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
ABot-N1: Toward a General Visual Language Navigation Foundation Model
ABot-N1: Toward a General Visual Language Navigation Foundation Model
Hugging Face Papers
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
Hugging Face Papers
Weak-to-Strong Generalization via Direct On-Policy Distillation
Weak-to-Strong Generalization via Direct On-Policy Distillation
Hugging Face Papers
4D Human-Scene Reconstruction from Low-Overlap Captures
4D Human-Scene Reconstruction from Low-Overlap Captures
Hugging Face Papers
LightMem-Ego: Your AI Memory for Everyday Life
LightMem-Ego: Your AI Memory for Everyday Life
Hugging Face Papers
AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification
AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification
Hugging Face Papers
Metacognition in LLMs: Foundations, Progress, and Opportunities
Metacognition in LLMs: Foundations, Progress, and Opportunities
Hugging Face Papers
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
Hugging Face Papers
NeuroCogMap Reveals Cognitive Organization of Large Language Models
NeuroCogMap Reveals Cognitive Organization of Large Language Models
Hugging Face Papers
Motion4Motion: Motion Transfer Across Subjects at Inference
Motion4Motion: Motion Transfer Across Subjects at Inference
Hugging Face Papers
CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation
CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation
Hugging Face Papers
LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow
LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow
#AIタグ
『Project "Lone Alpha": 自己定義型知性によるAIアーキテクチャの超越』第3話：共鳴と同期 —— ギフテッドの認知回路がAIをハッキングする
『Project "Lone Alpha": 自己定義型知性によるAIアーキテクチャの超越』第3話：共鳴と同期 —— ギフテッドの認知回路がAIをハッキングする
#AIタグ
【復活のIntel Mac】Appleに見捨てられたMacBook Airを救いたい（シンOCLP編）
【復活のIntel Mac】Appleに見捨てられたMacBook Airを救いたい（シンOCLP編）
#AIタグ
『Project "Lone Alpha": 自己定義型知性によるAIアーキテクチャの超越』第2話：Identity Layer —— 「人格」という名のOSをインストールする
『Project "Lone Alpha": 自己定義型知性によるAIアーキテクチャの超越』第2話：Identity Layer —— 「人格」という名のOSをインストールする
#AIタグ
Ambient Scribing in Tier-2 Indian Cities: Training an AI Tool for Doctors to Navigate Complex Code-Switching
Ambient Scribing in Tier-2 Indian Cities: Training an AI Tool for Doctors to Navigate Complex Code-Switching
#AIタグ
AIチャート分析プロンプトホロスコープから見る「ストレス耐性・限界サイン・回復方法」完全分析使ってみた
AIチャート分析プロンプトホロスコープから見る「ストレス耐性・限界サイン・回復方法」完全分析使ってみた
MarkTechPost
Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Using a Single RGB Camera
Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Using a Single RGB Camera
ITmedia NEWS 最新記事一覧
セブン-イレブン、テスラの「スーパーチャージャー」導入へ 26年度中に約10店舗
セブン-イレブン、テスラの「スーパーチャージャー」導入へ 26年度中に約10店舗
LLMタグが付けられた新着記事 - Qiita
【脱初心者】LLMを「使う側」から「作る側」へ！パーソナルAIアシスタント開発のロードマップ
【脱初心者】LLMを「使う側」から「作る側」へ！パーソナルAIアシスタント開発のロードマップ
＠IT 全フォーラム 最新記事一覧
EDRだけでは防げない 端末の脆弱性管理はなぜセキュリティ部門ではなくIT運用部門が主導すべきなのか
EDRだけでは防げない 端末の脆弱性管理はなぜセキュリティ部門ではなくIT運用部門が主導すべきなのか
機械学習タグが付けられた新着記事 - Qiita
