TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging
cs.LG updates on arXiv.org
Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries
Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries
cs.LG updates on arXiv.org
HierarchicalDAEW: Domain-Aware Edge-Weighted Graph Convolution with Evidential Uncertainty for Multi-Section Spatial Gene Expression Prediction from H&E Histology
HierarchicalDAEW: Domain-Aware Edge-Weighted Graph Convolution with Evidential Uncertainty for Multi-Section Spatial Gene Expression Prediction from H&E Histology
cs.LG updates on arXiv.org
Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation
Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation
cs.LG updates on arXiv.org
Three-Pronged Spectral Control for Federated Parameter Efficient Fine Tuning
Three-Pronged Spectral Control for Federated Parameter Efficient Fine Tuning
cs.LG updates on arXiv.org
Best-of-Evidence: Best-of-N Selection under Partial Verification
Best-of-Evidence: Best-of-N Selection under Partial Verification
cs.LG updates on arXiv.org
The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning
The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning
cs.LG updates on arXiv.org
ADABORD: a novel AdaBoost approach for ordinal classification
ADABORD: a novel AdaBoost approach for ordinal classification
cs.LG updates on arXiv.org
Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay
Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay
cs.LG updates on arXiv.org
Regularized Optimization on Grassmann Manifold: Theory, Algorithm and Applications
Regularized Optimization on Grassmann Manifold: Theory, Algorithm and Applications
cs.LG updates on arXiv.org
Counterfactual Explainability Framework With CycleGAN And Counterfactual-Classifier Alignnment Score for Retinal Disease Classification
Counterfactual Explainability Framework With CycleGAN And Counterfactual-Classifier Alignnment Score for Retinal Disease Classification
cs.LG updates on arXiv.org
From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python
From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python
cs.LG updates on arXiv.org
Spectral Transformation for Layer-wise Global Rank Discovery in Federated LoRA for Vision Transformers
Spectral Transformation for Layer-wise Global Rank Discovery in Federated LoRA for Vision Transformers
cs.LG updates on arXiv.org
Nipping the Butterfly Effect in the Bud: Self-Output Fine-Tuning for Autoregressive Weather Prediction
Nipping the Butterfly Effect in the Bud: Self-Output Fine-Tuning for Autoregressive Weather Prediction
cs.LG updates on arXiv.org
CASC: Causal Adversarial Subspace Clustering for Multivariate Spatiotemporal Data
CASC: Causal Adversarial Subspace Clustering for Multivariate Spatiotemporal Data
cs.LG updates on arXiv.org
Training Large Language Models for Self-Explanation Faithfulness
Training Large Language Models for Self-Explanation Faithfulness
cs.LG updates on arXiv.org
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
cs.LG updates on arXiv.org
Smooth Neural Point Processes via B-Splines
Smooth Neural Point Processes via B-Splines
cs.LG updates on arXiv.org
TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning
TOUR: A Trajectory-Level Unlearning Benchmark for Offline Reinforcement Learning
cs.LG updates on arXiv.org
GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Diabetes
GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Diabetes
cs.LG updates on arXiv.org
Demographically-Informed Heat-Mortality Risk Curves via Risk Graph Neural Networks
Demographically-Informed Heat-Mortality Risk Curves via Risk Graph Neural Networks
cs.LG updates on arXiv.org
Agree on the Model, Verify the Inference: GKR Protocols for HND-Based Transformer Inference
Agree on the Model, Verify the Inference: GKR Protocols for HND-Based Transformer Inference
cs.LG updates on arXiv.org
Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines
Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines
cs.LG updates on arXiv.org
Filter Learning for Subgraphs: Algebras and Performance Risk Bounds
Filter Learning for Subgraphs: Algebras and Performance Risk Bounds
cs.LG updates on arXiv.org
The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and What Actually Works
The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and What Actually Works
cs.LG updates on arXiv.org
Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning
Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning
cs.LG updates on arXiv.org
M$^3$-Gen: Interpretable Multimodal Generation of Gene Expression Profiles Using Clinical and Imaging Data
M$^3$-Gen: Interpretable Multimodal Generation of Gene Expression Profiles Using Clinical and Imaging Data
cs.LG updates on arXiv.org
How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning
How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning
cs.LG updates on arXiv.org
Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning
Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning
cs.LG updates on arXiv.org
Emergent Misalignment Recruits a Pre-existing Persona Subspace
Emergent Misalignment Recruits a Pre-existing Persona Subspace
cs.LG updates on arXiv.org
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
cs.LG updates on arXiv.org
Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy
Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy
cs.LG updates on arXiv.org
A Diffusion-Model Subpopulation Digital Twin for Mobile Health Deployment: A Case Study on the HeartSteps Intervention
A Diffusion-Model Subpopulation Digital Twin for Mobile Health Deployment: A Case Study on the HeartSteps Intervention
cs.LG updates on arXiv.org
Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
cs.LG updates on arXiv.org
