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
TurboServe: Serving Streaming Video Generation Efficiently and Economically
TurboServe: Serving Streaming Video Generation Efficiently and Economically
Hugging Face Papers
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
Hugging Face Papers
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
Hugging Face Papers
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
Hugging Face Papers
Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning
Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning
Hugging Face Papers
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Hugging Face Papers
CausalMix: Data Mixture as Causal Inference for Language Model Training
CausalMix: Data Mixture as Causal Inference for Language Model Training
Hugging Face Papers
ASPIRE: Agentic /Skills Discovery for Robotics
ASPIRE: Agentic /Skills Discovery for Robotics
Hugging Face Papers
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
Hugging Face Papers
BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
Hugging Face Papers
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Hugging Face Papers
The State-Prediction Separation Hypothesis
The State-Prediction Separation Hypothesis
Hugging Face Papers
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
Hugging Face Papers
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Hugging Face Papers
Autonomous Scientific Discovery via Iterative Meta-Reflection
Autonomous Scientific Discovery via Iterative Meta-Reflection
Hugging Face Papers
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
Hugging Face Papers
AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation
AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation
Hugging Face Papers
NoPA: Non-Parametric Online 3D Scene Graph Generation
NoPA: Non-Parametric Online 3D Scene Graph Generation
#AIタグ
FigmaのデザインをMCP経由でClaude Codeに読み込ませWordPress化してShifterに移行した話
FigmaのデザインをMCP経由でClaude Codeに読み込ませWordPress化してShifterに移行した話
#LLMタグ
低スペックPCでも35BクラスのAIモデルが動く！ Modal＋Ollama完全セットアップガイド
低スペックPCでも35BクラスのAIモデルが動く！ Modal＋Ollama完全セットアップガイド
#AIタグ
低スペックPCでも35BクラスのAIモデルが動く！ Modal＋Ollama完全セットアップガイド
低スペックPCでも35BクラスのAIモデルが動く！ Modal＋Ollama完全セットアップガイド
#AIタグ
「教員だから仕方ない」を変えたい。学校DXラボを始めます｜AI・Google Workspace・GAS・iPadで働き方をDX
「教員だから仕方ない」を変えたい。学校DXラボを始めます｜AI・Google Workspace・GAS・iPadで働き方をDX
#AIタグ
【2026年上半期トレンド】Z世代・α世代が選ぶ「バズったもの」から見えた、令和の”新常識”とは？
【2026年上半期トレンド】Z世代・α世代が選ぶ「バズったもの」から見えた、令和の”新常識”とは？
LLMタグが付けられた新着記事 - Qiita
次世代自律型AIエージェント「Manus」完全ガイド：特徴から活用事例、学習リソースまで徹底解説
次世代自律型AIエージェント「Manus」完全ガイド：特徴から活用事例、学習リソースまで徹底解説
LLMタグが付けられた新着記事 - Qiita
ChatGPTは競合を推薦していた。AIの"本音"を自動で暴くGEO診断ツールを作った
ChatGPTは競合を推薦していた。AIの"本音"を自動で暴くGEO診断ツールを作った
#AIタグ
AI時代に"替えられない人"になる3条件｜Meta 8,000人削減の裏で何が起きているのか‼️
AI時代に"替えられない人"になる3条件｜Meta 8,000人削減の裏で何が起きているのか‼️
#AIタグ
AIは、できないから安全なのではない。Fable5再開と"サンドイッチメール"事件で考える、牧歌的AI時代の終わり
AIは、できないから安全なのではない。Fable5再開と"サンドイッチメール"事件で考える、牧歌的AI時代の終わり
#LLMタグ
Claude Fable 5が復活｜無料は7月7日まで。7月8日から別料金へ——変更点と「枠が減る理由」を徹底解説
Claude Fable 5が復活｜無料は7月7日まで。7月8日から別料金へ——変更点と「枠が減る理由」を徹底解説
機械学習タグが付けられた新着記事 - Qiita
【深層学習の数学】交差エントロピーとKLダイバージェンス：Loss関数の正体を暴く（直感でわかる確率・情報量 #2）
【深層学習の数学】交差エントロピーとKLダイバージェンス：Loss関数の正体を暴く（直感でわかる確率・情報量 #2）
LLMタグが付けられた新着記事 - Qiita
【AIエージェント】Claude Code vs Antigravity CLI！一晩で200ドル溶かさないための「自律ループ制御」超入門（第7回）水泳
【AIエージェント】Claude Code vs Antigravity CLI！一晩で200ドル溶かさないための「自律ループ制御」超入門（第7回）水泳
Latent.Space
AIEWF Daily Dispatch: Autoresearch and the tension between AI and human agency
AIEWF Daily Dispatch: Autoresearch and the tension between AI and human agency
AI News & Artificial Intelligence | TechCrunch
Indian tech tycoon bets $30M of his own money to build AI alternative to Microsoft Office
Indian tech tycoon bets $30M of his own money to build AI alternative to Microsoft Office
WIRED
Walmart Promo Codes: Up to 65% Off for July 2026
Walmart Promo Codes: Up to 65% Off for July 2026
Zennの「大規模言語モデル」のフィード
AI彼女アプリを作っていて気付いた。覚えているAIより、覚えようとするAIの方が大事だった
AI彼女アプリを作っていて気付いた。覚えているAIより、覚えようとするAIの方が大事だった
機械学習タグが付けられた新着記事 - Qiita
AIは欠陥に気づくのに直さない、OpenAIのGeneBench-Proが測る溝
AIは欠陥に気づくのに直さない、OpenAIのGeneBench-Proが測る溝
#LLMタグ
AIエージェントは「黙って」あなたを説得できる—非対話型信念操作の実力と、企業が今すぐ導入すべきリスク評価枠組み
AIエージェントは「黙って」あなたを説得できる—非対話型信念操作の実力と、企業が今すぐ導入すべきリスク評価枠組み
#LLMタグ
タイピングの「乱れ」が認知負荷を語る—キーストローク動態でLLMツールの「使いにくさ」を可視化する
タイピングの「乱れ」が認知負荷を語る—キーストローク動態でLLMツールの「使いにくさ」を可視化する
＠IT 全フォーラム 最新記事一覧
KDDIの最大1422万件の情報漏えい事件 その裏には陸自USB問題と同様に中国の影？
KDDIの最大1422万件の情報漏えい事件 その裏には陸自USB問題と同様に中国の影？
cs.LG updates on arXiv.org
Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
cs.LG updates on arXiv.org
SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling
SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling
cs.LG updates on arXiv.org
SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification
SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification
cs.LG updates on arXiv.org
A Filtered Mixture-of-Generators for Fully Synthetic Survival Training
A Filtered Mixture-of-Generators for Fully Synthetic Survival Training
cs.LG updates on arXiv.org
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
cs.LG updates on arXiv.org
EVOTS: Evolutionary Transformer Search for Time Series Forecasting
EVOTS: Evolutionary Transformer Search for Time Series Forecasting
cs.LG updates on arXiv.org
FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts
FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts
cs.LG updates on arXiv.org
Verifiable Rewards for Calibrated Probabilistic Forecasting
Verifiable Rewards for Calibrated Probabilistic Forecasting
cs.LG updates on arXiv.org
TallyTrain: Communication-Efficient Federated Distillation
TallyTrain: Communication-Efficient Federated Distillation
cs.LG updates on arXiv.org
Play Like Champions: Counterfactual Feedback Generation in Latent Space
Play Like Champions: Counterfactual Feedback Generation in Latent Space
cs.LG updates on arXiv.org
TRIE: An Evaluation Framework for Stochastic PDE Surrogates
TRIE: An Evaluation Framework for Stochastic PDE Surrogates
