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
AlayaWorld: Long-Horizon and Playable Video World Generation
AlayaWorld: Long-Horizon and Playable Video World Generation
Hugging Face Papers
Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory
Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory
Hugging Face Papers
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
Hugging Face Papers
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
Hugging Face Papers
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Hugging Face Papers
MentalThink: Shaping Thoughts in Mental SVG World
MentalThink: Shaping Thoughts in Mental SVG World
Hugging Face Papers
TREK: Distill to Explore, Reinforce to Refine
TREK: Distill to Explore, Reinforce to Refine
Hugging Face Papers
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Hugging Face Papers
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Hugging Face Papers
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding
Hugging Face Papers
Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models
Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models
Hugging Face Papers
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
Hugging Face Papers
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
Hugging Face Papers
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Hugging Face Papers
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
Hugging Face Papers
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers
Hugging Face Papers
3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
Hugging Face Papers
MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
Hugging Face Papers
PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages
PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages
Hugging Face Papers
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models
Hugging Face Papers
CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation
CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation
Hugging Face Papers
Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment
Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment
Hugging Face Papers
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
#AIタグ
また悩みすぎて辛くなっていたので「低めの目標設定」をした。サブテーマは「AIはカウンセラーになれるのか」
また悩みすぎて辛くなっていたので「低めの目標設定」をした。サブテーマは「AIはカウンセラーになれるのか」
#AIタグ
【Fable5フル活用】eBay輸出で外注が不要になった話。AIに仕事を奪われたのではなく、外注費が消えました。
【Fable5フル活用】eBay輸出で外注が不要になった話。AIに仕事を奪われたのではなく、外注費が消えました。
#AIタグ
AIが答えを出す時代に、人間は何に意味を見出すのか。｜問いを探す人たち vol.8（81雑談会）
AIが答えを出す時代に、人間は何に意味を見出すのか。｜問いを探す人たち vol.8（81雑談会）
#AIタグ
バイト終了のお知らせ。月収60,000ドル（日本円で約900万円）実現!!海外AIを1回設定して、顔出しなしで動画自動化の全手順スマホ完結
バイト終了のお知らせ。月収60,000ドル（日本円で約900万円）実現!!海外AIを1回設定して、顔出しなしで動画自動化の全手順スマホ完結
#AIタグ
AIランサムウェアが「自動」で攻撃を完遂する時代—初のエージェント型JADEPUFFERを冷静に読む
AIランサムウェアが「自動」で攻撃を完遂する時代—初のエージェント型JADEPUFFERを冷静に読む
AI News & Artificial Intelligence | TechCrunch
AI chip maker SambaNova raises $1B at $11B valuation, 5 months after last mega round
AI chip maker SambaNova raises $1B at $11B valuation, 5 months after last mega round
MarkTechPost
NVIDIA’s Cosmos-Framework Tutorial: Designing a Colab-Friendly Miniature of Cosmos 3 World Models with Omnimodal Mixture-of-Transformers
NVIDIA’s Cosmos-Framework Tutorial: Designing a Colab-Friendly Miniature of Cosmos 3 World Models with Omnimodal Mixture-of-Transformers
#LLMタグ
「奥様のスマホからの衝撃」――60代・ビジネスパーソンのS.Kamoharaさんが、AI活用の本質を掴むまで
「奥様のスマホからの衝撃」――60代・ビジネスパーソンのS.Kamoharaさんが、AI活用の本質を掴むまで
LLMタグが付けられた新着記事 - Qiita
JSON mode が通るのに schema validation で落ちたので切り分けた
JSON mode が通るのに schema validation で落ちたので切り分けた
LLMタグが付けられた新着記事 - Qiita
ASR → LLM → TTS を「リアルタイム」にするには？ RTF と応答遅延の勘所
ASR → LLM → TTS を「リアルタイム」にするには？ RTF と応答遅延の勘所
ITmedia NEWS 最新記事一覧
三重県、庁内のUSBメモリ調査でマルウェア47個検知 陸自の報道受け1万個超を一斉調査
三重県、庁内のUSBメモリ調査でマルウェア47個検知 陸自の報道受け1万個超を一斉調査
#LLMタグ
Gemma 4 Technical Reportを読む: なぜ実行しやすさまで設計されているのか
Gemma 4 Technical Reportを読む: なぜ実行しやすさまで設計されているのか
WIRED
We-Vibe Discount Codes and Deals: Up to 60% Off
We-Vibe Discount Codes and Deals: Up to 60% Off
WIRED
Vimeo Promo Codes and Discounts: Up to 40% Off This July 2026
Vimeo Promo Codes and Discounts: Up to 40% Off This July 2026
WIRED
Lowe’s Promo Codes and Deals: Up to $300 Off Appliances
Lowe’s Promo Codes and Deals: Up to $300 Off Appliances
WIRED
Valvoline Coupons and Promo Codes for July 2026
Valvoline Coupons and Promo Codes for July 2026
WIRED
LegalZoom Promo Code: Exclusive 10% Off LLC Formations
LegalZoom Promo Code: Exclusive 10% Off LLC Formations
LLMタグが付けられた新着記事 - Qiita
エージェント用途の Claude Fable 5：ツールコール拒否と GLM 5.2 とのコスト比較
エージェント用途の Claude Fable 5：ツールコール拒否と GLM 5.2 とのコスト比較
ITmedia NEWS 最新記事一覧
ゲーム会社「ガンホー」元システム本部長を逮捕、架空発注で4000万円背任疑い 警視庁
ゲーム会社「ガンホー」元システム本部長を逮捕、架空発注で4000万円背任疑い 警視庁
cs.LG updates on arXiv.org
Statistically Meaningful Geometry and Gauge Symmetry Breaking: A Geometric Foundation for Scientific Discovery and Intelligence Emergence
Statistically Meaningful Geometry and Gauge Symmetry Breaking: A Geometric Foundation for Scientific Discovery and Intelligence Emergence
cs.LG updates on arXiv.org
Design-CP: Context Parallelism for Design of Protein Nanoparticles
Design-CP: Context Parallelism for Design of Protein Nanoparticles
cs.LG updates on arXiv.org
Geometry-Aware Infrastructure-Anchored Denoiser for UWB Sensing and Work-Zone Reconstruction
Geometry-Aware Infrastructure-Anchored Denoiser for UWB Sensing and Work-Zone Reconstruction
cs.LG updates on arXiv.org
The Granularity Paradox: How Temporal Disaggregation Inflates In-Sample Fit and Compounds Out-of-Sample Error
The Granularity Paradox: How Temporal Disaggregation Inflates In-Sample Fit and Compounds Out-of-Sample Error
cs.LG updates on arXiv.org
Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates
Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates
cs.LG updates on arXiv.org
Empirical Minimal-Realisation Compression of Deep Neural Networks via Controllability-Observability Tests
Empirical Minimal-Realisation Compression of Deep Neural Networks via Controllability-Observability Tests
cs.LG updates on arXiv.org
Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning
Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning
cs.LG updates on arXiv.org
AdaStop: Cost-Aware Early Stopping for DNN Test Selection
AdaStop: Cost-Aware Early Stopping for DNN Test Selection
cs.LG updates on arXiv.org
Learnable Weighting of Intra-Attribute Distances for Categorical Data Clustering with Nominal and Ordinal Attributes
Learnable Weighting of Intra-Attribute Distances for Categorical Data Clustering with Nominal and Ordinal Attributes
cs.LG updates on arXiv.org
Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy
Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy
cs.LG updates on arXiv.org
Parameter-Free Encoders Remain Viable for RDB Foundation Models
Parameter-Free Encoders Remain Viable for RDB Foundation Models
cs.LG updates on arXiv.org
InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programs
InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programs
cs.LG updates on arXiv.org
PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates
PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates
cs.LG updates on arXiv.org
$\mathbf{\lambda}$-VAE: Variance Equalization for Posterior Collapse
$\mathbf{\lambda}$-VAE: Variance Equalization for Posterior Collapse
cs.LG updates on arXiv.org
Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation
Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation
cs.LG updates on arXiv.org
Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids
Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids
cs.LG updates on arXiv.org
EquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation
EquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation
cs.LG updates on arXiv.org
SafeImpute: Reliable Clinical Data Imputation via Conformal Selection
SafeImpute: Reliable Clinical Data Imputation via Conformal Selection
cs.LG updates on arXiv.org
A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models
A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models
cs.LG updates on arXiv.org
Safe Bayesian Optimization with Counterfactual Policies
Safe Bayesian Optimization with Counterfactual Policies
cs.LG updates on arXiv.org
Intuitionistic Fuzzy Graph Embedded Random Vector Functional Link with Multiview Learning
Intuitionistic Fuzzy Graph Embedded Random Vector Functional Link with Multiview Learning
cs.LG updates on arXiv.org
Domain-Adaptive Climate Downscaling Under Temporal Distribution Shift
Domain-Adaptive Climate Downscaling Under Temporal Distribution Shift
cs.LG updates on arXiv.org
Orthogonal Dendritic Intrinsic Networks: An Architecture for Significance-Ordered, Orthogonal Latent Spaces
Orthogonal Dendritic Intrinsic Networks: An Architecture for Significance-Ordered, Orthogonal Latent Spaces
cs.LG updates on arXiv.org
Deep Reinforcement Learning for Dynamic Battery Management of Autonomous Order Pickers
Deep Reinforcement Learning for Dynamic Battery Management of Autonomous Order Pickers
cs.LG updates on arXiv.org
LLM-Driven Neural Network Generation with Same-Family Architecture Guidance: Disentangling Transfer and Adaptation
LLM-Driven Neural Network Generation with Same-Family Architecture Guidance: Disentangling Transfer and Adaptation
cs.LG updates on arXiv.org
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models
cs.LG updates on arXiv.org
Low-Overhead Error-Corrected QCNNs Using Bivariate Bicycle Codes
Low-Overhead Error-Corrected QCNNs Using Bivariate Bicycle Codes
cs.LG updates on arXiv.org
Multimodal Molecular Representation Learning with Graph Neural Networks, Deep & Cross Networks, and SMILES Embeddings
Multimodal Molecular Representation Learning with Graph Neural Networks, Deep & Cross Networks, and SMILES Embeddings
cs.LG updates on arXiv.org
Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor
Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor
cs.LG updates on arXiv.org
Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting
Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting
cs.LG updates on arXiv.org
Level-Crossing Density as a Mesh-Free High-Frequency Auxiliary Loss for Implicit Neural Representations
Level-Crossing Density as a Mesh-Free High-Frequency Auxiliary Loss for Implicit Neural Representations
cs.LG updates on arXiv.org
Decision-Focused Scenario Generation and Selection for Efficient and Robust Grid Dispatch
Decision-Focused Scenario Generation and Selection for Efficient and Robust Grid Dispatch
cs.LG updates on arXiv.org
AbICL: In-Context Learning for Antigen-Specific Antibody Affinity Ranking
AbICL: In-Context Learning for Antigen-Specific Antibody Affinity Ranking
cs.LG updates on arXiv.org
Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patterns
Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patterns
cs.LG updates on arXiv.org
Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations
Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations
cs.LG updates on arXiv.org
Differentially Private Natural Gradient Descent
Differentially Private Natural Gradient Descent
cs.LG updates on arXiv.org
No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training
No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training
cs.LG updates on arXiv.org
K-ABENA: K-Adaptive Backpropagation with Error-based N-exclusion Algorithm : (Compensated Loss-Based Sample Exclusion with Unbiased Gradient Estimation)
K-ABENA: K-Adaptive Backpropagation with Error-based N-exclusion Algorithm : (Compensated Loss-Based Sample Exclusion with Unbiased Gradient Estimation)
cs.LG updates on arXiv.org
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
cs.LG updates on arXiv.org
Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift
Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift
cs.LG updates on arXiv.org
Learning Sparsest Linear Causal DAGs with Latent Confounders via Higher-Order Cumulants
Learning Sparsest Linear Causal DAGs with Latent Confounders via Higher-Order Cumulants
cs.LG updates on arXiv.org
Stability Annealing Selects the Implicit Bias of Smoothed Sign Descent: A Rate-Indexed Barrier Path on Separable Data
Stability Annealing Selects the Implicit Bias of Smoothed Sign Descent: A Rate-Indexed Barrier Path on Separable Data
cs.LG updates on arXiv.org
Learning When to Automate: Queue Control in Human-AI Service Systems
Learning When to Automate: Queue Control in Human-AI Service Systems
cs.LG updates on arXiv.org
SplineNet: An Isogeometric Deep Learning Method for Complex Shells
SplineNet: An Isogeometric Deep Learning Method for Complex Shells
cs.LG updates on arXiv.org
Scalable Perturbation Learning for Online Self-Supervised Echo State Networks
Scalable Perturbation Learning for Online Self-Supervised Echo State Networks
cs.LG updates on arXiv.org
Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems
Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems
cs.LG updates on arXiv.org
x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability
x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability
cs.LG updates on arXiv.org
Self-Supervised Implicit CEST Reconstruction via Physics-Informed Lorentz Encoding
Self-Supervised Implicit CEST Reconstruction via Physics-Informed Lorentz Encoding
cs.LG updates on arXiv.org
Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning
Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning
cs.LG updates on arXiv.org
X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models
X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models
cs.LG updates on arXiv.org
Canopy: A Heterograph Foundation Model for Metabolic Engineering
Canopy: A Heterograph Foundation Model for Metabolic Engineering
cs.LG updates on arXiv.org
Quantitative Gaussian-Process limits of Tensor Programs
