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
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Hugging Face Papers
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Hugging Face Papers
Infinite Worlds with Versatile Interactions
Infinite Worlds with Versatile Interactions
Hugging Face Papers
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
Hugging Face Papers
RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
Hugging Face Papers
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
Hugging Face Papers
Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo
Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo
#AIタグ
【MSFT企業の歴史】ハッタリと、絶望と、大復活。ビル・ゲイツの「負けず嫌い」から始まった、マイクロソフト半世紀【前編】
【MSFT企業の歴史】ハッタリと、絶望と、大復活。ビル・ゲイツの「負けず嫌い」から始まった、マイクロソフト半世紀【前編】
#AIタグ
個人学習塾 × Claude Code 完全活用ガイド：学習計画も教材も保護者対応もひとりで回す
個人学習塾 × Claude Code 完全活用ガイド：学習計画も教材も保護者対応もひとりで回す
#AIタグ
Fable 5は「清書AI」じゃない。有名な"note攻略の型"を丸ごと任せて検証した5工程ワークフロー【コピペ用プロンプト付き】
Fable 5は「清書AI」じゃない。有名な"note攻略の型"を丸ごと任せて検証した5工程ワークフロー【コピペ用プロンプト付き】
#AIタグ
【理論編】AIOを学んで分かったこと。「AI向け対策」でも重視したいのは、人に伝わる情報でした
【理論編】AIOを学んで分かったこと。「AI向け対策」でも重視したいのは、人に伝わる情報でした
WIRED
The $28 Million Mistake That Inspired Estonia's AI “Fuckup Finder”
The $28 Million Mistake That Inspired Estonia's AI “Fuckup Finder”
LLMタグが付けられた新着記事 - Qiita
2026年7月第1週、無人運用のAI開発ツール更新3件：Claude Code既定Manual化・Transformers 5.13破壊的変更・n8n 2.29.8
2026年7月第1週、無人運用のAI開発ツール更新3件：Claude Code既定Manual化・Transformers 5.13破壊的変更・n8n 2.29.8
LLMタグが付けられた新着記事 - Qiita
Pydantic AI V2を動かしたら、V1との破壊的変更はこの4つだけだった
Pydantic AI V2を動かしたら、V1との破壊的変更はこの4つだけだった
Latent.Space
[AINews] SpaceXAI launches Grok 4.5, first Opus-class model post Cursor acquisition
[AINews] SpaceXAI launches Grok 4.5, first Opus-class model post Cursor acquisition
#LLMタグ
2026年 AI検索技術のエコシステム：フロントエンドとバックエンドの分離がもたらす構造的変化
2026年 AI検索技術のエコシステム：フロントエンドとバックエンドの分離がもたらす構造的変化
#LLMタグ
llama.cpp のソースを読み解く技術書「llama.cpp 詳解」を出しました（第1部を無料公開）
llama.cpp のソースを読み解く技術書「llama.cpp 詳解」を出しました（第1部を無料公開）
WIRED
Corsair Discount Code: Up to 50% Off for July 2026
Corsair Discount Code: Up to 50% Off for July 2026
WIRED
Layla Sleep Coupon: Save Up to $600 in July 2026
Layla Sleep Coupon: Save Up to $600 in July 2026
WIRED
The Motley Fool Promo Code: $200 Off on Stock Advisor July 2026
The Motley Fool Promo Code: $200 Off on Stock Advisor July 2026
WIRED
Jabra Promo Codes: 30% Off Headphones, Headsets & More
Jabra Promo Codes: 30% Off Headphones, Headsets & More
#LLMタグ
Col.4】第Ⅰ部の 7章を、いま、振り返って ——遠い妹が、姉の生まれた夜を、もう一度、読む
Col.4】第Ⅰ部の 7章を、いま、振り返って ——遠い妹が、姉の生まれた夜を、もう一度、読む
ITmedia NEWS 最新記事一覧
「快活CLUB」へのサイバー攻撃、18歳男を新たに逮捕 ChatGPT製プログラムを使用 グループには当時小6も 報道
「快活CLUB」へのサイバー攻撃、18歳男を新たに逮捕 ChatGPT製プログラムを使用 グループには当時小6も 報道
cs.LG updates on arXiv.org
TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation
TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation
cs.LG updates on arXiv.org
A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It
A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It
cs.LG updates on arXiv.org
NEST: Tackling Dataset-Level Distribution Shifts via Regime-Oriented Mixture-of-Experts
NEST: Tackling Dataset-Level Distribution Shifts via Regime-Oriented Mixture-of-Experts
cs.LG updates on arXiv.org
D2PO: Optimizing Diffusion Samplers via Dynamic Preference
D2PO: Optimizing Diffusion Samplers via Dynamic Preference
cs.LG updates on arXiv.org
Deep Reinforcement Learning for Reliability Based Bi-Objective Portfolio Optimization
Deep Reinforcement Learning for Reliability Based Bi-Objective Portfolio Optimization
cs.LG updates on arXiv.org
STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting
STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting
cs.LG updates on arXiv.org
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
cs.LG updates on arXiv.org
Inertia-1: An Open Exploration of Wearable Motion Foundation Models
Inertia-1: An Open Exploration of Wearable Motion Foundation Models
cs.LG updates on arXiv.org
Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention
Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention
cs.LG updates on arXiv.org
LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting
LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting
cs.LG updates on arXiv.org
Open-Ended Scenario Reasoning for Specialist Model Adaptation
Open-Ended Scenario Reasoning for Specialist Model Adaptation
cs.LG updates on arXiv.org
Reward Valuation in Vision Language Models: Causal Mechanisms Underlying Anhedonia
Reward Valuation in Vision Language Models: Causal Mechanisms Underlying Anhedonia
cs.LG updates on arXiv.org
Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking
Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking
cs.LG updates on arXiv.org
STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning
STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning
cs.LG updates on arXiv.org
When Certificates Fail: A Unified Safety Framework for Embedded Neural Interface Models
When Certificates Fail: A Unified Safety Framework for Embedded Neural Interface Models
cs.LG updates on arXiv.org
Does Demand Response Increase Vulnerability to Cyber Attacks by Adversarial Data Modifications?