Context-weighted Discrete Flow Matching
Context-weighted Discrete Flow Matching
cs.LG updates on arXiv.org
KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
cs.LG updates on arXiv.org
Test-Time Scaling via Error Localization
Test-Time Scaling via Error Localization
cs.LG updates on arXiv.org
Error Certificates for KV-Cache Eviction via Randomized Design
Error Certificates for KV-Cache Eviction via Randomized Design
cs.LG updates on arXiv.org
Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design
Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design
cs.LG updates on arXiv.org
Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
cs.LG updates on arXiv.org
Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context
Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context
cs.LG updates on arXiv.org
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
cs.LG updates on arXiv.org
Graph Learning on Ensembles of Cyclic Peptides: An Investigation of Molecular Ensemble Modeling
Graph Learning on Ensembles of Cyclic Peptides: An Investigation of Molecular Ensemble Modeling
cs.LG updates on arXiv.org
Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
cs.LG updates on arXiv.org
Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos
Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos
cs.LG updates on arXiv.org
From Attention to Frequency: Integration of Vision Transformer and FFT-ReLU for Enhanced Image Deblurring
From Attention to Frequency: Integration of Vision Transformer and FFT-ReLU for Enhanced Image Deblurring
cs.LG updates on arXiv.org
Preference Tuning as Spectral Update Reorganization
Preference Tuning as Spectral Update Reorganization
cs.LG updates on arXiv.org
Belief Propagation in LLM World Models: Measuring Strategic Information Bias with Prediction Markets
Belief Propagation in LLM World Models: Measuring Strategic Information Bias with Prediction Markets
cs.LG updates on arXiv.org
Naver-News-KO: A Korean News Summarization Dataset for Open-Source Fine-Tuning of Summarization Models
Naver-News-KO: A Korean News Summarization Dataset for Open-Source Fine-Tuning of Summarization Models
cs.LG updates on arXiv.org
GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus
GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus
cs.LG updates on arXiv.org
thaulab@EEUCA 2026: Who Said What to Whom? A Targeting-Aware Neural-Symbolic Pipeline for Gaming Toxicity Detection
thaulab@EEUCA 2026: Who Said What to Whom? A Targeting-Aware Neural-Symbolic Pipeline for Gaming Toxicity Detection
cs.LG updates on arXiv.org
Domyn-Small: A European 10B Reasoning Language Model
Domyn-Small: A European 10B Reasoning Language Model
cs.LG updates on arXiv.org
A Knowledge-Injection Framework for Zero-Shot Adaptation of LLMs to Delirium Prediction
A Knowledge-Injection Framework for Zero-Shot Adaptation of LLMs to Delirium Prediction
cs.LG updates on arXiv.org
DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding
DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding
cs.LG updates on arXiv.org
SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification
SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification
cs.LG updates on arXiv.org
Expectation Alignment of Language Models for Real-World User Expectations
Expectation Alignment of Language Models for Real-World User Expectations
cs.LG updates on arXiv.org
DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making
DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making
cs.LG updates on arXiv.org
Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models
Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models
cs.LG updates on arXiv.org
Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation
Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation
cs.LG updates on arXiv.org
LeanFlow: A Case Study in Workflow-Driven Lean Autoformalization
LeanFlow: A Case Study in Workflow-Driven Lean Autoformalization
cs.LG updates on arXiv.org
HERMES: Heterogeneous Edge-Relational Multi-Head Embedded SSM Attention for Traffic Conflict Prediction at Signalized Intersections
HERMES: Heterogeneous Edge-Relational Multi-Head Embedded SSM Attention for Traffic Conflict Prediction at Signalized Intersections
cs.LG updates on arXiv.org
MiniCache: Reusable Program Caching with Small Model Interfaces for Efficient LLM Inference
MiniCache: Reusable Program Caching with Small Model Interfaces for Efficient LLM Inference
cs.LG updates on arXiv.org
ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
cs.LG updates on arXiv.org
AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
cs.LG updates on arXiv.org
AI-Driven Multi-Hop Relay Selection for Smart Urban NR-V2X Networks via Learning-to-Optimize Graph Neural Networks
AI-Driven Multi-Hop Relay Selection for Smart Urban NR-V2X Networks via Learning-to-Optimize Graph Neural Networks
cs.LG updates on arXiv.org
Machine-Learned Compact Subspace Generation for Quantum Selected Configuration Interaction within Density Matrix Embedding Framework
Machine-Learned Compact Subspace Generation for Quantum Selected Configuration Interaction within Density Matrix Embedding Framework
cs.LG updates on arXiv.org
SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting
SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting
cs.LG updates on arXiv.org
Algorithmic Approaches to Sequential Decision-Making and Social Epistemology
Algorithmic Approaches to Sequential Decision-Making and Social Epistemology
cs.LG updates on arXiv.org
Masked Topology Modeling for Self-Supervised Learning on Parametric CAD
Masked Topology Modeling for Self-Supervised Learning on Parametric CAD
cs.LG updates on arXiv.org
Frontier Financial Judgement: Can agents tell what might move a stock?