Quantitative Gaussian-Process limits of Tensor Programs
cs.LG updates on arXiv.org
Physics-Informed Neural Embeddings of PDE Solution Families
Physics-Informed Neural Embeddings of PDE Solution Families
cs.LG updates on arXiv.org
TILDE: TILt-based Distributional Erasure for Concept Unlearning
TILDE: TILt-based Distributional Erasure for Concept Unlearning
cs.LG updates on arXiv.org
EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning
EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning
cs.LG updates on arXiv.org
GraphBU: MILP Instance Generation with Graph-Native Block Units
GraphBU: MILP Instance Generation with Graph-Native Block Units
cs.LG updates on arXiv.org
Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion
Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion
cs.LG updates on arXiv.org
Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge
Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge
cs.LG updates on arXiv.org
Broken Ergodicity and the Violation of the Fluctuation-Dissipation Theorem Lead to Generalization Beyond Overfitting in Machine Learning
Broken Ergodicity and the Violation of the Fluctuation-Dissipation Theorem Lead to Generalization Beyond Overfitting in Machine Learning
cs.LG updates on arXiv.org
Performance Optimization and Comparative Analysis of Generative AI Models on Advanced Accelerators
Performance Optimization and Comparative Analysis of Generative AI Models on Advanced Accelerators
cs.LG updates on arXiv.org
Life Cycle Assessment of Pre-training the Lucie 7B Open-Source Large Language Model on the Jean Zay Supercomputer
Life Cycle Assessment of Pre-training the Lucie 7B Open-Source Large Language Model on the Jean Zay Supercomputer
cs.LG updates on arXiv.org
A Task-Driven Evaluation of UAV Detection and Tracking under Synthetic Fog
A Task-Driven Evaluation of UAV Detection and Tracking under Synthetic Fog
cs.LG updates on arXiv.org
Full-range Binary Classifier Calibration for Stable Model Updates in Production
Full-range Binary Classifier Calibration for Stable Model Updates in Production
cs.LG updates on arXiv.org
SHARC: SHAP-Based Interpretability in Machine Learning Risk Models for Regulatory Capital under ICAAP and CCAR
SHARC: SHAP-Based Interpretability in Machine Learning Risk Models for Regulatory Capital under ICAAP and CCAR
cs.LG updates on arXiv.org
Black Hole Black Boxes: Numerical Black Hole Metrics via AInstein Neural Networks
Black Hole Black Boxes: Numerical Black Hole Metrics via AInstein Neural Networks
cs.LG updates on arXiv.org
Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets
Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets
cs.LG updates on arXiv.org
Higher-Order Certified Robustness for Regression
Higher-Order Certified Robustness for Regression
cs.LG updates on arXiv.org
Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity
Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity
cs.LG updates on arXiv.org
Hierarchical Classification via Cascading Feature Elimination: Application to Human Phenotype Ontology-Aligned Facial Phenotyping (FaceMesh2HPO)
Hierarchical Classification via Cascading Feature Elimination: Application to Human Phenotype Ontology-Aligned Facial Phenotyping (FaceMesh2HPO)
cs.LG updates on arXiv.org
DBNN: Neural Spike Classification Using a Deep Binarized Neural Network
DBNN: Neural Spike Classification Using a Deep Binarized Neural Network
cs.LG updates on arXiv.org
To Retain or to Adapt? Generalizing Continual Learning
To Retain or to Adapt? Generalizing Continual Learning
cs.LG updates on arXiv.org
Taxlifier: Leveraging Disease Taxonomy for Enhanced Multi-Label Classification in Chest Radiography
Taxlifier: Leveraging Disease Taxonomy for Enhanced Multi-Label Classification in Chest Radiography
cs.LG updates on arXiv.org
REVIVE: A Multi-Modal Framework for Vandalism Detection and Recovery in Autonomous Vehicles
REVIVE: A Multi-Modal Framework for Vandalism Detection and Recovery in Autonomous Vehicles
cs.LG updates on arXiv.org
Integrating GNSS-Derived Zenith Wet Delay into a Weather Foundation Model Improves Precipitation Forecasting
Integrating GNSS-Derived Zenith Wet Delay into a Weather Foundation Model Improves Precipitation Forecasting
cs.LG updates on arXiv.org
Physics-Regularized Machine Learning for Proprioceptive Vehicle Localization Using Onboard Sensors
Physics-Regularized Machine Learning for Proprioceptive Vehicle Localization Using Onboard Sensors
cs.LG updates on arXiv.org
Uncertainty-Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba
Uncertainty-Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba
cs.LG updates on arXiv.org
Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES
Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES
cs.LG updates on arXiv.org
Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
cs.LG updates on arXiv.org
IMR: Iterative Mode-World Weighted Regression for Multi-Agent Trajectory Prediction
IMR: Iterative Mode-World Weighted Regression for Multi-Agent Trajectory Prediction
cs.LG updates on arXiv.org
Association Restoration Test: Revealing Restorable Shortcuts after Unlearning
Association Restoration Test: Revealing Restorable Shortcuts after Unlearning
cs.LG updates on arXiv.org
Width-Robust Learnability in Mean-Field Bayesian Neural Networks
Width-Robust Learnability in Mean-Field Bayesian Neural Networks
cs.LG updates on arXiv.org
From Closed-Loop Optimization to Open Decision Making: Coupled Digital Twins for Predictive and Autonomous Microscopy
From Closed-Loop Optimization to Open Decision Making: Coupled Digital Twins for Predictive and Autonomous Microscopy
cs.LG updates on arXiv.org
Onnes: A Physics-Grounded Multi-Agent LLM Simulator for Cryogenic Fault Diagnosis in Quantum Computing Infrastructure
Onnes: A Physics-Grounded Multi-Agent LLM Simulator for Cryogenic Fault Diagnosis in Quantum Computing Infrastructure
cs.LG updates on arXiv.org
Contextual Procurement Auctions with Bandit Learning
Contextual Procurement Auctions with Bandit Learning
cs.LG updates on arXiv.org
Latency-Constrained Hardware-Aware Quantum Error Correction Co-Design with Adaptive Confidence-Gated Neural Decoding for the Rotated Surface Code
Latency-Constrained Hardware-Aware Quantum Error Correction Co-Design with Adaptive Confidence-Gated Neural Decoding for the Rotated Surface Code
cs.LG updates on arXiv.org
On the Condition Number Upper Bound of the L-BFGS Inverse Hessian Approximation Matrix with a Two-Sided Geometric Envelope Safeguarding Mechanism
On the Condition Number Upper Bound of the L-BFGS Inverse Hessian Approximation Matrix with a Two-Sided Geometric Envelope Safeguarding Mechanism
cs.LG updates on arXiv.org
Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization
Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization
cs.LG updates on arXiv.org