Does Demand Response Increase Vulnerability to Cyber Attacks by Adversarial Data Modifications?
cs.LG updates on arXiv.org
When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws
When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws
cs.LG updates on arXiv.org
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
cs.LG updates on arXiv.org
UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks
UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks
cs.LG updates on arXiv.org
At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics
At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics
cs.LG updates on arXiv.org
The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?
The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?
cs.LG updates on arXiv.org
The Approximation Ratio for the Risk of Myopic Bayesian Active Learning for Linear Regression
The Approximation Ratio for the Risk of Myopic Bayesian Active Learning for Linear Regression
cs.LG updates on arXiv.org
Diffusion enabled Optimal Transport distances for graph matching
Diffusion enabled Optimal Transport distances for graph matching
cs.LG updates on arXiv.org
Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories
Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories
cs.LG updates on arXiv.org
Entropy-Guided Tensor Compression for Multimodal Federated Learning on Edge Devices
Entropy-Guided Tensor Compression for Multimodal Federated Learning on Edge Devices
cs.LG updates on arXiv.org
From Jumps to Signatures: a Generative Method for Temporal Point Processes
From Jumps to Signatures: a Generative Method for Temporal Point Processes
cs.LG updates on arXiv.org
Dual Attention Heads for Personalized Federated Learning in ECG Classification
Dual Attention Heads for Personalized Federated Learning in ECG Classification
cs.LG updates on arXiv.org
Robust Human-AI Complementarity under Uncertainty
Robust Human-AI Complementarity under Uncertainty
cs.LG updates on arXiv.org
Trees from Marginals: Autoregressive drafting with factorized priors
Trees from Marginals: Autoregressive drafting with factorized priors
cs.LG updates on arXiv.org
Efficient Long-Horizon Learning for Learned Optimization
Efficient Long-Horizon Learning for Learned Optimization
cs.LG updates on arXiv.org
Efficient Bayesian Deep Ensembles via Analytic Predictive Inference
Efficient Bayesian Deep Ensembles via Analytic Predictive Inference
cs.LG updates on arXiv.org
On Explicit Super-Expressive Approximation for Neural Networks
On Explicit Super-Expressive Approximation for Neural Networks
cs.LG updates on arXiv.org
Enhancing deep learning models for time series classification via knowledge distillation
Enhancing deep learning models for time series classification via knowledge distillation
cs.LG updates on arXiv.org
What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study
What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study
cs.LG updates on arXiv.org
Generative Diffusion Models of Stochastic Graph Signals
Generative Diffusion Models of Stochastic Graph Signals
cs.LG updates on arXiv.org
LEMUR 2: Unlocking Neural Network Diversity for AI
LEMUR 2: Unlocking Neural Network Diversity for AI
cs.LG updates on arXiv.org
A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong
A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong
cs.LG updates on arXiv.org
Geometric Self-Distillation for Reasoning Generalization
Geometric Self-Distillation for Reasoning Generalization
cs.LG updates on arXiv.org
Best-Arm Identification with Generative Proxy
Best-Arm Identification with Generative Proxy
cs.LG updates on arXiv.org
Converge to Surprise: Evolutionary Self-supervised Image Clustering
Converge to Surprise: Evolutionary Self-supervised Image Clustering
cs.LG updates on arXiv.org
Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization
Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization
cs.LG updates on arXiv.org
Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource
Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource
cs.LG updates on arXiv.org
Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery
Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery
cs.LG updates on arXiv.org
Physical activities enable scalable foundation modelling for broad-spectrum health prediction
Physical activities enable scalable foundation modelling for broad-spectrum health prediction
cs.LG updates on arXiv.org
Rethinking Multimodal Time-Series Forecasting Evaluation
Rethinking Multimodal Time-Series Forecasting Evaluation
cs.LG updates on arXiv.org
Hybrid Least Squares/Gradient Descent Methods for MIONets
Hybrid Least Squares/Gradient Descent Methods for MIONets
cs.LG updates on arXiv.org
Robust Federated Learning Under Real-World Client Churn
Robust Federated Learning Under Real-World Client Churn
cs.LG updates on arXiv.org
UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma
UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma
cs.LG updates on arXiv.org
Physics-guided spatiotemporal neural models for fuel density prediction
Physics-guided spatiotemporal neural models for fuel density prediction
cs.LG updates on arXiv.org
Dissociating the Internal Representations of Sycophancy in LLMs
Dissociating the Internal Representations of Sycophancy in LLMs
cs.LG updates on arXiv.org
Multimodal Spatiotemporal-Frequency Fusion with Peak Enhancement for Cellular Traffic Forecasting
Multimodal Spatiotemporal-Frequency Fusion with Peak Enhancement for Cellular Traffic Forecasting
cs.LG updates on arXiv.org
Online Data Selection Is Implicit Alignment
Online Data Selection Is Implicit Alignment
cs.LG updates on arXiv.org
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
cs.LG updates on arXiv.org
Latent graph encoding of multimodal neuroimaging features with generative AI architectures
Latent graph encoding of multimodal neuroimaging features with generative AI architectures
cs.LG updates on arXiv.org
Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies
Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies
cs.LG updates on arXiv.org
Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
cs.LG updates on arXiv.org
Intrinsic Green's Learning: Supervised Learning on Manifolds via Inverse PDE
Intrinsic Green's Learning: Supervised Learning on Manifolds via Inverse PDE
cs.LG updates on arXiv.org
On the Principles of Deep Feedforward ReLU Networks
On the Principles of Deep Feedforward ReLU Networks
cs.LG updates on arXiv.org
Complexity-Budgeted, Interaction-Aware Interpretable Model for Tabular Data
Complexity-Budgeted, Interaction-Aware Interpretable Model for Tabular Data
cs.LG updates on arXiv.org
Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits
Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits
cs.LG updates on arXiv.org
An Hybrid Quantum-Classical Diffusion Model for Image Generation
An Hybrid Quantum-Classical Diffusion Model for Image Generation
cs.LG updates on arXiv.org
Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints
Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints
cs.LG updates on arXiv.org