Frontier Financial Judgement: Can agents tell what might move a stock?
cs.LG updates on arXiv.org
PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics
PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics
cs.LG updates on arXiv.org
Writhe-Based Polymer Link Classification Using Machine Learning
Writhe-Based Polymer Link Classification Using Machine Learning
cs.LG updates on arXiv.org
Cross-Domain Generalization in Optical Networks via Joint Contrastive and Classification Learning
Cross-Domain Generalization in Optical Networks via Joint Contrastive and Classification Learning
cs.LG updates on arXiv.org
Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing
Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing
cs.LG updates on arXiv.org
Self-Supervised Bio-Inspired Robotic Trajectory Planning with Obstacle Avoidance
Self-Supervised Bio-Inspired Robotic Trajectory Planning with Obstacle Avoidance
cs.LG updates on arXiv.org
Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles
Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles
cs.LG updates on arXiv.org
Emergent Compositional Skills in Mixture-of-Experts VLAs
Emergent Compositional Skills in Mixture-of-Experts VLAs
cs.LG updates on arXiv.org
The Geometry of Personality: Activation Steering with Jungian Cognitive Functions
The Geometry of Personality: Activation Steering with Jungian Cognitive Functions
cs.LG updates on arXiv.org
Probabilistic Residual Learning for Online Recommendations
Probabilistic Residual Learning for Online Recommendations
cs.LG updates on arXiv.org
Machine Learning for Charge State Characterization of Isolated Double Quantum Dots
Machine Learning for Charge State Characterization of Isolated Double Quantum Dots
cs.LG updates on arXiv.org
RadioTrace: Transmitter-Aware Diffusion for Radio Map Estimation without Deployment-Time Fine-Tuning
RadioTrace: Transmitter-Aware Diffusion for Radio Map Estimation without Deployment-Time Fine-Tuning
cs.LG updates on arXiv.org
An Analytically Trained Variational Surrogate for Quantum Phase Estimation on NISQ Hardware
An Analytically Trained Variational Surrogate for Quantum Phase Estimation on NISQ Hardware
cs.LG updates on arXiv.org
Automatic knot selection in smooth additive models
Automatic knot selection in smooth additive models
cs.LG updates on arXiv.org
Approximate Quantum State Preparation Through Proximal Policy Optimization
Approximate Quantum State Preparation Through Proximal Policy Optimization
cs.LG updates on arXiv.org
Safety-oriented sidewalk and road segmentation for smartphone-based assistive navigation
Safety-oriented sidewalk and road segmentation for smartphone-based assistive navigation
cs.LG updates on arXiv.org
Explaining Weather Bulletins via ILP
Explaining Weather Bulletins via ILP
cs.LG updates on arXiv.org
Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting
Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting
cs.LG updates on arXiv.org
DART: A Degradation-Aware Recurrent Transformer for Archival Film Restoration
DART: A Degradation-Aware Recurrent Transformer for Archival Film Restoration
cs.LG updates on arXiv.org
Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs
Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs
cs.LG updates on arXiv.org
Cautious optimism for deep parameterized quantum circuits
Cautious optimism for deep parameterized quantum circuits
cs.LG updates on arXiv.org
Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models
Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models
cs.LG updates on arXiv.org
Climate-resilient electric vehicle charging infrastructure for sustainable cities: An interpretable causal-ensemble framework for preventive maintenance and low-carbon mobility
Climate-resilient electric vehicle charging infrastructure for sustainable cities: An interpretable causal-ensemble framework for preventive maintenance and low-carbon mobility
cs.LG updates on arXiv.org
What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations
What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations
cs.LG updates on arXiv.org
Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models
Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models
cs.LG updates on arXiv.org
The Boundaries of Automation: A Theory of Persistent Human Participation
The Boundaries of Automation: A Theory of Persistent Human Participation
cs.LG updates on arXiv.org
Neural solutions of coupled ghost and gluon Dyson--Schwinger equations in Landau gauge