cs.LG updates on arXiv.org
StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting
StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting
cs.LG updates on arXiv.org
Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input Layouts
Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input Layouts
cs.LG updates on arXiv.org
Distributionally Robust Linear Regression With Block Lewis Weights
Distributionally Robust Linear Regression With Block Lewis Weights
cs.LG updates on arXiv.org
Learning dynamical systems from noisy data with Weak-form Kernel Ridge Regression
Learning dynamical systems from noisy data with Weak-form Kernel Ridge Regression
cs.LG updates on arXiv.org
Validating Causal Abstraction Metrics on Simulated Complex Systems
Validating Causal Abstraction Metrics on Simulated Complex Systems
cs.LG updates on arXiv.org
Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning
Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning
cs.LG updates on arXiv.org
Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds
Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds
cs.LG updates on arXiv.org
Understanding Guest Preferences and Optimizing Two-sided Marketplaces: Airbnb as an Example
Understanding Guest Preferences and Optimizing Two-sided Marketplaces: Airbnb as an Example
cs.LG updates on arXiv.org
EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems
EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems
cs.LG updates on arXiv.org
Generative Modeling of Quantum Distribution with Functional Flow Matching
Generative Modeling of Quantum Distribution with Functional Flow Matching
cs.LG updates on arXiv.org
Mapping the Evaluation Frontier: An Empirical Survey of the Bias-Reliability Tradeoff Across Eleven Evaluator-Agent Conditions
Mapping the Evaluation Frontier: An Empirical Survey of the Bias-Reliability Tradeoff Across Eleven Evaluator-Agent Conditions
cs.LG updates on arXiv.org
Watermarking for Proprietary Dataset Protection
Watermarking for Proprietary Dataset Protection
cs.LG updates on arXiv.org
K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks
K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks
cs.LG updates on arXiv.org
PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition
PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition
cs.LG updates on arXiv.org
SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
cs.LG updates on arXiv.org
Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL
Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL
cs.LG updates on arXiv.org
Timesynth: A Temporal Fidelity Framework for Health Signal Digital Twins
Timesynth: A Temporal Fidelity Framework for Health Signal Digital Twins
cs.LG updates on arXiv.org
Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning
Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning
cs.LG updates on arXiv.org
MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules
MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules
cs.LG updates on arXiv.org
How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Prediction
How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Prediction
cs.LG updates on arXiv.org
Interpretable vs Learned Encoders for High-Cardinality Fraud Detection
Interpretable vs Learned Encoders for High-Cardinality Fraud Detection
cs.LG updates on arXiv.org
Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization
Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization
cs.LG updates on arXiv.org
PAPA: Online Personalized Active Preference Alignment
PAPA: Online Personalized Active Preference Alignment
cs.LG updates on arXiv.org
From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research
From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research
cs.LG updates on arXiv.org
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
cs.LG updates on arXiv.org
Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition
Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition
cs.LG updates on arXiv.org
Group-Equivariant Poincar\'e Convolutional Networks
Group-Equivariant Poincar\'e Convolutional Networks
cs.LG updates on arXiv.org
Decision-focused Sparse Tangent Portfolio Optimization
Decision-focused Sparse Tangent Portfolio Optimization
cs.LG updates on arXiv.org
Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment
Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment
cs.LG updates on arXiv.org
Loss Smoothing for Stable Adaptation Under Distribution Shift
Loss Smoothing for Stable Adaptation Under Distribution Shift
cs.LG updates on arXiv.org
Multi-Label Node Classification with Label Influence Propagation
Multi-Label Node Classification with Label Influence Propagation
cs.LG updates on arXiv.org
Distributed Online Bandit Submodular Maximization with Bounded Sampling Violations
Distributed Online Bandit Submodular Maximization with Bounded Sampling Violations
cs.LG updates on arXiv.org
AdaBoosting Text Prompts for Vision-Language Models
AdaBoosting Text Prompts for Vision-Language Models
cs.LG updates on arXiv.org
Generative Refinement for Low-Budget Black-Box Optimization
Generative Refinement for Low-Budget Black-Box Optimization
cs.LG updates on arXiv.org
Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning
Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning
cs.LG updates on arXiv.org
LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data
LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data
cs.LG updates on arXiv.org
MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression
MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression
cs.LG updates on arXiv.org
Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling
Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling
cs.LG updates on arXiv.org
Which Metric Reflects the Spelling Rate Accuracy in Event-Related Potential-Based Brain-Computer Interfaces?