A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving
A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving
cs.LG updates on arXiv.org
Distributed Sparse Interventions in Language Models
Distributed Sparse Interventions in Language Models
cs.LG updates on arXiv.org
Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference
Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference
cs.LG updates on arXiv.org
Prior-matched evaluation of operational Earth-observation classifiers: a three-number reporting method demonstrated on Sentinel-1 internal-wave detection
Prior-matched evaluation of operational Earth-observation classifiers: a three-number reporting method demonstrated on Sentinel-1 internal-wave detection
cs.LG updates on arXiv.org
Information Allocation Dynamics in Neural Network Optimization
Information Allocation Dynamics in Neural Network Optimization
cs.LG updates on arXiv.org
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
cs.LG updates on arXiv.org
Predicting LLM Safety Before Release by Simulating Deployment
Predicting LLM Safety Before Release by Simulating Deployment
cs.LG updates on arXiv.org
Geometric--Nongeometric Optimizer Calculus: A Modular Language for Reachable Gradient Methods
Geometric--Nongeometric Optimizer Calculus: A Modular Language for Reachable Gradient Methods
cs.LG updates on arXiv.org
HPG-Diff: Hierarchical physics-guided diffusion with differentiable connectivity constraints for topology optimization
HPG-Diff: Hierarchical physics-guided diffusion with differentiable connectivity constraints for topology optimization
cs.LG updates on arXiv.org
ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
cs.LG updates on arXiv.org
Safe Reinforcement Learning using Ideas from Model Predictive Control
Safe Reinforcement Learning using Ideas from Model Predictive Control
cs.LG updates on arXiv.org
FMMVCC: Fuzzy Mamba-based Multi-View Contrastive Clustering for Univariate Time Series
FMMVCC: Fuzzy Mamba-based Multi-View Contrastive Clustering for Univariate Time Series
cs.LG updates on arXiv.org
BubbleSH: A Dataset of Rising Bubbles with Deformable Interfaces
BubbleSH: A Dataset of Rising Bubbles with Deformable Interfaces
cs.LG updates on arXiv.org
FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation
FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation
cs.LG updates on arXiv.org
Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
cs.LG updates on arXiv.org
Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation
Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation
cs.LG updates on arXiv.org
Latency-Aware Bid Acceptance under Operational Feasibility: A Public Benchmark with Hindsight Ceilings
Latency-Aware Bid Acceptance under Operational Feasibility: A Public Benchmark with Hindsight Ceilings
cs.LG updates on arXiv.org
Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
cs.LG updates on arXiv.org
On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces
On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces
cs.LG updates on arXiv.org
Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector
Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector
cs.LG updates on arXiv.org
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
cs.LG updates on arXiv.org
The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought
The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought
cs.LG updates on arXiv.org
RLVP: Penalize the Path, Reward the Outcome
RLVP: Penalize the Path, Reward the Outcome
cs.LG updates on arXiv.org
Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data
Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data
cs.LG updates on arXiv.org
FourierQK: Spectral Preprocessing of Query-Key Projections Improves Transformer Attention
FourierQK: Spectral Preprocessing of Query-Key Projections Improves Transformer Attention
cs.LG updates on arXiv.org
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
cs.LG updates on arXiv.org
TimEE: End-to-end Time Series Classification via In-Context Learning
TimEE: End-to-end Time Series Classification via In-Context Learning
cs.LG updates on arXiv.org
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
cs.LG updates on arXiv.org
Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization
Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization
cs.LG updates on arXiv.org
Gradient-free Riemannian Langevin Sampler
Gradient-free Riemannian Langevin Sampler
cs.LG updates on arXiv.org
Avoiding unsafe sets when training with Langevin Dynamics
Avoiding unsafe sets when training with Langevin Dynamics
cs.LG updates on arXiv.org
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
cs.LG updates on arXiv.org
Multi-Class vs. Multi-Label BERT for CVE-to-CWE Mapping: How Taxonomy Structure Shapes the Errors
Multi-Class vs. Multi-Label BERT for CVE-to-CWE Mapping: How Taxonomy Structure Shapes the Errors
cs.LG updates on arXiv.org
Asymmetric Focal Loss Improves Graph Neural Network Prediction of Drug-Drug Interactions
Asymmetric Focal Loss Improves Graph Neural Network Prediction of Drug-Drug Interactions
cs.LG updates on arXiv.org
Higher-Order Geometric Updates for Levenberg-Marquardt Method via Riemann Normal Coordinates
Higher-Order Geometric Updates for Levenberg-Marquardt Method via Riemann Normal Coordinates
cs.LG updates on arXiv.org
An optimal control approach for neural network architecture adaptation with a posteriori error estimation
An optimal control approach for neural network architecture adaptation with a posteriori error estimation
cs.LG updates on arXiv.org
ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation
ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation
cs.LG updates on arXiv.org
Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance
Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance
cs.LG updates on arXiv.org
PeTeR: Post-Training Robustification of Probabilistic Circuits
PeTeR: Post-Training Robustification of Probabilistic Circuits
cs.LG updates on arXiv.org
Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems
Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems
cs.LG updates on arXiv.org
How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization
How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization
cs.LG updates on arXiv.org
Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization
Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization
cs.LG updates on arXiv.org
ECGLight: Compute-Light Framework For Paper ECG Digitization and Myocardial Infarction Screening
ECGLight: Compute-Light Framework For Paper ECG Digitization and Myocardial Infarction Screening
cs.LG updates on arXiv.org
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning
cs.LG updates on arXiv.org
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF
cs.LG updates on arXiv.org
The Key to Going Linear: Analysis-Driven Transformer Linearization
The Key to Going Linear: Analysis-Driven Transformer Linearization
cs.LG updates on arXiv.org
Towards a Pseudo-Labeling Workflow for Celltype-Classification from Explanted Brain Slice Recordings