Neural solutions of coupled ghost and gluon Dyson--Schwinger equations in Landau gauge
cs.LG updates on arXiv.org
MIRROR: Learning from the Other View for Multi-Modal Reasoning
MIRROR: Learning from the Other View for Multi-Modal Reasoning
cs.LG updates on arXiv.org
Synthetic data generation framework for quality control automation in gravure printing
Synthetic data generation framework for quality control automation in gravure printing
cs.LG updates on arXiv.org
Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$
Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$
cs.LG updates on arXiv.org
3D-Aware VLMs with Implicit and Explicit Geometries
3D-Aware VLMs with Implicit and Explicit Geometries
cs.LG updates on arXiv.org
Classifier-pruned Bayesian optimization for particle accelerator tuning: Exploring temporally structured manifold of 6D beam phase space
Classifier-pruned Bayesian optimization for particle accelerator tuning: Exploring temporally structured manifold of 6D beam phase space
cs.LG updates on arXiv.org
Semantics at an Angle: When Cosine Similarity Works Until It Doesn't
Semantics at an Angle: When Cosine Similarity Works Until It Doesn't
cs.LG updates on arXiv.org
PreMoE: Proactive Inference for Efficient Mixture-of-Experts
PreMoE: Proactive Inference for Efficient Mixture-of-Experts
cs.LG updates on arXiv.org
Concept Concentration for Faithful Representation Intervention
Concept Concentration for Faithful Representation Intervention
cs.LG updates on arXiv.org
SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing Flows
SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing Flows
cs.LG updates on arXiv.org
Tackling Heterogeneity in Federated Learning via Variance-Reduced Boltzmann Sampling within Homogeneous Social Coalitions
Tackling Heterogeneity in Federated Learning via Variance-Reduced Boltzmann Sampling within Homogeneous Social Coalitions
cs.LG updates on arXiv.org
Overcoming the Communication-Performance Tradeoff in LLM Pretraining
Overcoming the Communication-Performance Tradeoff in LLM Pretraining
cs.LG updates on arXiv.org
MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems
MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems
cs.LG updates on arXiv.org
Simple Policy Gradients for Reasoning with Diffusion Language Models
Simple Policy Gradients for Reasoning with Diffusion Language Models
cs.LG updates on arXiv.org
On the Granularity of Causal Effect Identifiability
On the Granularity of Causal Effect Identifiability
cs.LG updates on arXiv.org
Structure-Preserving Physics-Informed Neural Network for the Korteweg--de Vries (KdV) Equation
Structure-Preserving Physics-Informed Neural Network for the Korteweg--de Vries (KdV) Equation
cs.LG updates on arXiv.org
Black box behavioural modelling: Predicting human activity schedules with a deep conditional generative approach
Black box behavioural modelling: Predicting human activity schedules with a deep conditional generative approach
cs.LG updates on arXiv.org
CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation
CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation
cs.LG updates on arXiv.org
Knowledge-Guided Time-Varying Causal Inference for Arctic Sea Ice Dynamics
Knowledge-Guided Time-Varying Causal Inference for Arctic Sea Ice Dynamics
cs.LG updates on arXiv.org
NeuraLSP: A Neural Spectral Preconditioner for Accelerating PDE Solvers
NeuraLSP: A Neural Spectral Preconditioner for Accelerating PDE Solvers
cs.LG updates on arXiv.org
PILD: Physics-Informed Learning via Diffusion
PILD: Physics-Informed Learning via Diffusion
cs.LG updates on arXiv.org
Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance
Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance
cs.LG updates on arXiv.org
Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents
Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents
cs.LG updates on arXiv.org
Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization
Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization
cs.LG updates on arXiv.org
Wireless TokenCom: RL-Based Tokenizer Agreement for Multi-User Wireless Token Communications
Wireless TokenCom: RL-Based Tokenizer Agreement for Multi-User Wireless Token Communications
cs.LG updates on arXiv.org
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training
cs.LG updates on arXiv.org
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
cs.LG updates on arXiv.org
Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner
Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner
cs.LG updates on arXiv.org
Hankel and Toeplitz Rank-1 Decomposition of Arbitrary Matrices with Applications to Signal Direction-of-Arrival Estimation
Hankel and Toeplitz Rank-1 Decomposition of Arbitrary Matrices with Applications to Signal Direction-of-Arrival Estimation
cs.LG updates on arXiv.org
Direct Bethe Free Energy Minimization for Bayesian Neural Networks
Direct Bethe Free Energy Minimization for Bayesian Neural Networks
cs.LG updates on arXiv.org
MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization
MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization
cs.LG updates on arXiv.org
Understanding and Accelerating the Training of Masked Diffusion Language Models
Understanding and Accelerating the Training of Masked Diffusion Language Models
cs.LG updates on arXiv.org
Constrained latent state modeling: A unifying perspective on representation learning under competing constraints
Constrained latent state modeling: A unifying perspective on representation learning under competing constraints
cs.LG updates on arXiv.org
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
cs.LG updates on arXiv.org
Learning Transfers: Kan Extensions for Neural Invariants
Learning Transfers: Kan Extensions for Neural Invariants
cs.LG updates on arXiv.org
Tight Sample Complexity of Transformers
Tight Sample Complexity of Transformers
cs.LG updates on arXiv.org
SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning
SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning
cs.LG updates on arXiv.org
HAMON: Passive Optical Sequence Mixing for Long-Horizon Forecasting
HAMON: Passive Optical Sequence Mixing for Long-Horizon Forecasting
cs.LG updates on arXiv.org
Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
cs.LG updates on arXiv.org
Evaluation and Prognostic Validation of Deep Regression Models for WSI-Based Gene-Expression Prediction
Evaluation and Prognostic Validation of Deep Regression Models for WSI-Based Gene-Expression Prediction
cs.LG updates on arXiv.org
Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
cs.LG updates on arXiv.org
How Robust Is Homogeneity Bias in LLMs? Evidence Across Models, Decoding Settings, and Identity Signals
How Robust Is Homogeneity Bias in LLMs? Evidence Across Models, Decoding Settings, and Identity Signals
cs.LG updates on arXiv.org
Statistical Inference for Generative Model Comparison
Statistical Inference for Generative Model Comparison
cs.LG updates on arXiv.org
Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
cs.LG updates on arXiv.org
Loss-Complexity Landscape and Model Structure Functions
Loss-Complexity Landscape and Model Structure Functions
cs.LG updates on arXiv.org
DynaMark: A Reinforcement Learning Framework for Dynamic Watermarking in Industrial Machine Tool Controllers
DynaMark: A Reinforcement Learning Framework for Dynamic Watermarking in Industrial Machine Tool Controllers
cs.LG updates on arXiv.org
torchsom: The Reference PyTorch Library for Self-Organizing Maps
torchsom: The Reference PyTorch Library for Self-Organizing Maps
cs.LG updates on arXiv.org
Neural Guided Sampling for Quantum Circuit Optimization
Neural Guided Sampling for Quantum Circuit Optimization
cs.LG updates on arXiv.org
Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
cs.LG updates on arXiv.org
Spectral functions in Minkowski quantum electrodynamics from neural reconstruction
Spectral functions in Minkowski quantum electrodynamics from neural reconstruction
cs.LG updates on arXiv.org
Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks
Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks
cs.LG updates on arXiv.org
Environment-Aware Channel Inference via Cross-Modal Flow: From Multimodal Sensing to Wireless Channels
Environment-Aware Channel Inference via Cross-Modal Flow: From Multimodal Sensing to Wireless Channels
cs.LG updates on arXiv.org
Exploiting the Alternatives: Coordinated Learning via Hierarchical RL for Dynamic VNEAP
Exploiting the Alternatives: Coordinated Learning via Hierarchical RL for Dynamic VNEAP
cs.LG updates on arXiv.org
Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation
Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation
cs.LG updates on arXiv.org
Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
cs.LG updates on arXiv.org
Boltzmann generators for amorphous particle systems
Boltzmann generators for amorphous particle systems
cs.LG updates on arXiv.org
Non-Stationary Functional Bilevel Optimization
Non-Stationary Functional Bilevel Optimization