Few-Medoids: An Embarrassingly Simple Coreset Selection Method for Few-Shot Knowledge Distillation
Few-Medoids: An Embarrassingly Simple Coreset Selection Method for Few-Shot Knowledge Distillation
cs.LG updates on arXiv.org
On the convergence of graph Laplacians with a symmetric divergence
On the convergence of graph Laplacians with a symmetric divergence
cs.LG updates on arXiv.org
Energy-Efficient GPU DVFS for Fine-Tuning of SLMs on Resource-constrained Embedded Devices
Energy-Efficient GPU DVFS for Fine-Tuning of SLMs on Resource-constrained Embedded Devices
cs.LG updates on arXiv.org
Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding
Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding
cs.LG updates on arXiv.org
Is Domain Adaptation Always Helpful? A Frozen-Backbone Study of Cross-Domain Sentiment Transfer
Is Domain Adaptation Always Helpful? A Frozen-Backbone Study of Cross-Domain Sentiment Transfer
cs.LG updates on arXiv.org
Discovering Frequent Closed Embedded Sub-DAGs in Spatio-Temporal Event Data
Discovering Frequent Closed Embedded Sub-DAGs in Spatio-Temporal Event Data
cs.LG updates on arXiv.org
Multi-Channel Spread-Spectrum Code Watermarking
Multi-Channel Spread-Spectrum Code Watermarking
cs.LG updates on arXiv.org
REAN: Reconstruction-aware ECG Anonymization Based on Privacy--Utility Orthogonality
REAN: Reconstruction-aware ECG Anonymization Based on Privacy--Utility Orthogonality
cs.LG updates on arXiv.org
Separation Capacity of Scattering Networks on Low-Dimensional Datasets
Separation Capacity of Scattering Networks on Low-Dimensional Datasets
cs.LG updates on arXiv.org
Determinantal point process sampling for bioacoustic active learning
Determinantal point process sampling for bioacoustic active learning
cs.LG updates on arXiv.org
6G Sensing Security: Distributed Game-Theoretic RL for Urban Beamforming and Attacker Detection
6G Sensing Security: Distributed Game-Theoretic RL for Urban Beamforming and Attacker Detection
cs.LG updates on arXiv.org
Static Metrics Are Insufficient: Predicting Java Method Energy Usage with Execution Time
Static Metrics Are Insufficient: Predicting Java Method Energy Usage with Execution Time
cs.LG updates on arXiv.org
Enhanced Seam Segmentation for Automated Welding Robot in Construction Through Transfer Learning: Addressing Limitations of Bilateral Segmentation Network
Enhanced Seam Segmentation for Automated Welding Robot in Construction Through Transfer Learning: Addressing Limitations of Bilateral Segmentation Network
cs.LG updates on arXiv.org
Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design
Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design
cs.LG updates on arXiv.org
TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios
TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios
cs.LG updates on arXiv.org
Entanglement as a Structural Complexity Axis: A PAC-Bayesian View of Generalization in Quantum Policies and Value Functions
Entanglement as a Structural Complexity Axis: A PAC-Bayesian View of Generalization in Quantum Policies and Value Functions
cs.LG updates on arXiv.org
A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problems
A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problems
cs.LG updates on arXiv.org
Kernel-based Operator Learning: Error Analysis, Budget Allocation, and a Physics-Informed Extension
Kernel-based Operator Learning: Error Analysis, Budget Allocation, and a Physics-Informed Extension
cs.LG updates on arXiv.org
Dithered Gaussian Mechanism for Randomness-Efficient Differential Privacy
Dithered Gaussian Mechanism for Randomness-Efficient Differential Privacy
cs.LG updates on arXiv.org
Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement
Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement
cs.LG updates on arXiv.org
A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel
A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel
cs.LG updates on arXiv.org
Learning to Throw Objects Safely in Multi-Obstacle Environments
Learning to Throw Objects Safely in Multi-Obstacle Environments
cs.LG updates on arXiv.org
What Images Cannot Say: Language-Guided Olfactory Representation Learning
What Images Cannot Say: Language-Guided Olfactory Representation Learning
cs.LG updates on arXiv.org
Provable learning separation for predicting time-evolution of quantum many-body systems
Provable learning separation for predicting time-evolution of quantum many-body systems
cs.LG updates on arXiv.org
Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles
Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles
cs.LG updates on arXiv.org
Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo Engine
Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo Engine
cs.LG updates on arXiv.org
The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology
The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology
cs.LG updates on arXiv.org
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
cs.LG updates on arXiv.org
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
cs.LG updates on arXiv.org
DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised
DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised
cs.LG updates on arXiv.org
Trust-free Personalized Decentralized Learning
Trust-free Personalized Decentralized Learning
cs.LG updates on arXiv.org
Universality of Benign Overfitting in Binary Linear Classification
Universality of Benign Overfitting in Binary Linear Classification
cs.LG updates on arXiv.org
The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer
The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer
cs.LG updates on arXiv.org
MAME: Multidimensional Adaptive Metamer Exploration with Human Perceptual Feedback
MAME: Multidimensional Adaptive Metamer Exploration with Human Perceptual Feedback
cs.LG updates on arXiv.org
Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
cs.LG updates on arXiv.org
Explainable embeddings with Distance Explainer
Explainable embeddings with Distance Explainer
cs.LG updates on arXiv.org
Temporal Variational Implicit Neural Representations
Temporal Variational Implicit Neural Representations
cs.LG updates on arXiv.org
Learning The Minimum Action Distance
Learning The Minimum Action Distance
cs.LG updates on arXiv.org
Variational Learning of Disentangled Representations
Variational Learning of Disentangled Representations
cs.LG updates on arXiv.org
Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization
Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization
cs.LG updates on arXiv.org
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
cs.LG updates on arXiv.org
FedDAF: Federated Domain Adaptation Using Model Functional Distance
FedDAF: Federated Domain Adaptation Using Model Functional Distance
cs.LG updates on arXiv.org
How Can Mamba Learn In Context with Outliers and Generalize Provably?