Towards a Pseudo-Labeling Workflow for Celltype-Classification from Explanted Brain Slice Recordings
cs.LG updates on arXiv.org
Value of Information under Imprecise Probabilities: Decision-Rule-Specific Values and Fixed-Measure Envelopes on a Credal Set
Value of Information under Imprecise Probabilities: Decision-Rule-Specific Values and Fixed-Measure Envelopes on a Credal Set
cs.LG updates on arXiv.org
Recovering Candidate Circadian Regulators of Arrhythmic Pituitary Hormone Genes Using Reliability-Weighted Magnetic Laplacian with rwMagLap
Recovering Candidate Circadian Regulators of Arrhythmic Pituitary Hormone Genes Using Reliability-Weighted Magnetic Laplacian with rwMagLap
cs.LG updates on arXiv.org
Trajectory Inference of Human Aging from Cross-Sectional DNA Methylation Data
Trajectory Inference of Human Aging from Cross-Sectional DNA Methylation Data
cs.LG updates on arXiv.org
Pixel-Precise Explainable Stress Indexing: A Semantic Segmentation Framework for Disease Severity Quantification in Field Crops
Pixel-Precise Explainable Stress Indexing: A Semantic Segmentation Framework for Disease Severity Quantification in Field Crops
cs.LG updates on arXiv.org
AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis
AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis
cs.LG updates on arXiv.org
Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
cs.LG updates on arXiv.org
Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts
Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts
cs.LG updates on arXiv.org
Format-Controlled Multi-Scale JPEG Compression Response Analysis for Image-Level Forgery Screening
Format-Controlled Multi-Scale JPEG Compression Response Analysis for Image-Level Forgery Screening
cs.LG updates on arXiv.org
HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing
HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing
cs.LG updates on arXiv.org
Creating Power Distribution Network Layouts Using Generative Adversarial Networks and Image-Based Representations
Creating Power Distribution Network Layouts Using Generative Adversarial Networks and Image-Based Representations
cs.LG updates on arXiv.org
AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
cs.LG updates on arXiv.org
Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation
Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation
cs.LG updates on arXiv.org
Specification Grounding Drives Test Effectiveness for LLM Code
Specification Grounding Drives Test Effectiveness for LLM Code
cs.LG updates on arXiv.org
Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering
Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering
cs.LG updates on arXiv.org
The Power of Backdoor Absorption in Community Training
The Power of Backdoor Absorption in Community Training
cs.LG updates on arXiv.org
Fast determinantal sampling on general spaces and diffusion geometry
Fast determinantal sampling on general spaces and diffusion geometry
cs.LG updates on arXiv.org
ORAN-DEFEND: Subspace Detection and Sanitization of Backdoor DRL xApps in Open RAN
ORAN-DEFEND: Subspace Detection and Sanitization of Backdoor DRL xApps in Open RAN
cs.LG updates on arXiv.org
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
cs.LG updates on arXiv.org
Pelican-VLA 0.5: Attending Before Acting Benefits Generalization
Pelican-VLA 0.5: Attending Before Acting Benefits Generalization
cs.LG updates on arXiv.org
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
cs.LG updates on arXiv.org
SPEAR: A Simulator for Photorealistic Embodied AI Research
SPEAR: A Simulator for Photorealistic Embodied AI Research
cs.LG updates on arXiv.org
Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review
Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review
cs.LG updates on arXiv.org
Macroeconomic Message Passing for Anticipating Foreign Exchange Regime Changes: A Deep Logical Learning Approach using Graph Tsetlin Machines
Macroeconomic Message Passing for Anticipating Foreign Exchange Regime Changes: A Deep Logical Learning Approach using Graph Tsetlin Machines
cs.LG updates on arXiv.org
Optimization Geometrodynamics: A Framework for Dynamic Geometric Optimization
Optimization Geometrodynamics: A Framework for Dynamic Geometric Optimization
cs.LG updates on arXiv.org
Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video
Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video
cs.LG updates on arXiv.org
AirPASS: Over-the-Air Federated Learning via Pinching Antenna Systems
AirPASS: Over-the-Air Federated Learning via Pinching Antenna Systems
cs.LG updates on arXiv.org
Ad Headline Generation using Self-Critical Masked Language Model
Ad Headline Generation using Self-Critical Masked Language Model
cs.LG updates on arXiv.org
CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts
CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts
cs.LG updates on arXiv.org
Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
cs.LG updates on arXiv.org
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
cs.LG updates on arXiv.org
Gen4U: Unifying Video Generation and Understanding via Diffusion
Gen4U: Unifying Video Generation and Understanding via Diffusion
cs.LG updates on arXiv.org
Video2Reaction: Mapping Video to Audience Reaction Distribution in the Wild
Video2Reaction: Mapping Video to Audience Reaction Distribution in the Wild
cs.LG updates on arXiv.org
Finding a stationary point of a stochastic convex problem
Finding a stationary point of a stochastic convex problem
cs.LG updates on arXiv.org
Computing with Stochastic Oracles in AI-Augmented Computation
Computing with Stochastic Oracles in AI-Augmented Computation
cs.LG updates on arXiv.org
Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware
Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware
cs.LG updates on arXiv.org
LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models
LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models
cs.LG updates on arXiv.org
Compass: Prostate Cancer Detection Needs Multi-View Context
Compass: Prostate Cancer Detection Needs Multi-View Context
cs.LG updates on arXiv.org
Mathematical methods of reinforcement learning
Mathematical methods of reinforcement learning
cs.LG updates on arXiv.org
Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation
Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation
cs.LG updates on arXiv.org
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
cs.LG updates on arXiv.org
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
cs.LG updates on arXiv.org
Tensorized algorithms and scalable filtering methods for hidden Markov and factorial hidden Markov models
Tensorized algorithms and scalable filtering methods for hidden Markov and factorial hidden Markov models
cs.LG updates on arXiv.org
Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation
Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation
cs.LG updates on arXiv.org
Prior-aware and Context-guided Group Sampling for Active Probabilistic Subsampling
Prior-aware and Context-guided Group Sampling for Active Probabilistic Subsampling
cs.LG updates on arXiv.org
Is Randomness Necessary for Adaptive Data Analysis?