cs.LG updates on arXiv.org
Error Amplification Limits ANN-to-SNN Conversion in Continuous Control
Error Amplification Limits ANN-to-SNN Conversion in Continuous Control
cs.LG updates on arXiv.org
Multimodal Learning for Arcing Detection in Pantograph-Catenary Systems
Multimodal Learning for Arcing Detection in Pantograph-Catenary Systems
cs.LG updates on arXiv.org
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
cs.LG updates on arXiv.org
AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching
AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching
cs.LG updates on arXiv.org
VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory
VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory
cs.LG updates on arXiv.org
Gumbel Distillation for Parallel Text Generation
Gumbel Distillation for Parallel Text Generation
cs.LG updates on arXiv.org
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
cs.LG updates on arXiv.org
Fairness Constraints in High-Dimensional Generalized Linear Models
Fairness Constraints in High-Dimensional Generalized Linear Models
cs.LG updates on arXiv.org
AI Security Policy Should Assess Systems, Not Only Models
AI Security Policy Should Assess Systems, Not Only Models
cs.LG updates on arXiv.org
Conditional Entropy of Heat Diffusion on Temporal Networks
Conditional Entropy of Heat Diffusion on Temporal Networks
cs.LG updates on arXiv.org
Multimodality Stacking with Blockwise missing values and application to the PIONeeR biomarkers study for prediction of resistance to immunotherapy
Multimodality Stacking with Blockwise missing values and application to the PIONeeR biomarkers study for prediction of resistance to immunotherapy
cs.LG updates on arXiv.org
Theoretical Aspects of Lie Groupoid and Lie Algebroid Equivariant Convolutional Neural Networks
Theoretical Aspects of Lie Groupoid and Lie Algebroid Equivariant Convolutional Neural Networks
cs.LG updates on arXiv.org
OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons
OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons
cs.LG updates on arXiv.org
Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing
Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing
cs.LG updates on arXiv.org
Zero-Shot Neural Priors for Generalizable Cross-Subject and Cross-Task EEG Decoding
Zero-Shot Neural Priors for Generalizable Cross-Subject and Cross-Task EEG Decoding
cs.LG updates on arXiv.org
On Pairwise Quantile Regression - Statistical Guarantees and Applications
On Pairwise Quantile Regression - Statistical Guarantees and Applications
stat.ML updates on arXiv.org
SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting
SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting
stat.ML updates on arXiv.org
Automatic knot selection in smooth additive models
Automatic knot selection in smooth additive models
stat.ML updates on arXiv.org
Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting
Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting
stat.ML updates on arXiv.org
Generative Bayesian Filtering for State Estimation
Generative Bayesian Filtering for State Estimation
stat.ML updates on arXiv.org
ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
stat.ML updates on arXiv.org
CLOE: Christoffel Loss Autoencoder for Anomaly Detection
CLOE: Christoffel Loss Autoencoder for Anomaly Detection
stat.ML updates on arXiv.org
Fisher Widths: Local Learning Geometry and Anisotropic Recovery
Fisher Widths: Local Learning Geometry and Anisotropic Recovery
stat.ML updates on arXiv.org
When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers
When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers
stat.ML updates on arXiv.org
High Minima of Gaussian Processes: Overshoots and Minimizer Locations
High Minima of Gaussian Processes: Overshoots and Minimizer Locations
stat.ML updates on arXiv.org
Twoblock clustering trees with coskewness-based dimension reduction: recovering piecewise multivariate linear regimes
Twoblock clustering trees with coskewness-based dimension reduction: recovering piecewise multivariate linear regimes
stat.ML updates on arXiv.org
Self-Balancing Sequential Sampling: Fast Convergence with Controlled Predictability
Self-Balancing Sequential Sampling: Fast Convergence with Controlled Predictability
stat.ML updates on arXiv.org
Smooth Neural Point Processes via B-Splines
Smooth Neural Point Processes via B-Splines
stat.ML updates on arXiv.org
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
stat.ML updates on arXiv.org