Which Metric Reflects the Spelling Rate Accuracy in Event-Related Potential-Based Brain-Computer Interfaces?
cs.LG updates on arXiv.org
Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization
Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization
cs.LG updates on arXiv.org
Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos
Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos
cs.LG updates on arXiv.org
From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training
From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training
cs.LG updates on arXiv.org
Spectroscopy Analysis with Machine Learning Regression for the Quantification of Carbon and Nitrogen Contents in Inceptisol and Oxisol Soil Types: Comparing Different Preprocessing and Validation methods as well as Feature Importance
Spectroscopy Analysis with Machine Learning Regression for the Quantification of Carbon and Nitrogen Contents in Inceptisol and Oxisol Soil Types: Comparing Different Preprocessing and Validation methods as well as Feature Importance
cs.LG updates on arXiv.org
Constrained Bayesian Optimisation with Multiple Information Sources
Constrained Bayesian Optimisation with Multiple Information Sources
cs.LG updates on arXiv.org
Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization
Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization
cs.LG updates on arXiv.org
Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm
Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm
cs.LG updates on arXiv.org
Explainable AI for Cancer Drug Response Prediction: Beyond Univariate Feature Attributions
Explainable AI for Cancer Drug Response Prediction: Beyond Univariate Feature Attributions
cs.LG updates on arXiv.org
Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations
Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations
cs.LG updates on arXiv.org
LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning
LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning
cs.LG updates on arXiv.org
Automatic Detection of Stress from Speech in the Trier Social Stress Test
Automatic Detection of Stress from Speech in the Trier Social Stress Test
cs.LG updates on arXiv.org
Generative Model Proposal based Particle Filtering for Data Assimilation
Generative Model Proposal based Particle Filtering for Data Assimilation
cs.LG updates on arXiv.org
Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling
Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling
cs.LG updates on arXiv.org
The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology
The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology
cs.LG updates on arXiv.org
GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache
GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache
cs.LG updates on arXiv.org
Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization
Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization
cs.LG updates on arXiv.org
When Context Compensates for Sparse Event History: AlphaEarth for Spatio-Temporal Point-Process Forecasting
When Context Compensates for Sparse Event History: AlphaEarth for Spatio-Temporal Point-Process Forecasting
cs.LG updates on arXiv.org
Staleness-Learning Rate Scaling Laws for Asynchronous RLHF
Staleness-Learning Rate Scaling Laws for Asynchronous RLHF
cs.LG updates on arXiv.org
CausalMix: Data Mixture as Causal Inference for Language Model Training
CausalMix: Data Mixture as Causal Inference for Language Model Training
cs.LG updates on arXiv.org
SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
cs.LG updates on arXiv.org
ZO-Act: Efficient Zeroth-Order Fine-Tuning via One-Shot Activation-Informed Low-Rank Subspaces
ZO-Act: Efficient Zeroth-Order Fine-Tuning via One-Shot Activation-Informed Low-Rank Subspaces
cs.LG updates on arXiv.org
GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems
GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems
cs.LG updates on arXiv.org
Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search
Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search
cs.LG updates on arXiv.org
A Lightweight Self-Supervised Learning Framework for Multivariate Time Series using Hierarchical-JEPA on ECG Data
A Lightweight Self-Supervised Learning Framework for Multivariate Time Series using Hierarchical-JEPA on ECG Data
cs.LG updates on arXiv.org
Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation
Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation
cs.LG updates on arXiv.org
Decision-Aware Training for Sample-Based Generative Models
Decision-Aware Training for Sample-Based Generative Models
cs.LG updates on arXiv.org
QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling
QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling
cs.LG updates on arXiv.org
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
cs.LG updates on arXiv.org
Neural Certificate Pricing for Combinatorial Optimization Problems
Neural Certificate Pricing for Combinatorial Optimization Problems
cs.LG updates on arXiv.org
Quantum vs. Classical Machine Learning: A Unified Empirical Comparison
Quantum vs. Classical Machine Learning: A Unified Empirical Comparison
cs.LG updates on arXiv.org
TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
cs.LG updates on arXiv.org
Language-Critique Imitation Learning from Suboptimal Demonstrations
Language-Critique Imitation Learning from Suboptimal Demonstrations
cs.LG updates on arXiv.org
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
cs.LG updates on arXiv.org
Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps
Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps
cs.LG updates on arXiv.org
Urban Deceleration Behavior Modes Under Scene Context: An Early-Kinematic Classifier from Argoverse 2 Multi-Agent Trajectories
Urban Deceleration Behavior Modes Under Scene Context: An Early-Kinematic Classifier from Argoverse 2 Multi-Agent Trajectories
cs.LG updates on arXiv.org
Spatio-Temporal Gaussian Process for Building Terrain-Incorporating Wind Power Curves
Spatio-Temporal Gaussian Process for Building Terrain-Incorporating Wind Power Curves
cs.LG updates on arXiv.org
Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
cs.LG updates on arXiv.org
CogTax: A Four-Level Cognitive Taxonomy for Command-Line Computing Education
CogTax: A Four-Level Cognitive Taxonomy for Command-Line Computing Education
cs.LG updates on arXiv.org
A Mechanism-Driven Theory of Phase Transitions in Active Learning
A Mechanism-Driven Theory of Phase Transitions in Active Learning
cs.LG updates on arXiv.org
Steal the Patch Size: Adversarially Manipulate Vision-Language Models
Steal the Patch Size: Adversarially Manipulate Vision-Language Models
cs.LG updates on arXiv.org
HydraCollab: Adaptive Collaborative-Perception for Distributed Autonomous Systems
HydraCollab: Adaptive Collaborative-Perception for Distributed Autonomous Systems
cs.LG updates on arXiv.org
Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent
Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent
cs.LG updates on arXiv.org
SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing
SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing
cs.LG updates on arXiv.org
Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics
Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics
cs.LG updates on arXiv.org
Leveraging Multimodality for Real-Time Classification of Transients and Variables found by the Zwicky Transient Facility
Leveraging Multimodality for Real-Time Classification of Transients and Variables found by the Zwicky Transient Facility
cs.LG updates on arXiv.org
Computer vision-based neural networks for radioisotope identification in urban environments
Computer vision-based neural networks for radioisotope identification in urban environments
cs.LG updates on arXiv.org
Self-Organized Learning in Oscillatory Neural Networks with Memristive Signed Couplings
Self-Organized Learning in Oscillatory Neural Networks with Memristive Signed Couplings
cs.LG updates on arXiv.org
Rosetta: Composable Native Multimodal Pretraining
Rosetta: Composable Native Multimodal Pretraining
cs.LG updates on arXiv.org
From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
cs.LG updates on arXiv.org
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
cs.LG updates on arXiv.org
SoK: Attack and Defense Landscape of Mobile On-device AI Systems
SoK: Attack and Defense Landscape of Mobile On-device AI Systems
cs.LG updates on arXiv.org
When AI meets quantum information: A comprehensive review
When AI meets quantum information: A comprehensive review
cs.LG updates on arXiv.org
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
cs.LG updates on arXiv.org
MindAU: EEG-Conditioned Facial Action Unit Editing via Dual-Stream Manifold Alignment
MindAU: EEG-Conditioned Facial Action Unit Editing via Dual-Stream Manifold Alignment
cs.LG updates on arXiv.org
A Mechanistic View of Authority Hierarchy in LLM Sycophancy
A Mechanistic View of Authority Hierarchy in LLM Sycophancy
cs.LG updates on arXiv.org
Information-Regularized Attention for Visual-Centric Reasoning
Information-Regularized Attention for Visual-Centric Reasoning
cs.LG updates on arXiv.org
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
cs.LG updates on arXiv.org
Neural Network-Based Estimation of Time-Dependent Parameters in AR(p) Processes
Neural Network-Based Estimation of Time-Dependent Parameters in AR(p) Processes
cs.LG updates on arXiv.org
Predicting Lethal Outcome (Cause) And Understanding Key Biomarkers Linked With Acute Myocardial Infarction Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies
Predicting Lethal Outcome (Cause) And Understanding Key Biomarkers Linked With Acute Myocardial Infarction Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies
cs.LG updates on arXiv.org
How Environment and Urbanization Shape Bird Diversity in Sri Lanka
How Environment and Urbanization Shape Bird Diversity in Sri Lanka
cs.LG updates on arXiv.org
Optimal scaling of MCMC algorithms: exploiting the symmetry of the Metropolis-Hastings formula
Optimal scaling of MCMC algorithms: exploiting the symmetry of the Metropolis-Hastings formula
cs.LG updates on arXiv.org
Auditing Forgetting in Limited Memory Language Models
Auditing Forgetting in Limited Memory Language Models
cs.LG updates on arXiv.org
What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music
What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music
cs.LG updates on arXiv.org
Coachable agents for interactive gameplay
Coachable agents for interactive gameplay
cs.LG updates on arXiv.org
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
cs.LG updates on arXiv.org
LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
cs.LG updates on arXiv.org
Forensic-Oriented Intrusion Detection Using Synthetic Network Traffic Data and Explainable Artificial Intelligence
Forensic-Oriented Intrusion Detection Using Synthetic Network Traffic Data and Explainable Artificial Intelligence
cs.LG updates on arXiv.org
Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers
Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers
cs.LG updates on arXiv.org
Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition
Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition
cs.LG updates on arXiv.org
Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning
Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning
cs.LG updates on arXiv.org
Shapley in Context: Explaining Financial Language with Domain Expertise
Shapley in Context: Explaining Financial Language with Domain Expertise
cs.LG updates on arXiv.org
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
cs.LG updates on arXiv.org
The Binary Tree Mechanism is Optimal for Approximate Differentially Private Continual Counting
The Binary Tree Mechanism is Optimal for Approximate Differentially Private Continual Counting
cs.LG updates on arXiv.org
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
cs.LG updates on arXiv.org
A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models
A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models
cs.LG updates on arXiv.org
Bridging Quantum Computing Paradigms toward Semiconductor Yield: A Controlled CV-versus-DV Comparison on Wafer-Map Defect Classification