How Can Mamba Learn In Context with Outliers and Generalize Provably?
cs.LG updates on arXiv.org
Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics
Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics
cs.LG updates on arXiv.org
AtomBench: A Benchmarking Framework for Generative Crystal Reconstruction Models in Conventional Superconductors
AtomBench: A Benchmarking Framework for Generative Crystal Reconstruction Models in Conventional Superconductors
cs.LG updates on arXiv.org
Solver-Integrated Adversarial Attacking and Training of Neural Operators
Solver-Integrated Adversarial Attacking and Training of Neural Operators
cs.LG updates on arXiv.org
SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
cs.LG updates on arXiv.org
LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation
LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation
cs.LG updates on arXiv.org
Deep Reinforcement Learning for Dynamic Origin-Destination Matrix Estimation in Microscopic Traffic Simulations Considering Credit Assignment
Deep Reinforcement Learning for Dynamic Origin-Destination Matrix Estimation in Microscopic Traffic Simulations Considering Credit Assignment
cs.LG updates on arXiv.org
Adaptive digital twins for predictive decision-making: Online Bayesian learning of transition dynamics
Adaptive digital twins for predictive decision-making: Online Bayesian learning of transition dynamics
cs.LG updates on arXiv.org
PGOT: A Physics-Geometry Operator Transformer for Complex PDEs
PGOT: A Physics-Geometry Operator Transformer for Complex PDEs
cs.LG updates on arXiv.org
KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta
KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta
cs.LG updates on arXiv.org
SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines
SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines
cs.LG updates on arXiv.org
FlexAct: Why Learn when you can Pick?
FlexAct: Why Learn when you can Pick?
cs.LG updates on arXiv.org
Geometric Stability: The Missing Axis of Representations
Geometric Stability: The Missing Axis of Representations
cs.LG updates on arXiv.org
A Constrained Optimization Perspective of Unrolled Transformers
A Constrained Optimization Perspective of Unrolled Transformers
cs.LG updates on arXiv.org
GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning
GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning
cs.LG updates on arXiv.org
TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning
TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning
cs.LG updates on arXiv.org
StepShield: When, Not Whether to Intervene on Rogue Agents
StepShield: When, Not Whether to Intervene on Rogue Agents
cs.LG updates on arXiv.org
BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networks
BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networks
cs.LG updates on arXiv.org
Universal Algorithm-Implicit Learning
Universal Algorithm-Implicit Learning
cs.LG updates on arXiv.org
Transformers converge to invariant algorithmic cores
Transformers converge to invariant algorithmic cores
cs.LG updates on arXiv.org
Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure
Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure
cs.LG updates on arXiv.org
Leech Lattice Vector Quantization for Efficient LLM Compression
Leech Lattice Vector Quantization for Efficient LLM Compression
cs.LG updates on arXiv.org
Channel-wise Retrieval for Multivariate Time Series Forecasting
Channel-wise Retrieval for Multivariate Time Series Forecasting
cs.LG updates on arXiv.org
Fine-Tuning Regimes Define Distinct Continual Learning Problems
Fine-Tuning Regimes Define Distinct Continual Learning Problems
cs.LG updates on arXiv.org
Joint Energy Management and Coordinated AIGC Workload Scheduling for Distributed Data Centers: A Diffusion-Aided Reward Shaping Approach
Joint Energy Management and Coordinated AIGC Workload Scheduling for Distributed Data Centers: A Diffusion-Aided Reward Shaping Approach
cs.LG updates on arXiv.org
PerCaM-Health: Personalized Dynamic Causal Graphs for Healthcare Reasoning
PerCaM-Health: Personalized Dynamic Causal Graphs for Healthcare Reasoning
cs.LG updates on arXiv.org
MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
cs.LG updates on arXiv.org
Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning
Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning
cs.LG updates on arXiv.org
BigMac: Breaking the Pareto Frontier of Compute and Memory in Multimodal LLM Training
BigMac: Breaking the Pareto Frontier of Compute and Memory in Multimodal LLM Training
cs.LG updates on arXiv.org
Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems
Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems
cs.LG updates on arXiv.org
GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators
GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators
cs.LG updates on arXiv.org
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
cs.LG updates on arXiv.org
On the Redundancy of Timestep Embeddings in Diffusion Models
On the Redundancy of Timestep Embeddings in Diffusion Models
cs.LG updates on arXiv.org
Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"
Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"
cs.LG updates on arXiv.org
Active Quantum Kernel Acquisition for Gaussian Process Regression
Active Quantum Kernel Acquisition for Gaussian Process Regression
cs.LG updates on arXiv.org
When Prices Double in a Week: Forecasting of Agricultural Volatility in Import-Isolated Markets
When Prices Double in a Week: Forecasting of Agricultural Volatility in Import-Isolated Markets
cs.LG updates on arXiv.org
PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint
PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint
cs.LG updates on arXiv.org
Learning the Supports for Categorical Critic in Reinforcement Learning
Learning the Supports for Categorical Critic in Reinforcement Learning
cs.LG updates on arXiv.org
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers
cs.LG updates on arXiv.org
Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches
Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches
cs.LG updates on arXiv.org
MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning
MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning
cs.LG updates on arXiv.org
Classification of Financial Data Using Quantum Support Vector Machine
Classification of Financial Data Using Quantum Support Vector Machine
cs.LG updates on arXiv.org
Benign Overfitting with Quantum Kernels
Benign Overfitting with Quantum Kernels
cs.LG updates on arXiv.org
HERB: Human-augmented Efficient Reinforcement learning for Bin-packing
HERB: Human-augmented Efficient Reinforcement learning for Bin-packing
cs.LG updates on arXiv.org
Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems
Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems
cs.LG updates on arXiv.org
Position: EU AI Act's Research Exemptions Can Break the Publication Norms of Major AI Conferences
Position: EU AI Act's Research Exemptions Can Break the Publication Norms of Major AI Conferences
cs.LG updates on arXiv.org
MASCA: LLM based-Multi Agents System for Credit Assessment
MASCA: LLM based-Multi Agents System for Credit Assessment
cs.LG updates on arXiv.org
Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI
Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI
cs.LG updates on arXiv.org
Reduced NEXI protocol for the quantification of human gray matter microstructure on the Connectome 2.0 scanner
Reduced NEXI protocol for the quantification of human gray matter microstructure on the Connectome 2.0 scanner
cs.LG updates on arXiv.org
Base Models Know How to Reason, Thinking Models Learn When
Base Models Know How to Reason, Thinking Models Learn When
cs.LG updates on arXiv.org
A Fast Binary Splitting Approach for Non-Adaptive Learning of Erd\H{o}s--R\'enyi Graphs
A Fast Binary Splitting Approach for Non-Adaptive Learning of Erd\H{o}s--R\'enyi Graphs
cs.LG updates on arXiv.org
No-Regret Gaussian Process Optimization of Time-Varying Functions
No-Regret Gaussian Process Optimization of Time-Varying Functions
cs.LG updates on arXiv.org
A Comparative Study of EMG- and IMU-based Gesture Recognition at the Wrist and Forearm
A Comparative Study of EMG- and IMU-based Gesture Recognition at the Wrist and Forearm
cs.LG updates on arXiv.org
SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models
SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models
cs.LG updates on arXiv.org
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
cs.LG updates on arXiv.org
Reliable Mislabel Detection for Video Capsule Endoscopy Data
Reliable Mislabel Detection for Video Capsule Endoscopy Data
cs.LG updates on arXiv.org
Conformal Prediction Sets for Instance Segmentation
Conformal Prediction Sets for Instance Segmentation
cs.LG updates on arXiv.org
A Gibbs posterior sampler for inverse problem based on prior diffusion model
A Gibbs posterior sampler for inverse problem based on prior diffusion model
cs.LG updates on arXiv.org
Estimation of instrument and noise parameters for inverse problem based on prior diffusion model
Estimation of instrument and noise parameters for inverse problem based on prior diffusion model
cs.LG updates on arXiv.org
Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique
Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique
cs.LG updates on arXiv.org
PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
cs.LG updates on arXiv.org
What Counts as Real? Speech Restoration and Voice Quality Conversion Pose New Challenges to Deepfake Detection
What Counts as Real? Speech Restoration and Voice Quality Conversion Pose New Challenges to Deepfake Detection
cs.LG updates on arXiv.org
Towards Interpretable Foundation Models for Retinal Fundus Images
Towards Interpretable Foundation Models for Retinal Fundus Images
cs.LG updates on arXiv.org
DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
cs.LG updates on arXiv.org
Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?
Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?
cs.LG updates on arXiv.org
Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates
Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates
cs.LG updates on arXiv.org
Data-Efficient Indentation Size Effect Correction in Steels Using Machine Learning and Physics-Constrained Neural Network
Data-Efficient Indentation Size Effect Correction in Steels Using Machine Learning and Physics-Constrained Neural Network
cs.LG updates on arXiv.org
Model-based Bootstrap of Controlled Markov Chains
Model-based Bootstrap of Controlled Markov Chains
cs.LG updates on arXiv.org
A semantic mutation metric for metamorphic relation adequacy in scientific computing programs
A semantic mutation metric for metamorphic relation adequacy in scientific computing programs
cs.LG updates on arXiv.org
Parameter-Free and Group Conditional Online Conformal Prediction
Parameter-Free and Group Conditional Online Conformal Prediction
cs.LG updates on arXiv.org
Distribution-free changepoint localization after sequential change detection
Distribution-free changepoint localization after sequential change detection
cs.LG updates on arXiv.org
It does what it says on the tin: safe synthetic data from coarsened margins
It does what it says on the tin: safe synthetic data from coarsened margins
cs.LG updates on arXiv.org
CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention
CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention
cs.LG updates on arXiv.org
DanceOPD: On-Policy Generative Field Distillation
DanceOPD: On-Policy Generative Field Distillation
cs.LG updates on arXiv.org
Robust Bayes-Assisted Conformal Prediction
Robust Bayes-Assisted Conformal Prediction
cs.LG updates on arXiv.org
Wan-Streamer v0.2: Higher Resolution, Same Latency
Wan-Streamer v0.2: Higher Resolution, Same Latency
cs.LG updates on arXiv.org
TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction
TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction
cs.LG updates on arXiv.org
Physically-Relevant Information Learning in High-Dimensional Time-Derivatives Spaces
Physically-Relevant Information Learning in High-Dimensional Time-Derivatives Spaces
cs.LG updates on arXiv.org
Unified Audio Intelligence Without Regressing on Text Intelligence
Unified Audio Intelligence Without Regressing on Text Intelligence
cs.LG updates on arXiv.org
Shape Over Intensity: Directional Topological Encoding for False Positive Reduction in Intracranial Aneurysm Detection
Shape Over Intensity: Directional Topological Encoding for False Positive Reduction in Intracranial Aneurysm Detection
cs.LG updates on arXiv.org
Multiplayer Interactive World Models with Representation Autoencoders
Multiplayer Interactive World Models with Representation Autoencoders
cs.LG updates on arXiv.org
LLM-as-a-Verifier: A General-Purpose Verification Framework
LLM-as-a-Verifier: A General-Purpose Verification Framework
stat.ML updates on arXiv.org
Higher-Order Certified Robustness for Regression
Higher-Order Certified Robustness for Regression
stat.ML updates on arXiv.org
Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity
Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity
stat.ML updates on arXiv.org
To Retain or to Adapt? Generalizing Continual Learning
To Retain or to Adapt? Generalizing Continual Learning
stat.ML updates on arXiv.org
Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
stat.ML updates on arXiv.org
Width-Robust Learnability in Mean-Field Bayesian Neural Networks
Width-Robust Learnability in Mean-Field Bayesian Neural Networks
stat.ML updates on arXiv.org
On the convergence of graph Laplacians with a symmetric divergence
On the convergence of graph Laplacians with a symmetric divergence
stat.ML updates on arXiv.org
Separation Capacity of Scattering Networks on Low-Dimensional Datasets
Separation Capacity of Scattering Networks on Low-Dimensional Datasets
stat.ML updates on arXiv.org
A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problems
A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problems
stat.ML updates on arXiv.org
A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel
A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel
stat.ML updates on arXiv.org
Exact computation of posterior distribution of mixture weights in hierarchical Bayesian models
Exact computation of posterior distribution of mixture weights in hierarchical Bayesian models
stat.ML updates on arXiv.org
No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training
No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training
stat.ML updates on arXiv.org
Stochastic generator of trajectories from record data: application to the fluctuations of a glacier's frontal position from a sample of moraines
Stochastic generator of trajectories from record data: application to the fluctuations of a glacier's frontal position from a sample of moraines
stat.ML updates on arXiv.org
Closed-form fractional radial links for elliptical Mahalanobis discriminant analysis
Closed-form fractional radial links for elliptical Mahalanobis discriminant analysis