YOLO26 のセマンティックセグメンテーションを PyTorch と ONNX で比較する
YOLO26 のセマンティックセグメンテーションを PyTorch と ONNX で比較する
WIRED
Nike Promo Codes and Discounts: 30% for July 2026
Nike Promo Codes and Discounts: 30% for July 2026
WIRED
Design Within Reach Promo Codes: 30% Off | July 2026
Design Within Reach Promo Codes: 30% Off | July 2026
#LLMタグ
ナデラCEOが警告！AIに支払う「二重コスト」とは？ 見えない資産を失わないための生存戦略 🚨💰
ナデラCEOが警告！AIに支払う「二重コスト」とは？ 見えない資産を失わないための生存戦略 🚨💰
cs.LG updates on arXiv.org
Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey
Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey
cs.LG updates on arXiv.org
Position: Every Ground Truth is a Human Construction, not an Objective Truth
Position: Every Ground Truth is a Human Construction, not an Objective Truth
cs.LG updates on arXiv.org
AuditWeave: A Tamper-Evident, Auditor-Navigable Evidence Layer for AI-Assisted and Data-Transformation Workflows
AuditWeave: A Tamper-Evident, Auditor-Navigable Evidence Layer for AI-Assisted and Data-Transformation Workflows
cs.LG updates on arXiv.org
Ablation, Statistical Inference, and Validation for KV-Cache Compression
Ablation, Statistical Inference, and Validation for KV-Cache Compression
cs.LG updates on arXiv.org
SciML in the Wild: A Diagnostic Study of When Structural Priors Help and When They Hurt
SciML in the Wild: A Diagnostic Study of When Structural Priors Help and When They Hurt
cs.LG updates on arXiv.org
MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference
MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference
cs.LG updates on arXiv.org
Prioritizing Search Space Regions in the Low Autocorrelation Binary Sequences Problem
Prioritizing Search Space Regions in the Low Autocorrelation Binary Sequences Problem
cs.LG updates on arXiv.org
What Context Does a Coding Agent Actually Need to Act?
What Context Does a Coding Agent Actually Need to Act?
cs.LG updates on arXiv.org
Reference-Based Distillation Detection in LLMs
Reference-Based Distillation Detection in LLMs
cs.LG updates on arXiv.org
Depth-Entropy Guided Sampling for Training-Free LLM Reasoning
Depth-Entropy Guided Sampling for Training-Free LLM Reasoning
cs.LG updates on arXiv.org
FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift
FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift
cs.LG updates on arXiv.org
Mitigating Early Training Collapse in CTR Models
Mitigating Early Training Collapse in CTR Models
cs.LG updates on arXiv.org
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
cs.LG updates on arXiv.org
Quantum-Inspired Contextual Learning for Sparse-Ring Fraud Detection in Dynamic Transaction Graphs
Quantum-Inspired Contextual Learning for Sparse-Ring Fraud Detection in Dynamic Transaction Graphs
cs.LG updates on arXiv.org
Manifold Constrained Tabular Deep Neural Networks
Manifold Constrained Tabular Deep Neural Networks
cs.LG updates on arXiv.org
EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?
EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?