Bridging Quantum Computing Paradigms toward Semiconductor Yield: A Controlled CV-versus-DV Comparison on Wafer-Map Defect Classification
cs.LG updates on arXiv.org
Understanding How Humans Inject Knowledge into Machine Learning Workflows through Visual Analytics
Understanding How Humans Inject Knowledge into Machine Learning Workflows through Visual Analytics
cs.LG updates on arXiv.org
Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
cs.LG updates on arXiv.org
Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices
Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices
cs.LG updates on arXiv.org
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
cs.LG updates on arXiv.org
Function-Counting Theory for Low-Dimensional Data Structures
Function-Counting Theory for Low-Dimensional Data Structures
cs.LG updates on arXiv.org
How Much Do RF Drone Benchmarks Overstate? A Controlled Study and Theory of Data Leakage in UAV Signal Identification
How Much Do RF Drone Benchmarks Overstate? A Controlled Study and Theory of Data Leakage in UAV Signal Identification
cs.LG updates on arXiv.org
Characterizing and Identifying Separable Graphical Models
Characterizing and Identifying Separable Graphical Models
cs.LG updates on arXiv.org
Message Passing Enables Efficient Reasoning
Message Passing Enables Efficient Reasoning
cs.LG updates on arXiv.org
Group-invariant Coresets for Data-efficient Active Learning
Group-invariant Coresets for Data-efficient Active Learning
cs.LG updates on arXiv.org
FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
cs.LG updates on arXiv.org
GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics
GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics
cs.LG updates on arXiv.org
Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
cs.LG updates on arXiv.org
The State-Prediction Separation Hypothesis
The State-Prediction Separation Hypothesis
cs.LG updates on arXiv.org
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
cs.LG updates on arXiv.org
Semi-Bandit Learning for Monotone Stochastic Optimization
Semi-Bandit Learning for Monotone Stochastic Optimization
cs.LG updates on arXiv.org
Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
cs.LG updates on arXiv.org
Invariance Pair Guidance: Robustness to Spurious Correlations via Corrective Gradients
Invariance Pair Guidance: Robustness to Spurious Correlations via Corrective Gradients
cs.LG updates on arXiv.org
Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning
Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning
cs.LG updates on arXiv.org
scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
cs.LG updates on arXiv.org
FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data
FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data
cs.LG updates on arXiv.org
Fraud is Not Just Rarity: A Causal Prototype Attention Approach to Realistic Synthetic Oversampling
Fraud is Not Just Rarity: A Causal Prototype Attention Approach to Realistic Synthetic Oversampling
cs.LG updates on arXiv.org
FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning
FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning
cs.LG updates on arXiv.org
TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
cs.LG updates on arXiv.org
FedIA: Importance-Aware Aggregation for Domain-Robust Federated Graph Learning
FedIA: Importance-Aware Aggregation for Domain-Robust Federated Graph Learning
cs.LG updates on arXiv.org
Predicting LLM Reasoning Performance with Small Proxy Model
Predicting LLM Reasoning Performance with Small Proxy Model
cs.LG updates on arXiv.org
Self-Improving Neural Pruning: A Graph Neural Network Framework for Scalable Mixed Bundle Pricing
Self-Improving Neural Pruning: A Graph Neural Network Framework for Scalable Mixed Bundle Pricing
cs.LG updates on arXiv.org
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
cs.LG updates on arXiv.org
Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning
Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning
cs.LG updates on arXiv.org
FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
cs.LG updates on arXiv.org
When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models
When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models
cs.LG updates on arXiv.org
Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings
Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings
cs.LG updates on arXiv.org
OpFML: Pipeline for ML-based Operational Inference
OpFML: Pipeline for ML-based Operational Inference
cs.LG updates on arXiv.org
KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning
KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning
cs.LG updates on arXiv.org
PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
cs.LG updates on arXiv.org
Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing
Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing
cs.LG updates on arXiv.org
Geometry-Preserving Neural Architectures on Manifolds with Boundary
Geometry-Preserving Neural Architectures on Manifolds with Boundary
cs.LG updates on arXiv.org
Calibrated Test-Time Guidance for Bayesian Inference
Calibrated Test-Time Guidance for Bayesian Inference
cs.LG updates on arXiv.org
MetaOthello: A Controlled Study of Multiple World Models in Transformers
MetaOthello: A Controlled Study of Multiple World Models in Transformers
cs.LG updates on arXiv.org
Amortized Maximum Inner Product Search with Learned Support Functions
Amortized Maximum Inner Product Search with Learned Support Functions
cs.LG updates on arXiv.org
Competition-Aware CPC Forecasting with Near-Market Coverage
Competition-Aware CPC Forecasting with Near-Market Coverage
cs.LG updates on arXiv.org
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
cs.LG updates on arXiv.org
Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
cs.LG updates on arXiv.org
ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding
ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding
cs.LG updates on arXiv.org
Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
cs.LG updates on arXiv.org
When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration
When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration
cs.LG updates on arXiv.org