stat.ML updates on arXiv.org
Quantitative Gaussian-Process limits of Tensor Programs
Quantitative Gaussian-Process limits of Tensor Programs
stat.ML updates on arXiv.org
A unified perspective of Gaussian process approximation for differential equations
A unified perspective of Gaussian process approximation for differential equations
stat.ML updates on arXiv.org
Approximate Risk Minimization Over Shrinking-Thresholding Rules in Normal Mean Estimation
Approximate Risk Minimization Over Shrinking-Thresholding Rules in Normal Mean Estimation
stat.ML updates on arXiv.org
Factor-Augmented Machine Learning Panel Regressions
Factor-Augmented Machine Learning Panel Regressions
stat.ML updates on arXiv.org
Feature Learning for the High Dimensional Stationary Sch\"odinger Equation with Deep Ritz Method
Feature Learning for the High Dimensional Stationary Sch\"odinger Equation with Deep Ritz Method
stat.ML updates on arXiv.org
EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning
EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning
stat.ML updates on arXiv.org
No-Regret Gaussian Process Optimization of Time-Varying Functions
No-Regret Gaussian Process Optimization of Time-Varying Functions
stat.ML updates on arXiv.org
A Gibbs posterior sampler for inverse problem based on prior diffusion model
A Gibbs posterior sampler for inverse problem based on prior diffusion model
stat.ML updates on arXiv.org
Estimation of instrument and noise parameters for inverse problem based on prior diffusion model
Estimation of instrument and noise parameters for inverse problem based on prior diffusion model
stat.ML updates on arXiv.org
Model-based Bootstrap of Controlled Markov Chains
Model-based Bootstrap of Controlled Markov Chains
stat.ML updates on arXiv.org
Parameter-Free and Group Conditional Online Conformal Prediction
Parameter-Free and Group Conditional Online Conformal Prediction
stat.ML updates on arXiv.org
Distribution-free changepoint localization after sequential change detection
Distribution-free changepoint localization after sequential change detection
stat.ML updates on arXiv.org
It does what it says on the tin: safe synthetic data from coarsened margins
It does what it says on the tin: safe synthetic data from coarsened margins
stat.ML updates on arXiv.org
Robust Bayes-Assisted Conformal Prediction
Robust Bayes-Assisted Conformal Prediction
stat.ML updates on arXiv.org
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
stat.ML updates on arXiv.org
Universality of Benign Overfitting in Binary Linear Classification
Universality of Benign Overfitting in Binary Linear Classification
stat.ML updates on arXiv.org
Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation
Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation
stat.ML updates on arXiv.org
Benign Overfitting with Quantum Kernels
Benign Overfitting with Quantum Kernels
stat.ML updates on arXiv.org
Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
stat.ML updates on arXiv.org
Variational Learning of Disentangled Representations
Variational Learning of Disentangled Representations
stat.ML updates on arXiv.org
Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics
Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics
stat.ML updates on arXiv.org
Geometric Stability: The Missing Axis of Representations
Geometric Stability: The Missing Axis of Representations
stat.ML updates on arXiv.org
Conformal Prediction Sets for Instance Segmentation
Conformal Prediction Sets for Instance Segmentation
stat.ML updates on arXiv.org
Joint Energy Management and Coordinated AIGC Workload Scheduling for Distributed Data Centers: A Diffusion-Aided Reward Shaping Approach
Joint Energy Management and Coordinated AIGC Workload Scheduling for Distributed Data Centers: A Diffusion-Aided Reward Shaping Approach
stat.ML updates on arXiv.org
Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems
Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems
stat.ML updates on arXiv.org
Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding
Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding
stat.ML updates on arXiv.org
Stabilized Higher-Order Influence Functions: Statistical Theory of a Class of Bilinear Forms
Stabilized Higher-Order Influence Functions: Statistical Theory of a Class of Bilinear Forms
stat.ML updates on arXiv.org
The Exact Worst-Case Tail Probability under Bounded Kurtosis
The Exact Worst-Case Tail Probability under Bounded Kurtosis
＠IT 全フォーラム 最新記事一覧
「セキュリティ対策証明」経験ありは8割超、だがSCS評価制度迫るも“SaaS把握率”は2割未満
「セキュリティ対策証明」経験ありは8割超、だがSCS評価制度迫るも“SaaS把握率”は2割未満
＠IT 全フォーラム 最新記事一覧
「AIで障害調査」どころじゃなかったDeNA 「2週間でも無理」だった原因特定をどう2日で実現？
「AIで障害調査」どころじゃなかったDeNA 「2週間でも無理」だった原因特定をどう2日で実現？
#LLMタグ
【衝撃】noteが2Q累計営業益「20倍超」！？AI活用で人件費率低下の真相と、エンジニアの未来が変わる3つの兆候🚀
【衝撃】noteが2Q累計営業益「20倍超」！？AI活用で人件費率低下の真相と、エンジニアの未来が変わる3つの兆候🚀
#LLMタグ
【GPT-5.5Thinking×Claude】ちくわ記事ご購入250回突破記念‼️スマホ対応。平成コギャルテトリス操作方法🎁
【GPT-5.5Thinking×Claude】ちくわ記事ご購入250回突破記念‼️スマホ対応。平成コギャルテトリス操作方法🎁
ITmedia NEWS 最新記事一覧
BOOTH、0円出品で「セールはこちら」きょうから禁止 新着通知を使った“宣伝ハック”に終止符