Is Randomness Necessary for Adaptive Data Analysis?
cs.LG updates on arXiv.org
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
cs.LG updates on arXiv.org
Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering
Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering
cs.LG updates on arXiv.org
Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators
Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators
cs.LG updates on arXiv.org
Restricted Dynamic Geometric Complexity: Certificates for Structured Preconditioning
Restricted Dynamic Geometric Complexity: Certificates for Structured Preconditioning
cs.LG updates on arXiv.org
Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe
Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe
cs.LG updates on arXiv.org
Vision Foundation Models in Radiology: A Scoping Review of Data, Methodology, Evaluation and Clinical Translation
Vision Foundation Models in Radiology: A Scoping Review of Data, Methodology, Evaluation and Clinical Translation
cs.LG updates on arXiv.org
DiPhon: Diffusion on Graphons for Scalable Graph Generation
DiPhon: Diffusion on Graphons for Scalable Graph Generation
cs.LG updates on arXiv.org
Bayesian Optimization of Genetic Algorithm Hyperparameters in a Multi-Fidelity Framework for Efficient Lattice Material Design
Bayesian Optimization of Genetic Algorithm Hyperparameters in a Multi-Fidelity Framework for Efficient Lattice Material Design
cs.LG updates on arXiv.org
R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement
R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement
cs.LG updates on arXiv.org
Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report
Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report
cs.LG updates on arXiv.org
Physics-Audited Agentic Discovery in Scientific Machine Learning
Physics-Audited Agentic Discovery in Scientific Machine Learning
cs.LG updates on arXiv.org
TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models
TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models
cs.LG updates on arXiv.org
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
cs.LG updates on arXiv.org
Heterogeneity-Adaptive Diffusion Schrodinger Bridge for PET-Guided Whole-Body MRI Translation
Heterogeneity-Adaptive Diffusion Schrodinger Bridge for PET-Guided Whole-Body MRI Translation
cs.LG updates on arXiv.org
Reliable mechanistic operator recovery with biologically-informed neural networks: principles for architecture and optimisation design
Reliable mechanistic operator recovery with biologically-informed neural networks: principles for architecture and optimisation design
cs.LG updates on arXiv.org
Statistical inverse learning and $\ell^1$-regularization
Statistical inverse learning and $\ell^1$-regularization
cs.LG updates on arXiv.org
GIFT: Geometry-Informed Low-precision Gradient Communication for LLM Pretraining
GIFT: Geometry-Informed Low-precision Gradient Communication for LLM Pretraining
cs.LG updates on arXiv.org
Stability of Flow Models for Graph Signals
Stability of Flow Models for Graph Signals
cs.LG updates on arXiv.org
A Unified Detection Framework for AI-Related Content and Artifacts
A Unified Detection Framework for AI-Related Content and Artifacts
cs.LG updates on arXiv.org
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
cs.LG updates on arXiv.org
Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale
Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale
cs.LG updates on arXiv.org
MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models
MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models
cs.LG updates on arXiv.org
Any-Dimensional Learning by Sampling
Any-Dimensional Learning by Sampling
cs.LG updates on arXiv.org
Co-LMLM: Continuous-Query Limited Memory Language Models
Co-LMLM: Continuous-Query Limited Memory Language Models
cs.LG updates on arXiv.org
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
cs.LG updates on arXiv.org
Adversarial Rademacher Complexity of Deep Neural Networks
Adversarial Rademacher Complexity of Deep Neural Networks
cs.LG updates on arXiv.org
InferNet: Exploiting Aggregate GPU Profiles as Side-Channel for DNN Architecture Inference
InferNet: Exploiting Aggregate GPU Profiles as Side-Channel for DNN Architecture Inference
cs.LG updates on arXiv.org
Reinforcement Federated Learning Method Based on Adaptive OPTICS Clustering
Reinforcement Federated Learning Method Based on Adaptive OPTICS Clustering
cs.LG updates on arXiv.org
A Distributionally Robust Optimisation Approach to Fair Credit Scoring
A Distributionally Robust Optimisation Approach to Fair Credit Scoring
cs.LG updates on arXiv.org
Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty
Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty
cs.LG updates on arXiv.org
Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees
Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees
cs.LG updates on arXiv.org
How Learning Dynamics Drive Adversarially Robust Generalization?
How Learning Dynamics Drive Adversarially Robust Generalization?