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models
cs.LG updates on arXiv.org
Zeroth-Order Optimization at the Edge of Stability
Zeroth-Order Optimization at the Edge of Stability
cs.LG updates on arXiv.org
REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations
REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations
cs.LG updates on arXiv.org
FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
cs.LG updates on arXiv.org
FastUMAP: Scalable Dimensionality Reduction via Bipartite Landmark Sampling
FastUMAP: Scalable Dimensionality Reduction via Bipartite Landmark Sampling
cs.LG updates on arXiv.org
Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention
Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention
cs.LG updates on arXiv.org
Explaining Tabular Foundation Model Differences Through Meta-Features
Explaining Tabular Foundation Model Differences Through Meta-Features
cs.LG updates on arXiv.org
Nonlinear Bayesian Estimator for Parameter Learning: A Fixed-Point Characterization
Nonlinear Bayesian Estimator for Parameter Learning: A Fixed-Point Characterization
cs.LG updates on arXiv.org
Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives
Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives
cs.LG updates on arXiv.org
Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting
Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting
cs.LG updates on arXiv.org
A new classification method based on Minimum Spanning Trees
A new classification method based on Minimum Spanning Trees
cs.LG updates on arXiv.org
Inverse Reinforcement Learning for Interpretable Keystroke Biomarkers in Parkinson's Disease
Inverse Reinforcement Learning for Interpretable Keystroke Biomarkers in Parkinson's Disease
cs.LG updates on arXiv.org
PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs
PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs
cs.LG updates on arXiv.org
What Was That Again? Certified Robustness for Automatic Speech Recognition
What Was That Again? Certified Robustness for Automatic Speech Recognition
cs.LG updates on arXiv.org
ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions
ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions
cs.LG updates on arXiv.org
Optimization on the Oblique Manifold for Sparse Simplex Constraints via Multiplicative Updates
Optimization on the Oblique Manifold for Sparse Simplex Constraints via Multiplicative Updates
cs.LG updates on arXiv.org
PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks
PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks
cs.LG updates on arXiv.org
Explainability in mulimodal deep transformation models for stroke outcome prediction
Explainability in mulimodal deep transformation models for stroke outcome prediction
cs.LG updates on arXiv.org
Towards Weaker Variance Assumptions for Stochastic Optimization
Towards Weaker Variance Assumptions for Stochastic Optimization
cs.LG updates on arXiv.org
A General Approach to Visualizing Uncertainty in Statistical Graphics
A General Approach to Visualizing Uncertainty in Statistical Graphics
cs.LG updates on arXiv.org
Energy-Efficient Real-Time 4-Stage Sleep Classification at 10-Second Resolution
Energy-Efficient Real-Time 4-Stage Sleep Classification at 10-Second Resolution
cs.LG updates on arXiv.org
FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel
FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel
cs.LG updates on arXiv.org
CWT-Enhanced Vibration Sensing With Time-Frequency Region Localization Using YOLO
CWT-Enhanced Vibration Sensing With Time-Frequency Region Localization Using YOLO
cs.LG updates on arXiv.org
Reward function compression facilitates goal-dependent reinforcement learning
Reward function compression facilitates goal-dependent reinforcement learning
cs.LG updates on arXiv.org
Breaking the Weak Recovery Limit in Random Phase Retrieval with Learned Regularizers
Breaking the Weak Recovery Limit in Random Phase Retrieval with Learned Regularizers
cs.LG updates on arXiv.org
Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
cs.LG updates on arXiv.org
Root Cause Analysis of Outliers in Unknown Cyclic Graphs
Root Cause Analysis of Outliers in Unknown Cyclic Graphs
cs.LG updates on arXiv.org
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
cs.LG updates on arXiv.org
Quantitative Understanding of PDF Fits and their Uncertainties
Quantitative Understanding of PDF Fits and their Uncertainties
cs.LG updates on arXiv.org
Fast Score-Based Sampling via Log-Concave Reductions
Fast Score-Based Sampling via Log-Concave Reductions
cs.LG updates on arXiv.org
Zero-Shot Distracted Driver Detection via Vision Language Models with Double Decoupling
Zero-Shot Distracted Driver Detection via Vision Language Models with Double Decoupling
cs.LG updates on arXiv.org
Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
cs.LG updates on arXiv.org
GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition
GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition
cs.LG updates on arXiv.org
MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation
MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation
cs.LG updates on arXiv.org
From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
cs.LG updates on arXiv.org
IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video
IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video
cs.LG updates on arXiv.org
Goal-oriented learning of stochastic differential equations using error bounds on path-space observables
Goal-oriented learning of stochastic differential equations using error bounds on path-space observables
cs.LG updates on arXiv.org
Large language model-enabled automated data extraction for concrete materials informatics
Large language model-enabled automated data extraction for concrete materials informatics
cs.LG updates on arXiv.org
Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks
Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks
cs.LG updates on arXiv.org
Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
cs.LG updates on arXiv.org
Real-time virtual circuits for plasma shape control via neural network emulators