BOOTH、0円出品で「セールはこちら」きょうから禁止 新着通知を使った“宣伝ハック”に終止符
MarkTechPost
Ant Group’s Robbyant Open-Sources LingBot-Vision: A 1B Boundary-Centric Vision Foundation Model for Dense Spatial Perception
Ant Group’s Robbyant Open-Sources LingBot-Vision: A 1B Boundary-Centric Vision Foundation Model for Dense Spatial Perception
ITmedia NEWS 最新記事一覧
女性声優にXの“青バッジ”を勝手に送り付ける怪事案が相次ぐ 津田美波さん、黒木ほの香さん、土屋李央さんなど
女性声優にXの“青バッジ”を勝手に送り付ける怪事案が相次ぐ 津田美波さん、黒木ほの香さん、土屋李央さんなど
ITmedia NEWS 最新記事一覧
Metaの新AI「Muse Image」公開に伴う注意点 Instagram公開アカウントのコンテンツ再利用を防ぐには
Metaの新AI「Muse Image」公開に伴う注意点 Instagram公開アカウントのコンテンツ再利用を防ぐには
ITmedia NEWS 最新記事一覧
テスラ車が住宅に突っ込み高齢女性が死亡 遺族は「運転支援システムに欠陥」と訴えも、マスク氏らは反論 米国
テスラ車が住宅に突っ込み高齢女性が死亡 遺族は「運転支援システムに欠陥」と訴えも、マスク氏らは反論 米国
ITmedia NEWS 最新記事一覧
note上方修正 「AI活用、想定以上」で人件費率低下 2Q累計営業益は「20倍超」に
note上方修正 「AI活用、想定以上」で人件費率低下 2Q累計営業益は「20倍超」に
Latent.Space
[AINews] Lilian Weng summarizes 35 papers on Harness Engineering for RSI
[AINews] Lilian Weng summarizes 35 papers on Harness Engineering for RSI
#LLMタグ
【2026年最新】トヨタがAIで採用業務を革新！「逸材不採用」を防ぐ裏技と、エンジニアに迫る人事DXの真実 🚀
【2026年最新】トヨタがAIで採用業務を革新！「逸材不採用」を防ぐ裏技と、エンジニアに迫る人事DXの真実 🚀
#LLMタグ
【生成AIニュースまとめ】2026年7月8日 — 初の自走型AIランサムウェアとAnthropicの売上逆転
【生成AIニュースまとめ】2026年7月8日 — 初の自走型AIランサムウェアとAnthropicの売上逆転
機械学習タグが付けられた新着記事 - Qiita
【技術解説】株式投資 データ分析 pandasで高頻度取引の低レイテンシ技術をマスターしよう！
【技術解説】株式投資 データ分析 pandasで高頻度取引の低レイテンシ技術をマスターしよう！
#LLMタグ
【速報】Claude Fable 5サブスクが突如延長！「寝ずに使い切った奴ら」の悲劇と、AI時代の生存戦略 🚨💻
【速報】Claude Fable 5サブスクが突如延長！「寝ずに使い切った奴ら」の悲劇と、AI時代の生存戦略 🚨💻
ITmedia NEWS 最新記事一覧
Netflix、「VOGUE」「Rolling Stone」など著名メディアの動画を配信へ
Netflix、「VOGUE」「Rolling Stone」など著名メディアの動画を配信へ
#LLMタグ
論文紹介”COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami”(https://arxiv.org/pdf/2606.26299)
論文紹介”COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami”(https://arxiv.org/pdf/2606.26299)
機械学習タグが付けられた新着記事 - Qiita
生成AIパスポート対策問題集をUdemyで公開しています｜全240問・2026年シラバス対応
生成AIパスポート対策問題集をUdemyで公開しています｜全240問・2026年シラバス対応
＠IT 全フォーラム 最新記事一覧
PR： 「AIファースト」の前にやるべきこと――東大、日本マイクロソフト、リコー、レゾナックが語るデータ基盤の未来
PR： 「AIファースト」の前にやるべきこと――東大、日本マイクロソフト、リコー、レゾナックが語るデータ基盤の未来
MarkTechPost
NVIDIA Releases Audex (Nemotron-Labs-Audex-30B-A3B): A Unified Audio-Text LLM That Preserves the Text Intelligence of Its Backbone
NVIDIA Releases Audex (Nemotron-Labs-Audex-30B-A3B): A Unified Audio-Text LLM That Preserves the Text Intelligence of Its Backbone
ITmedia NEWS 最新記事一覧
「Claude Fable 5」サブスク、突如5日間延長 ユーザー悲喜こもごも「寝ずに頑張ったのに」「制限リセットして」
「Claude Fable 5」サブスク、突如5日間延長 ユーザー悲喜こもごも「寝ずに頑張ったのに」「制限リセットして」
#LLMタグ
なぜClaude Codeは開発を加速させるのか｜仕様書をAIに与えてコード生成の精度を最大化する完全ガイド
なぜClaude Codeは開発を加速させるのか｜仕様書をAIに与えてコード生成の精度を最大化する完全ガイド
The Verge
Meta’s glasses will turn off the camera if you tamper with the privacy light
Meta’s glasses will turn off the camera if you tamper with the privacy light
＠IT 全フォーラム 最新記事一覧
「約30万円の講座、30万円上限で助成」 東京都、AIなどを学べる「若手エンジニアコース」受講者募集中
「約30万円の講座、30万円上限で助成」 東京都、AIなどを学べる「若手エンジニアコース」受講者募集中
AI News & Artificial Intelligence | TechCrunch
Meta just launched a new AI generator, Muse Image, and users are already pushing back over use of their photos
Meta just launched a new AI generator, Muse Image, and users are already pushing back over use of their photos
ITmedia NEWS 最新記事一覧
“ストレスで飲酒”は脳を変質させる 断酒しても戻らず、中年になって変化への対応力が低下 米国チームがマウス実験
“ストレスで飲酒”は脳を変質させる 断酒しても戻らず、中年になって変化への対応力が低下 米国チームがマウス実験
ITmedia NEWS 最新記事一覧
犬が飼い主に従うのは「忖度」？ それとも「人が好き」だから？ 餌を巡る綱引き対決で狼と比較実験
犬が飼い主に従うのは「忖度」？ それとも「人が好き」だから？ 餌を巡る綱引き対決で狼と比較実験
WIRED
Meta Now Lets Anyone Use Your Instagram Photos in AI Images—Unless You Opt Out
Meta Now Lets Anyone Use Your Instagram Photos in AI Images—Unless You Opt Out
The Verge
Of course viewers are giving up on Netflix shows
Of course viewers are giving up on Netflix shows
The Verge
Netflix is about to host videos from BuzzFeed, Condé Nast, and other publishers
Netflix is about to host videos from BuzzFeed, Condé Nast, and other publishers
Hugging Face - Blog
From Hugging Face to Amazon SageMaker Studio in one click
From Hugging Face to Amazon SageMaker Studio in one click
The Verge
Meta’s new Muse Image model can pull other Instagram users into AI photos
Meta’s new Muse Image model can pull other Instagram users into AI photos
AI News & Artificial Intelligence | TechCrunch
Why the rise of open source AI isn’t hurting Anthropic … yet
Why the rise of open source AI isn’t hurting Anthropic … yet
＠IT 全フォーラム 最新記事一覧
ソフトバンクの「1人100エージェント」を支える独自AIゲートウェイ「Cloud Proxy」の正体
ソフトバンクの「1人100エージェント」を支える独自AIゲートウェイ「Cloud Proxy」の正体
AI News & Artificial Intelligence | TechCrunch
Microsoft joins AI cost-cutting trend by relying more on its own models
Microsoft joins AI cost-cutting trend by relying more on its own models
AI News & Artificial Intelligence | TechCrunch
Discord admits AI moderation bug wrongfully banned users over harmless images
Discord admits AI moderation bug wrongfully banned users over harmless images
The Verge
X says top accounts steal videos from other users as it announces new video tools
X says top accounts steal videos from other users as it announces new video tools
WIRED
Mysterious Compound Detected on Pluto and Titan
Mysterious Compound Detected on Pluto and Titan