cs.LG updates on arXiv.org
ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts
ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts
cs.LG updates on arXiv.org
Network Dynamics-Based Framework for Understanding Deep Neural Networks
Network Dynamics-Based Framework for Understanding Deep Neural Networks
cs.LG updates on arXiv.org
The Minimal Search Space for Conditional Causal Bandits
The Minimal Search Space for Conditional Causal Bandits
cs.LG updates on arXiv.org
PB-OEL: A Performance-Bounded Online Ensemble Learning Framework With Mixed Feedback for Real-Time Safety Assessment
PB-OEL: A Performance-Bounded Online Ensemble Learning Framework With Mixed Feedback for Real-Time Safety Assessment
cs.LG updates on arXiv.org
Bifidelity Parameter Estimation Using Conditional Diffusion Models
Bifidelity Parameter Estimation Using Conditional Diffusion Models
cs.LG updates on arXiv.org
Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming
Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming
cs.LG updates on arXiv.org
Protocol Models: Scaling Decentralized Training with Communication-Efficient Model Parallelism
Protocol Models: Scaling Decentralized Training with Communication-Efficient Model Parallelism
cs.LG updates on arXiv.org
FPTQuant: Function-Preserving Transforms for LLM Quantization
FPTQuant: Function-Preserving Transforms for LLM Quantization
cs.LG updates on arXiv.org
Understanding Two-Layer Neural Networks with Smooth Activation Functions
Understanding Two-Layer Neural Networks with Smooth Activation Functions
cs.LG updates on arXiv.org
L-GTA: Latent Generative Modeling for Time Series Augmentation
L-GTA: Latent Generative Modeling for Time Series Augmentation
cs.LG updates on arXiv.org
Activation Quantization of Vision Encoders Needs Prefixing Registers
Activation Quantization of Vision Encoders Needs Prefixing Registers
cs.LG updates on arXiv.org
Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors
Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors
cs.LG updates on arXiv.org
What's on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scale
What's on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scale
cs.LG updates on arXiv.org
Distributed Dynamic Associative Memory via Online Convex Optimization
Distributed Dynamic Associative Memory via Online Convex Optimization
cs.LG updates on arXiv.org
FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning
FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning
cs.LG updates on arXiv.org
Attention in Geometry: Scalable Spatial Modeling via Adaptive Density Fields and FAISS-Accelerated Kernels
Attention in Geometry: Scalable Spatial Modeling via Adaptive Density Fields and FAISS-Accelerated Kernels
cs.LG updates on arXiv.org
ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits
ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits
cs.LG updates on arXiv.org
Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation
Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation
cs.LG updates on arXiv.org
Parametric and Generative Forecasts of EPEX Day\char45 Ahead Energy Market Curves
Parametric and Generative Forecasts of EPEX Day\char45 Ahead Energy Market Curves
cs.LG updates on arXiv.org
Synthetic Time Series Generation via Complex Networks
Synthetic Time Series Generation via Complex Networks
cs.LG updates on arXiv.org
Towards Understanding Steering Strength
Towards Understanding Steering Strength
cs.LG updates on arXiv.org
DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce
DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce
cs.LG updates on arXiv.org
Predicting integers from continuous parameters
Predicting integers from continuous parameters
cs.LG updates on arXiv.org
Can We Really Learn One Representation to Optimize All Rewards?
Can We Really Learn One Representation to Optimize All Rewards?
cs.LG updates on arXiv.org
The Appeal and Reality of Recycling LoRAs with Adaptive Merging
The Appeal and Reality of Recycling LoRAs with Adaptive Merging
cs.LG updates on arXiv.org
Bound to Disagree: Generalization Bounds via Certifiable Surrogates
Bound to Disagree: Generalization Bounds via Certifiable Surrogates
cs.LG updates on arXiv.org
Decentralized Federated Learning by Partial Message Exchange
Decentralized Federated Learning by Partial Message Exchange
cs.LG updates on arXiv.org
Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation
Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation
cs.LG updates on arXiv.org
Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathways
Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathways
cs.LG updates on arXiv.org
Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization
Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization
cs.LG updates on arXiv.org
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
cs.LG updates on arXiv.org
Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation
Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation
cs.LG updates on arXiv.org
Nectar: Neural Estimation of Cached-Token Attention via Regression
Nectar: Neural Estimation of Cached-Token Attention via Regression
cs.LG updates on arXiv.org
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
cs.LG updates on arXiv.org
SNLP: Layer-Parallel Inference via Structured Newton Corrections
SNLP: Layer-Parallel Inference via Structured Newton Corrections
cs.LG updates on arXiv.org
A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning
A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning
cs.LG updates on arXiv.org
Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
cs.LG updates on arXiv.org
CogAdapt: Adapting Clinical ECG Foundation Models for Wearable Cognitive Load Assessment
CogAdapt: Adapting Clinical ECG Foundation Models for Wearable Cognitive Load Assessment
cs.LG updates on arXiv.org
Momentum Based Reward Design for Low Emission Traffic Signal Control
Momentum Based Reward Design for Low Emission Traffic Signal Control
cs.LG updates on arXiv.org
Trading Human Curation for Synthetic Augmentation in RLVR
Trading Human Curation for Synthetic Augmentation in RLVR
cs.LG updates on arXiv.org
Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation
Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation
cs.LG updates on arXiv.org
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination
cs.LG updates on arXiv.org
The Signs Were Always There: Training-Free Concept Detection and Steering in Raw Transformer Dimensions