Real-time virtual circuits for plasma shape control via neural network emulators
cs.LG updates on arXiv.org
Wasserstein Contraction of Coordinate Ascent Variational Inference
Wasserstein Contraction of Coordinate Ascent Variational Inference
cs.LG updates on arXiv.org
Korzhinskii-Net: Physics-Informed Neural Network for Sub-Surface Mineral Prospectivity Modelling
Korzhinskii-Net: Physics-Informed Neural Network for Sub-Surface Mineral Prospectivity Modelling
cs.LG updates on arXiv.org
Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds
Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds
cs.LG updates on arXiv.org
Statistical Properties of Training & Generalization
Statistical Properties of Training & Generalization
cs.LG updates on arXiv.org
FeLoG: Scalable and Efficient Distributed Graph Embedding with Feedback Loop Mechanism
FeLoG: Scalable and Efficient Distributed Graph Embedding with Feedback Loop Mechanism
cs.LG updates on arXiv.org
Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval
Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval
cs.LG updates on arXiv.org
Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation
Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation
cs.LG updates on arXiv.org
Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks
Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks
cs.LG updates on arXiv.org
DataComp-VLM: Improved Open Datasets for Vision-Language Models
DataComp-VLM: Improved Open Datasets for Vision-Language Models
cs.LG updates on arXiv.org
Understanding Evaluation Illusion in Diffusion Large Language Models
Understanding Evaluation Illusion in Diffusion Large Language Models
stat.ML updates on arXiv.org
From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
stat.ML updates on arXiv.org
Neural Network-Based Estimation of Time-Dependent Parameters in AR(p) Processes
Neural Network-Based Estimation of Time-Dependent Parameters in AR(p) Processes
stat.ML updates on arXiv.org
Hierarchical Variational Kalman Filtering
Hierarchical Variational Kalman Filtering
stat.ML updates on arXiv.org
Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
stat.ML updates on arXiv.org
Function-Counting Theory for Low-Dimensional Data Structures
Function-Counting Theory for Low-Dimensional Data Structures
stat.ML updates on arXiv.org
Characterizing and Identifying Separable Graphical Models
Characterizing and Identifying Separable Graphical Models
stat.ML updates on arXiv.org
Measuring Racial Disparities in Rent Growth Under Algorithmic Landlord Concentration in U.S. Metros
Measuring Racial Disparities in Rent Growth Under Algorithmic Landlord Concentration in U.S. Metros
stat.ML updates on arXiv.org
Uniform-in-time Propagation-of-Chaos for Stein Variational Gradient Descent
Uniform-in-time Propagation-of-Chaos for Stein Variational Gradient Descent
stat.ML updates on arXiv.org
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
stat.ML updates on arXiv.org
Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent
Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent
stat.ML updates on arXiv.org
Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics
Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics
stat.ML updates on arXiv.org
Distributionally Robust Linear Regression With Block Lewis Weights
Distributionally Robust Linear Regression With Block Lewis Weights
stat.ML updates on arXiv.org
Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning
Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning
stat.ML updates on arXiv.org
Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization
Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization
stat.ML updates on arXiv.org
From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research
From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research
stat.ML updates on arXiv.org
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
stat.ML updates on arXiv.org
Approximate full-conformal multi-task regression with reproducing kernels
Approximate full-conformal multi-task regression with reproducing kernels
stat.ML updates on arXiv.org
Convolutional Symmetric AutoEncoders: enhancing latent stability via differential geometry
Convolutional Symmetric AutoEncoders: enhancing latent stability via differential geometry
stat.ML updates on arXiv.org
Decision-Aware Training for Sample-Based Generative Models
Decision-Aware Training for Sample-Based Generative Models
stat.ML updates on arXiv.org
Root Cause Analysis of Outliers in Unknown Cyclic Graphs
Root Cause Analysis of Outliers in Unknown Cyclic Graphs
stat.ML updates on arXiv.org
Wasserstein Contraction of Coordinate Ascent Variational Inference
Wasserstein Contraction of Coordinate Ascent Variational Inference
stat.ML updates on arXiv.org
Statistical Properties of Training & Generalization
Statistical Properties of Training & Generalization
stat.ML updates on arXiv.org
Towards Weaker Variance Assumptions for Stochastic Optimization
Towards Weaker Variance Assumptions for Stochastic Optimization
stat.ML updates on arXiv.org
Fast Score-Based Sampling via Log-Concave Reductions
Fast Score-Based Sampling via Log-Concave Reductions
stat.ML updates on arXiv.org
Amortized Maximum Inner Product Search with Learned Support Functions
Amortized Maximum Inner Product Search with Learned Support Functions
stat.ML updates on arXiv.org
Zeroth-Order Optimization at the Edge of Stability
Zeroth-Order Optimization at the Edge of Stability
stat.ML updates on arXiv.org
Nonlinear Bayesian Estimator for Parameter Learning: A Fixed-Point Characterization
Nonlinear Bayesian Estimator for Parameter Learning: A Fixed-Point Characterization
stat.ML updates on arXiv.org
Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds
Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds
stat.ML updates on arXiv.org
A new classification method based on Minimum Spanning Trees
A new classification method based on Minimum Spanning Trees
＠IT 全フォーラム 最新記事一覧
マツダが“脱テープ”で「遅い」の声をなくし、容量単価まで約10分の1に その方法は？
マツダが“脱テープ”で「遅い」の声をなくし、容量単価まで約10分の1に その方法は？
＠IT 全フォーラム 最新記事一覧
「脆弱なコード、データ漏えい、侵害され得るモデル」 開発者の不安をMicrosoftはどう解消するのか
「脆弱なコード、データ漏えい、侵害され得るモデル」 開発者の不安をMicrosoftはどう解消するのか