Cautious optimism for deep parameterized quantum circuits
Cautious optimism for deep parameterized quantum circuits
stat.ML updates on arXiv.org
Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
stat.ML updates on arXiv.org
Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design
Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design
stat.ML updates on arXiv.org
Optimal use of a black-box learner in semiparametric estimation
Optimal use of a black-box learner in semiparametric estimation
stat.ML updates on arXiv.org
Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghana
Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghana
stat.ML updates on arXiv.org
Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
stat.ML updates on arXiv.org
Statistical Inference for Generative Model Comparison
Statistical Inference for Generative Model Comparison
stat.ML updates on arXiv.org
torchsom: The Reference PyTorch Library for Self-Organizing Maps
torchsom: The Reference PyTorch Library for Self-Organizing Maps
stat.ML updates on arXiv.org
Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
stat.ML updates on arXiv.org
Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks
Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks
stat.ML updates on arXiv.org
Boltzmann generators for amorphous particle systems
Boltzmann generators for amorphous particle systems
stat.ML updates on arXiv.org
Non-Stationary Functional Bilevel Optimization
Non-Stationary Functional Bilevel Optimization
stat.ML updates on arXiv.org
Fairness Constraints in High-Dimensional Generalized Linear Models
Fairness Constraints in High-Dimensional Generalized Linear Models
stat.ML updates on arXiv.org
On Pairwise Quantile Regression - Statistical Guarantees and Applications
On Pairwise Quantile Regression - Statistical Guarantees and Applications
stat.ML updates on arXiv.org
Concept Concentration for Faithful Representation Intervention
Concept Concentration for Faithful Representation Intervention
stat.ML updates on arXiv.org
Multivariate Planar Curves: A Statistical Framework for Shape Analysis in Images
Multivariate Planar Curves: A Statistical Framework for Shape Analysis in Images
stat.ML updates on arXiv.org
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
stat.ML updates on arXiv.org
Multimodality Stacking with Blockwise missing values and application to the PIONeeR biomarkers study for prediction of resistance to immunotherapy
Multimodality Stacking with Blockwise missing values and application to the PIONeeR biomarkers study for prediction of resistance to immunotherapy
＠IT 全フォーラム 最新記事一覧
海外の「Claude」や「GPT」ではダメなのか 日本企業向けai&、そのメリットは？
海外の「Claude」や「GPT」ではダメなのか 日本企業向けai&、そのメリットは？
LLMタグが付けられた新着記事 - Qiita
OpenAIのAIエージェント事例から考えるDoctor AIを備えたAI Runtime設計
OpenAIのAIエージェント事例から考えるDoctor AIを備えたAI Runtime設計
ITmedia NEWS 最新記事一覧
「2日かかる攻撃が25分に」生成AIで“爆速化”するサイバー攻撃、パロアルトの識者が警鐘
「2日かかる攻撃が25分に」生成AIで“爆速化”するサイバー攻撃、パロアルトの識者が警鐘
機械学習タグが付けられた新着記事 - Qiita
【技術解説】【完全ガイド】PythonによるLSTMを用いた株式時系列予測の実装
【技術解説】【完全ガイド】PythonによるLSTMを用いた株式時系列予測の実装
ITmedia NEWS 最新記事一覧
Meta、AI楽観論のブランドキャンペーン開始──BGMはなぜかボウイの終末ソング
Meta、AI楽観論のブランドキャンペーン開始──BGMはなぜかボウイの終末ソング
ITmedia NEWS 最新記事一覧
「人工甘味料」で脳の老化スピードが加速？ 1.6年分の加齢差に相当 1万人超を調査、2025年に医学誌掲載
「人工甘味料」で脳の老化スピードが加速？ 1.6年分の加齢差に相当 1万人超を調査、2025年に医学誌掲載
AI News & Artificial Intelligence | TechCrunch
How AI guardrails are impeding the work of offensive cybersecurity researchers
How AI guardrails are impeding the work of offensive cybersecurity researchers
#LLMタグ
硅谷101 解説：大規模言語モデルの裏側にいる「内容工程師」──記者・編集者がAIの語り口を設計する新職種
硅谷101 解説：大規模言語モデルの裏側にいる「内容工程師」──記者・編集者がAIの語り口を設計する新職種
#LLMタグ
AIエージェントは、なぜ「現場」に浸透しないのか——OSWorld 2.0が可視化したギャップの正体
AIエージェントは、なぜ「現場」に浸透しないのか——OSWorld 2.0が可視化したギャップの正体
#LLMタグ
【構造批評】-西側LLM実装遅延編-規制に時間を費やす間に、中国製AIが防御基盤へ入り込む矛盾‼️
【構造批評】-西側LLM実装遅延編-規制に時間を費やす間に、中国製AIが防御基盤へ入り込む矛盾‼️
ITmedia NEWS 最新記事一覧
Appleの「マップ」がFordの次世代EVに直接統合へ 新SDKで「CarPlay」なしでもナビが機能
Appleの「マップ」がFordの次世代EVに直接統合へ 新SDKで「CarPlay」なしでもナビが機能
WIRED
An FDA Panel Just Endorsed These Unproven Peptides
An FDA Panel Just Endorsed These Unproven Peptides
#LLMタグ
AI時代に個人開発者は「次のYouTuber」になるのか。成功事例に見る構造的な類似と決定的な違い
AI時代に個人開発者は「次のYouTuber」になるのか。成功事例に見る構造的な類似と決定的な違い
#LLMタグ
【CLAUDE.mdが負債になる前に】Google発「OKF」でAIエージェントの知識庫を作る70行Python — 散らばるMarkdownを検索できる資産に変える
【CLAUDE.mdが負債になる前に】Google発「OKF」でAIエージェントの知識庫を作る70行Python — 散らばるMarkdownを検索できる資産に変える
ITmedia NEWS 最新記事一覧
Google、アカウントログイン方法に「自撮り動画」を追加 ロックアウト時の復旧を容易に
Google、アカウントログイン方法に「自撮り動画」を追加 ロックアウト時の復旧を容易に
＠IT 全フォーラム 最新記事一覧
AI時代に「守る」はもう古い Gartnerが『五輪書』で説いた新たなセキュリティ論