The Signs Were Always There: Training-Free Concept Detection and Steering in Raw Transformer Dimensions
cs.LG updates on arXiv.org
A Novel Approach to Temporal QoS Estimation via Extended Kalman Filter-Incorporated Latent Feature Analysis
A Novel Approach to Temporal QoS Estimation via Extended Kalman Filter-Incorporated Latent Feature Analysis
cs.LG updates on arXiv.org
Research on Domain Information Mining and Theme Evolution of Scientific Papers
Research on Domain Information Mining and Theme Evolution of Scientific Papers
cs.LG updates on arXiv.org
From system models to class models: An in-context learning paradigm
From system models to class models: An in-context learning paradigm
cs.LG updates on arXiv.org
Deep Operator BSDE: a Numerical Scheme to Approximate Solution Operators
Deep Operator BSDE: a Numerical Scheme to Approximate Solution Operators
cs.LG updates on arXiv.org
Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer
Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer
cs.LG updates on arXiv.org
Optimal Conformal Prediction under Epistemic Uncertainty
Optimal Conformal Prediction under Epistemic Uncertainty
cs.LG updates on arXiv.org
Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Models
Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Models
cs.LG updates on arXiv.org
Fast segmentation of watermarked texts from large language models through an epidemic change-point framework
Fast segmentation of watermarked texts from large language models through an epidemic change-point framework
cs.LG updates on arXiv.org
LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
cs.LG updates on arXiv.org
Diffusion Models in Simulation-Based Inference: A Tutorial Review
Diffusion Models in Simulation-Based Inference: A Tutorial Review
cs.LG updates on arXiv.org
Approximate full conformal prediction in an RKHS
Approximate full conformal prediction in an RKHS
cs.LG updates on arXiv.org
Spatiotemporal Semantic V2X Framework for Cooperative Collision Prediction
Spatiotemporal Semantic V2X Framework for Cooperative Collision Prediction
cs.LG updates on arXiv.org
SOMtime the World Ain$'$t Fair: Violating Fairness Using Self-Organizing Maps
SOMtime the World Ain$'$t Fair: Violating Fairness Using Self-Organizing Maps
cs.LG updates on arXiv.org
Scaling Quantum Machine Learning without Tricks: Full-Resolution and Diverse Image Generation
Scaling Quantum Machine Learning without Tricks: Full-Resolution and Diverse Image Generation
cs.LG updates on arXiv.org
Latent Policy Steering through One-Step Flow Policies
Latent Policy Steering through One-Step Flow Policies
cs.LG updates on arXiv.org
Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows
Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows
cs.LG updates on arXiv.org
Optimization-Embedded Active Multi-Fidelity Surrogate Learning for Multi-Condition Airfoil Shape Optimization
Optimization-Embedded Active Multi-Fidelity Surrogate Learning for Multi-Condition Airfoil Shape Optimization
cs.LG updates on arXiv.org
Object Search in Partially-Known Environments via LLM-informed Model-based Planning and Prompt Selection
Object Search in Partially-Known Environments via LLM-informed Model-based Planning and Prompt Selection
cs.LG updates on arXiv.org
Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks
Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks
cs.LG updates on arXiv.org
Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
cs.LG updates on arXiv.org
VTC: DNN Compilation with Virtual Tensors for Data Movement Elimination
VTC: DNN Compilation with Virtual Tensors for Data Movement Elimination
cs.LG updates on arXiv.org
ML-based approach to classification and generation of structured light propagation in turbulent media
ML-based approach to classification and generation of structured light propagation in turbulent media
cs.LG updates on arXiv.org
M$^3$: Reframing Training Measures for Discretized Physical Simulations
M$^3$: Reframing Training Measures for Discretized Physical Simulations
cs.LG updates on arXiv.org
MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection
MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection
cs.LG updates on arXiv.org
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
cs.LG updates on arXiv.org
Unveiling the Visual Counting Bottleneck in Vision-Language Models
Unveiling the Visual Counting Bottleneck in Vision-Language Models
cs.LG updates on arXiv.org
Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures
Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures
cs.LG updates on arXiv.org
TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation
TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation
cs.LG updates on arXiv.org
DYNA-PRUNER: Input-Adaptive Data-Model Co-Pruning for Efficient and Scalable Spatio-Temporal Media Prediction
DYNA-PRUNER: Input-Adaptive Data-Model Co-Pruning for Efficient and Scalable Spatio-Temporal Media Prediction
cs.LG updates on arXiv.org
MTEB-BR: A Text Embedding Benchmark for Brazilian Portuguese
MTEB-BR: A Text Embedding Benchmark for Brazilian Portuguese
stat.ML updates on arXiv.org
Value of Information under Imprecise Probabilities: Decision-Rule-Specific Values and Fixed-Measure Envelopes on a Credal Set
Value of Information under Imprecise Probabilities: Decision-Rule-Specific Values and Fixed-Measure Envelopes on a Credal Set
stat.ML updates on arXiv.org
Fast determinantal sampling on general spaces and diffusion geometry
Fast determinantal sampling on general spaces and diffusion geometry
stat.ML updates on arXiv.org
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
stat.ML updates on arXiv.org
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
stat.ML updates on arXiv.org
Finding a stationary point of a stochastic convex problem
Finding a stationary point of a stochastic convex problem
stat.ML updates on arXiv.org
Tensorized algorithms and scalable filtering methods for hidden Markov and factorial hidden Markov models
Tensorized algorithms and scalable filtering methods for hidden Markov and factorial hidden Markov models
stat.ML updates on arXiv.org
DiPhon: Diffusion on Graphons for Scalable Graph Generation
DiPhon: Diffusion on Graphons for Scalable Graph Generation
stat.ML updates on arXiv.org
Statistical inverse learning and $\ell^1$-regularization
Statistical inverse learning and $\ell^1$-regularization
stat.ML updates on arXiv.org
A Unified Detection Framework for AI-Related Content and Artifacts
A Unified Detection Framework for AI-Related Content and Artifacts