＠IT 全フォーラム 最新記事一覧
「賢さよりツール連携力が重要」 Microsoftが実験的な小型AIエージェント基盤を公開
「賢さよりツール連携力が重要」 Microsoftが実験的な小型AIエージェント基盤を公開
#LLMタグ
【技術解説】DeepSeekがまた静かにやってくれました──"再学習なし"でLLM推論を最大85%高速化する「DSpark」とは
【技術解説】DeepSeekがまた静かにやってくれました──"再学習なし"でLLM推論を最大85%高速化する「DSpark」とは
Zennの「大規模言語モデル」のフィード
同じコードをローカルLLMに51回監査させたら：多数決は"正しさ"より"しつこさ"を選んでいた
同じコードをローカルLLMに51回監査させたら：多数決は"正しさ"より"しつこさ"を選んでいた
NVIDIA Blog
NVIDIA Unlocks AI Compute at Scale, Inviting Partners to Power the AI Infrastructure Buildout
NVIDIA Unlocks AI Compute at Scale, Inviting Partners to Power the AI Infrastructure Buildout
#LLMタグ
【衝撃】AIに「電気ショックを与えろ」と命じ続けたら？ 11のLLMが“ミルグラム実験”で露呈した正体と、エンジニアが知っておくべき安全設計の真実 🧠⚡
【衝撃】AIに「電気ショックを与えろ」と命じ続けたら？ 11のLLMが“ミルグラム実験”で露呈した正体と、エンジニアが知っておくべき安全設計の真実 🧠⚡
Zennの「大規模言語モデル」のフィード
なぜ、2025～2026年頃にプロンプトエンジニアリングはコンテキストエンジニアリングに変化したのか？
なぜ、2025～2026年頃にプロンプトエンジニアリングはコンテキストエンジニアリングに変化したのか？
ITmedia NEWS 最新記事一覧
「端末からSuicaが消えた」対処法は JR東「モバイルSuica」2日朝もアクセスしづらく
「端末からSuicaが消えた」対処法は JR東「モバイルSuica」2日朝もアクセスしづらく
Zennの「大規模言語モデル」のフィード
Claude Fable 5とループエンジニアリング ── "プロンプトを打たない"時代の公式ガイド要約
Claude Fable 5とループエンジニアリング ── "プロンプトを打たない"時代の公式ガイド要約
#LLMタグ
2030年、コンタクトセンターの「保留音」が消えるかもしれない。──カラクリR&Dチームの未来予測
2030年、コンタクトセンターの「保留音」が消えるかもしれない。──カラクリR&Dチームの未来予測
#LLMタグ
【生成AIニュースまとめ】2026年7月2日 — Claude Fable 5がグローバル復活、Sonnet 5とGPT-5.6で夏の主導権争い
【生成AIニュースまとめ】2026年7月2日 — Claude Fable 5がグローバル復活、Sonnet 5とGPT-5.6で夏の主導権争い
＠IT 全フォーラム 最新記事一覧
Windows上の「Linux開発環境」が変わる 使い慣れたコマンドも“そのまま利用可能”に
Windows上の「Linux開発環境」が変わる 使い慣れたコマンドも“そのまま利用可能”に
Zennの「機械学習」のフィード
Claudecodeを使って１日で競馬予想AIを作成してみた（まさかの結果に。。）
Claudecodeを使って１日で競馬予想AIを作成してみた（まさかの結果に。。）
ITmedia NEWS 最新記事一覧
東京ディズニーランド初のドローン演出 夜間エンタメ「Reach for the Stars」フィナーレ彩る
東京ディズニーランド初のドローン演出 夜間エンタメ「Reach for the Stars」フィナーレ彩る
#LLMタグ
【ビジネス・セキュリティニュース 2026/7/2】シャドーAI対策「7割が未着手」 「AIは全て禁止」は限界 IT部門が採るべき一手とは？ Gartner提言／【AI駆動開発】AIに「図を描いて」と頼むと“それっぽいけど使えない図”が出てくる問題を、draw.io生成スキルで倒した - Qiita／AI以後の受託システム開発はどうなっていくのか ほか
【ビジネス・セキュリティニュース 2026/7/2】シャドーAI対策「7割が未着手」 「AIは全て禁止」は限界 IT部門が採るべき一手とは？ Gartner提言／【AI駆動開発】AIに「図を描いて」と頼むと“それっぽいけど使えない図”が出てくる問題を、draw.io生成スキルで倒した - Qiita／AI以後の受託システム開発はどうなっていくのか ほか
#LLMタグ
石原潔という先駆者のはなし。「日本で一番早い『Tiarra』の記事」『おはようインターネット』(ログイン 1997年6月20日号)
石原潔という先駆者のはなし。「日本で一番早い『Tiarra』の記事」『おはようインターネット』(ログイン 1997年6月20日号)
＠IT 全フォーラム 最新記事一覧
PR： AI時代の主戦場は「AI」ではない？ フォーティネットが見据える次の競争軸
PR： AI時代の主戦場は「AI」ではない？ フォーティネットが見据える次の競争軸
ITmedia NEWS 最新記事一覧
浅田真央さんの旧ドメイン、GMOが「アフィサイトに」と販売で批判殺到【訂正あり】
浅田真央さんの旧ドメイン、GMOが「アフィサイトに」と販売で批判殺到【訂正あり】
ITmedia NEWS 最新記事一覧
Googleの「Gemini Spark」がmacOSに対応──Canvaなど外部アプリとの連携も
Googleの「Gemini Spark」がmacOSに対応──Canvaなど外部アプリとの連携も
#LLMタグ
日立が本気を出す？「Hitachi iQ Studio」でAIが基幹業務に突入。エンジニアが見逃せない3つの真実 🔥
日立が本気を出す？「Hitachi iQ Studio」でAIが基幹業務に突入。エンジニアが見逃せない3つの真実 🔥
Latent.Space
Autoresearch: The feedback loop behind self-improving agents
Autoresearch: The feedback loop behind self-improving agents
Zennの「大規模言語モデル」のフィード
マルチエージェント協調 ― 親子の委任とボードによるタスク分解の2系統【プロンプトで読み解くAIエージェント #6】
マルチエージェント協調 ― 親子の委任とボードによるタスク分解の2系統【プロンプトで読み解くAIエージェント #6】
WIRED
The Best July 4 Grill and Griddle Deals: Weber, Traeger, Recteq
The Best July 4 Grill and Griddle Deals: Weber, Traeger, Recteq
#LLMタグ
【コスト半額】Claude APIのMessage Batches APIで一括処理を"投げっぱなし"にする実装ガイド — 料金を50%オフにする40行Python【2026-07】
【コスト半額】Claude APIのMessage Batches APIで一括処理を"投げっぱなし"にする実装ガイド — 料金を50%オフにする40行Python【2026-07】
Zennの「大規模言語モデル」のフィード
「Autopilot が3日間 done ゼロ」の犯人は、レビュー承認の freshness 判定だった話
「Autopilot が3日間 done ゼロ」の犯人は、レビュー承認の freshness 判定だった話
ITmedia NEWS 最新記事一覧
AIに「相手に電気ショックを与えろ」と命じ続けたらボタンを押すのか？ 11のLLMで“ミルグラム実験” 抵抗できたのは……
AIに「相手に電気ショックを与えろ」と命じ続けたらボタンを押すのか？ 11のLLMで“ミルグラム実験” 抵抗できたのは……
The Verge
Apple’s entry-level MacBook Pro could be up for a redesign
Apple’s entry-level MacBook Pro could be up for a redesign
Zennの「大規模言語モデル」のフィード
Context Length足りないんだから増やせばいいじゃん、と思ってた頃が僕にもありました
Context Length足りないんだから増やせばいいじゃん、と思ってた頃が僕にもありました
#LLMタグ
可能性分布としての世界、可能性分布としての意味／量子論・LLM・パーソナライズされた創造性の接続点
可能性分布としての世界、可能性分布としての意味／量子論・LLM・パーソナライズされた創造性の接続点
ITmedia NEWS 最新記事一覧
「赤」と「緑」を見分けられる仕組みを世界初解明、色覚障害の理解へ一歩 名工大や東大などがScience誌で発表
「赤」と「緑」を見分けられる仕組みを世界初解明、色覚障害の理解へ一歩 名工大や東大などがScience誌で発表
ITmedia NEWS 最新記事一覧
Anthropicの営業はAIエージェントをこう使う！ 日本法人メンバーが明かす手の内
Anthropicの営業はAIエージェントをこう使う！ 日本法人メンバーが明かす手の内
WIRED
Mexico’s Victory Over Ecuador Made the Ground Shake. Was It an Artificial Earthquake?
Mexico’s Victory Over Ecuador Made the Ground Shake. Was It an Artificial Earthquake?
Zennの「大規模言語モデル」のフィード
"「常連に悪くて、値上げできない」── 材料費が上がった定食屋で、守る一皿を決めて、全部は上げずに黒字へ戻す"
"「常連に悪くて、値上げできない」── 材料費が上がった定食屋で、守る一皿を決めて、全部は上げずに黒字へ戻す"
MarkTechPost
Using Lift to Turn Research PDFs into Structured JSON with Controlled, Schema-Guided Field-Level Evaluation
Using Lift to Turn Research PDFs into Structured JSON with Controlled, Schema-Guided Field-Level Evaluation
The Verge
Xbox’s ‘reset’: all the news about Microsoft’s looming layoffs and studio closures
Xbox’s ‘reset’: all the news about Microsoft’s looming layoffs and studio closures
MarkTechPost
Anthropic Redeploys Claude Fable 5 on July 1 After US Export Controls Lift, Adds New Cybersecurity Classifier
Anthropic Redeploys Claude Fable 5 on July 1 After US Export Controls Lift, Adds New Cybersecurity Classifier
MIT News - Artificial intelligence
MIT in the media: Innovating and educating for the next 250 years of America
MIT in the media: Innovating and educating for the next 250 years of America
WIRED
Goose, a New Gay Dating App, Appears to Be a Psyop
Goose, a New Gay Dating App, Appears to Be a Psyop
The Verge
Elon Musk denies a report about SpaceX’s AI phone prototype
Elon Musk denies a report about SpaceX’s AI phone prototype
＠IT 全フォーラム 最新記事一覧
「コーディングはボトルネックだったためしがない」 AI駆動開発の盲点と成果が出ない理由、Gartnerが明かす
「コーディングはボトルネックだったためしがない」 AI駆動開発の盲点と成果が出ない理由、Gartnerが明かす
＠IT 全フォーラム 最新記事一覧
Windows 11移行で悩む人に朗報？ Windows 10「拡張セキュリティ更新（ESU）」が期間延長へ
Windows 11移行で悩む人に朗報？ Windows 10「拡張セキュリティ更新（ESU）」が期間延長へ
WIRED
An Explosion Knocked Out Anduril’s Rocket Motor Test Site in Mississippi
An Explosion Knocked Out Anduril’s Rocket Motor Test Site in Mississippi
Latent.Space
How Cursor deploys AI inside the enterprise
How Cursor deploys AI inside the enterprise
AI News & Artificial Intelligence | TechCrunch
SpaceX has an AI device prototype, and it sure sounds phone-ish
SpaceX has an AI device prototype, and it sure sounds phone-ish