AI時代に「守る」はもう古い Gartnerが『五輪書』で説いた新たなセキュリティ論
＠IT 全フォーラム 最新記事一覧
「その場しのぎAIプロンプトはもう結構」 上質な成果だけを出す定番10例とその理由
「その場しのぎAIプロンプトはもう結構」 上質な成果だけを出す定番10例とその理由
Zennの「大規模言語モデル」のフィード
Claude vs GPT、実測で比較したら月の差額が27円だった——乗り換えずにプロンプトだけ改善した話
Claude vs GPT、実測で比較したら月の差額が27円だった——乗り換えずにプロンプトだけ改善した話
Zennの「大規模言語モデル」のフィード
gpt-ossを4bit量子化したら流暢に壊れた話。量子化方式で忠実度が2倍変わった実測記録
gpt-ossを4bit量子化したら流暢に壊れた話。量子化方式で忠実度が2倍変わった実測記録
The Verge
Alexa Plus is getting an AI update to handle more complicated instructions
Alexa Plus is getting an AI update to handle more complicated instructions
Zennの「大規模言語モデル」のフィード
スライド単位のバッチ役割レビューで指摘が薄くなる理由、同時評価対象数という変数
スライド単位のバッチ役割レビューで指摘が薄くなる理由、同時評価対象数という変数
Zennの「大規模言語モデル」のフィード
LLM-as-a-Judgeはどこまで信用できるか。人手177件と突き合わせたらκ=0.25だった
LLM-as-a-Judgeはどこまで信用できるか。人手177件と突き合わせたらκ=0.25だった
The Verge
The Echo Show 21 is a great smart home hub that’s $80 off
The Echo Show 21 is a great smart home hub that’s $80 off
AI News & Artificial Intelligence | TechCrunch
AMD takes on Nvidia with its Helios AI rack-scale system
AMD takes on Nvidia with its Helios AI rack-scale system
＠IT 全フォーラム 最新記事一覧
Win11のストレージ空き容量が激減？ 新機能「ポイントインタイムリストア」のわなと賢い設定術
Win11のストレージ空き容量が激減？ 新機能「ポイントインタイムリストア」のわなと賢い設定術
The Verge
FCC Chairman Brendan Carr’s war on the First Amendment
FCC Chairman Brendan Carr’s war on the First Amendment
MarkTechPost
Andrew Ng Just Released OpenWorker: An Open-Source, Local-First Desktop AI Coworker That Returns Finished Deliverables Instead of Chat
Andrew Ng Just Released OpenWorker: An Open-Source, Local-First Desktop AI Coworker That Returns Finished Deliverables Instead of Chat
AI News & Artificial Intelligence | TechCrunch
Anthropic updates Claude voice mode with more capable models
Anthropic updates Claude voice mode with more capable models
The Verge
Claude’s voice mode is now available for Opus and Sonnet
Claude’s voice mode is now available for Opus and Sonnet
WIRED
Meta’s New Feel-Good AI Ad Uses a Song About the World Ending
Meta’s New Feel-Good AI Ad Uses a Song About the World Ending
AI News & Artificial Intelligence | TechCrunch
AegisAI, founded by former Google security execs, lands $36M to stop AI-driven spear phishing
AegisAI, founded by former Google security execs, lands $36M to stop AI-driven spear phishing
WIRED
For Taylor Swift, Madison Square Garden’s Controversial Cameras Briefly Went Dark
For Taylor Swift, Madison Square Garden’s Controversial Cameras Briefly Went Dark
Qiita - 人気の記事
Embeddingモデル10種を実測比較してみた —— クロスモーダル / 多言語 / Needle-in-a-Haystack / MRL【2026年3月時点】
Embeddingモデル10種を実測比較してみた —— クロスモーダル / 多言語 / Needle-in-a-Haystack / MRL【2026年3月時点】
The Verge
Corsair’s PC case with a panoramic glass design is $70 off
Corsair’s PC case with a panoramic glass design is $70 off
The Verge
Tesla’s robotaxi promises are clashing with reality
Tesla’s robotaxi promises are clashing with reality
AI News & Artificial Intelligence | TechCrunch
Runway launches AI model router as generative media gets crowded
Runway launches AI model router as generative media gets crowded
AI News & Artificial Intelligence | TechCrunch
OpenAI makes ChatGPT Health available to all US users
OpenAI makes ChatGPT Health available to all US users
The Verge
Geekbench 7 will push your computer or phone even harder for better benchmarking
Geekbench 7 will push your computer or phone even harder for better benchmarking
The Verge
OpenAI is making big claims as it rolls out ChatGPT Health to everyone
OpenAI is making big claims as it rolls out ChatGPT Health to everyone
WIRED
The EU Fines Google $1 Billion for Prioritizing Its Own Services in Search
The EU Fines Google $1 Billion for Prioritizing Its Own Services in Search
The Verge
Amazon puts Luna cloud-streamed games like Fallout 4 inside Prime Video
Amazon puts Luna cloud-streamed games like Fallout 4 inside Prime Video
AI News & Artificial Intelligence | TechCrunch
Meta launched a new AI optimism ad set to a song about human extinction
Meta launched a new AI optimism ad set to a song about human extinction
Zennの「大規模言語モデル」のフィード
Github Copilot Appの /spawnとは？Session同士をまとめて管理したい
Github Copilot Appの /spawnとは？Session同士をまとめて管理したい
AI News & Artificial Intelligence | TechCrunch
Nvidia is sending GPUs to the moon
Nvidia is sending GPUs to the moon
AI News & Artificial Intelligence | TechCrunch
AI chip startup Etched defies skeptics, hits $10.3B valuation from big-name investors
AI chip startup Etched defies skeptics, hits $10.3B valuation from big-name investors
Qiita - 人気の記事
狩野英孝さんのポストは、なぜ1992年へ飛んだのか？整数オーバーフローが起こす時刻バグ
狩野英孝さんのポストは、なぜ1992年へ飛んだのか？整数オーバーフローが起こす時刻バグ