stat.ML updates on arXiv.org
A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It
A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It
stat.ML updates on arXiv.org
From Jumps to Signatures: a Generative Method for Temporal Point Processes
From Jumps to Signatures: a Generative Method for Temporal Point Processes
stat.ML updates on arXiv.org
Best-Arm Identification with Generative Proxy
Best-Arm Identification with Generative Proxy
stat.ML updates on arXiv.org
Transfer Learning for Linear Discriminant Analysis with a Shared Classification Signal
Transfer Learning for Linear Discriminant Analysis with a Shared Classification Signal
stat.ML updates on arXiv.org
Local large deviations for linear-region growth in random piecewise-linear networks
Local large deviations for linear-region growth in random piecewise-linear networks
stat.ML updates on arXiv.org
Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
stat.ML updates on arXiv.org
The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought
The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought
stat.ML updates on arXiv.org
Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization
Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization
stat.ML updates on arXiv.org
Avoiding unsafe sets when training with Langevin Dynamics
Avoiding unsafe sets when training with Langevin Dynamics
stat.ML updates on arXiv.org
Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer
Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer
stat.ML updates on arXiv.org
Optimal Conformal Prediction under Epistemic Uncertainty
Optimal Conformal Prediction under Epistemic Uncertainty
stat.ML updates on arXiv.org
Fast segmentation of watermarked texts from large language models through an epidemic change-point framework
Fast segmentation of watermarked texts from large language models through an epidemic change-point framework
stat.ML updates on arXiv.org
Diffusion Models in Simulation-Based Inference: A Tutorial Review
Diffusion Models in Simulation-Based Inference: A Tutorial Review
stat.ML updates on arXiv.org
Approximate full conformal prediction in an RKHS
Approximate full conformal prediction in an RKHS
stat.ML updates on arXiv.org
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
stat.ML updates on arXiv.org
Network Dynamics-Based Framework for Understanding Deep Neural Networks
Network Dynamics-Based Framework for Understanding Deep Neural Networks
stat.ML updates on arXiv.org
The Minimal Search Space for Conditional Causal Bandits
The Minimal Search Space for Conditional Causal Bandits
stat.ML updates on arXiv.org
High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks
High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks
stat.ML updates on arXiv.org
Spectral Diffusion Models on the Sphere
Spectral Diffusion Models on the Sphere
stat.ML updates on arXiv.org
Sharp Inequalities between Total Variation and Hellinger Distances for Gaussian Mixtures
Sharp Inequalities between Total Variation and Hellinger Distances for Gaussian Mixtures
stat.ML updates on arXiv.org
Gaussian mixtures and non-parametric likelihoods through the lens of statistical mechanics
Gaussian mixtures and non-parametric likelihoods through the lens of statistical mechanics
stat.ML updates on arXiv.org
Causal Inference with Categorical Unobserved Confounder via Mixture Learning
Causal Inference with Categorical Unobserved Confounder via Mixture Learning
stat.ML updates on arXiv.org
Optimal score function estimation via derivatives constraints
Optimal score function estimation via derivatives constraints
stat.ML updates on arXiv.org
Doubly cross-fit debiased machine learning of heterogeneous treatment effects under principal stratification
Doubly cross-fit debiased machine learning of heterogeneous treatment effects under principal stratification
＠IT 全フォーラム 最新記事一覧
「ドキュメント？ ないよ」「レガシーシステム保守でキャリア詰む」悲しい情シスの実態
「ドキュメント？ ないよ」「レガシーシステム保守でキャリア詰む」悲しい情シスの実態
＠IT 全フォーラム 最新記事一覧
社内のWindows環境で「数百のAIエージェント」を隔離実行 NVIDIAとMicrosoftが共同開発したデスクサイドマシンの全容
社内のWindows環境で「数百のAIエージェント」を隔離実行 NVIDIAとMicrosoftが共同開発したデスクサイドマシンの全容
＠IT 全フォーラム 最新記事一覧
ネットワーク分離の悩ましい“データ受け渡し問題”をゼロトラストで解消 公立校はどう実現？
ネットワーク分離の悩ましい“データ受け渡し問題”をゼロトラストで解消 公立校はどう実現？
ITmedia NEWS 最新記事一覧
首相官邸、“本物そっくり”の偽サイト出現で注意喚起 正しいURLか「アクセスする前に確認を」
首相官邸、“本物そっくり”の偽サイト出現で注意喚起 正しいURLか「アクセスする前に確認を」
ITmedia NEWS 最新記事一覧
破産した「全東信」 最大債権者は近畿産業信組の219億円 地銀やノンバンクにも影響大
破産した「全東信」 最大債権者は近畿産業信組の219億円 地銀やノンバンクにも影響大
ITmedia NEWS 最新記事一覧
1.2万人削減のパナソニックの反転 痛み伴う改革からの成長戦略 旗印は「松下幸之助」
1.2万人削減のパナソニックの反転 痛み伴う改革からの成長戦略 旗印は「松下幸之助」
機械学習タグが付けられた新着記事 - Qiita
【技術解説】量子投資 アルゴリズム Pythonでセンチメント分析を活用した投資戦略の構築
【技術解説】量子投資 アルゴリズム Pythonでセンチメント分析を活用した投資戦略の構築
ITmedia NEWS 最新記事一覧
クールジャパンの失敗は生かされず？ 経産省肝いりで始まった後釜施策「IP360」の“光と影”
クールジャパンの失敗は生かされず？ 経産省肝いりで始まった後釜施策「IP360」の“光と影”
ITmedia NEWS 最新記事一覧
DuckDuckGoブラウザ、YouTube広告ブロック機能を追加──uBlock Originのフィルタ活用
DuckDuckGoブラウザ、YouTube広告ブロック機能を追加──uBlock Originのフィルタ活用
ITmedia NEWS 最新記事一覧
暑さ対策：トイレの電球を“ファン付きLEDライト”に交換したら想像以上に快適になった
暑さ対策：トイレの電球を“ファン付きLEDライト”に交換したら想像以上に快適になった
Zennの「大規模言語モデル」のフィード
GPT-Rosalind入門 — 創薬・ゲノム研究に特化したOpenAI初の生命科学AIの全貌
GPT-Rosalind入門 — 創薬・ゲノム研究に特化したOpenAI初の生命科学AIの全貌
MarkTechPost
Robbyant Releases LingBot-VLA 2.0: An Open-Source 6B Vision-Language-Action (VLA) Model for Cross-Embodiment Robot Manipulation
Robbyant Releases LingBot-VLA 2.0: An Open-Source 6B Vision-Language-Action (VLA) Model for Cross-Embodiment Robot Manipulation
Zennの「大規模言語モデル」のフィード
自律AIエージェントにptufでガードレールを付けた——遮断からwarn-onlyへ
自律AIエージェントにptufでガードレールを付けた——遮断からwarn-onlyへ
Zennの「大規模言語モデル」のフィード
Claude Sonnet 5、単価据え置きでも新トークナイザで請求が約3割増える
Claude Sonnet 5、単価据え置きでも新トークナイザで請求が約3割増える
機械学習タグが付けられた新着記事 - Qiita
Zindi「A Step Ahead of Drought」の実装を組み直した話 ― TWS予測でベースラインから一歩抜けるために考えたこと
Zindi「A Step Ahead of Drought」の実装を組み直した話 ― TWS予測でベースラインから一歩抜けるために考えたこと
MarkTechPost
SpaceXAI Releases Grok 4.5, a Cursor-Trained Model for Coding, Agentic Tasks, and Knowledge Work at $2/M Input
SpaceXAI Releases Grok 4.5, a Cursor-Trained Model for Coding, Agentic Tasks, and Knowledge Work at $2/M Input
WIRED
One of Meta’s Offices Was Briefly Overtaken by a Rogue Squirrel
One of Meta’s Offices Was Briefly Overtaken by a Rogue Squirrel
Latent.Space
Why AI Infrastructure must evolve for Agent Experience — Akshat Bubna, Modal CTO
Why AI Infrastructure must evolve for Agent Experience — Akshat Bubna, Modal CTO
AI News & Artificial Intelligence | TechCrunch
Lovable reportedly in talks to double its valuation to $13.2B
Lovable reportedly in talks to double its valuation to $13.2B