cs.LG updates on arXiv.org
ERP Data Provisioning Financial Control Testing
ERP Data Provisioning Financial Control Testing
cs.LG updates on arXiv.org
Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls
Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls
cs.LG updates on arXiv.org
Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels
Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels
cs.LG updates on arXiv.org
JEPA for AI-Native 6G: Predictive Representations and Open Challenges
JEPA for AI-Native 6G: Predictive Representations and Open Challenges
cs.LG updates on arXiv.org
The Silent Freeze: Predicting When Low-Precision Training Stops Learning
The Silent Freeze: Predicting When Low-Precision Training Stops Learning
cs.LG updates on arXiv.org
Discovering Latent Response Laws in Forced Physical Systems
Discovering Latent Response Laws in Forced Physical Systems
cs.LG updates on arXiv.org
Quota Marketplace: Dynamic Pricing for Efficient Allocation of ML Training Resources
Quota Marketplace: Dynamic Pricing for Efficient Allocation of ML Training Resources
cs.LG updates on arXiv.org
Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation
Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation
cs.LG updates on arXiv.org
RUBRIC: Realism--Utility Balanced Ranking for Imbalanced Classification
RUBRIC: Realism--Utility Balanced Ranking for Imbalanced Classification
cs.LG updates on arXiv.org
Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data
Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data
cs.LG updates on arXiv.org
Learning Predictive Ambiguity Sets for Decision-Focused Distributionally Robust Optimization
Learning Predictive Ambiguity Sets for Decision-Focused Distributionally Robust Optimization
cs.LG updates on arXiv.org
A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition
A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition
cs.LG updates on arXiv.org
From Direction to Magnitude: How Multimodal Instruction-Tuning Reorganizes the Geometric Encoding of Identity-Specifying Prompts in Transformer Hidden States
From Direction to Magnitude: How Multimodal Instruction-Tuning Reorganizes the Geometric Encoding of Identity-Specifying Prompts in Transformer Hidden States
cs.LG updates on arXiv.org
Nonlinear Axiomatic Attribution for Cooperative Games
Nonlinear Axiomatic Attribution for Cooperative Games
cs.LG updates on arXiv.org
Serving the Long Tail: Training-Free LLM Candidate Generation for Vacation Rental Marketplaces
Serving the Long Tail: Training-Free LLM Candidate Generation for Vacation Rental Marketplaces
cs.LG updates on arXiv.org
Nonparametric Bayesian Inverse Reinforcement Learning with Data-Parallel Gibbs Sampling
Nonparametric Bayesian Inverse Reinforcement Learning with Data-Parallel Gibbs Sampling
cs.LG updates on arXiv.org
Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention
Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention
cs.LG updates on arXiv.org
SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification
SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification
cs.LG updates on arXiv.org
A Foundation Model for Multimodal Event Sequences in Financial Applications
A Foundation Model for Multimodal Event Sequences in Financial Applications
cs.LG updates on arXiv.org
Optimizing ARDL Models for Retail Sales Forecasting and Fair Pricing
Optimizing ARDL Models for Retail Sales Forecasting and Fair Pricing
cs.LG updates on arXiv.org
Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization
Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization
cs.LG updates on arXiv.org
Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction
Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction
cs.LG updates on arXiv.org
Vilya-1: An all-atom foundation model for macrocycle structure prediction and design
Vilya-1: An all-atom foundation model for macrocycle structure prediction and design
cs.LG updates on arXiv.org
MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers
MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers
cs.LG updates on arXiv.org
FlashTrie: A GPU-Accelerated Constrained Beam Search for Generative Retrieval
FlashTrie: A GPU-Accelerated Constrained Beam Search for Generative Retrieval
cs.LG updates on arXiv.org
Conservation Laws for Diffusion Models
Conservation Laws for Diffusion Models
cs.LG updates on arXiv.org
Error Aware Distribution Prediction for Lightweight Implicit Neural Representations
Error Aware Distribution Prediction for Lightweight Implicit Neural Representations
cs.LG updates on arXiv.org
Distance-Preserving Embeddings in Inhomogeneous Random Graphs
Distance-Preserving Embeddings in Inhomogeneous Random Graphs
cs.LG updates on arXiv.org
TabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Data
TabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Data
cs.LG updates on arXiv.org
When Data Imbalance Helps: Robust Generalization Through Shortcut Saturation
When Data Imbalance Helps: Robust Generalization Through Shortcut Saturation
cs.LG updates on arXiv.org
GAE: Graph-Augmented Evolution for Scientific Discovery via Reinforcement Optimization
GAE: Graph-Augmented Evolution for Scientific Discovery via Reinforcement Optimization
cs.LG updates on arXiv.org
SALT-GNN: Handling Dense Neighborhoods in Anti-Money Laundering Graphs via Statistics-Aware Attention
SALT-GNN: Handling Dense Neighborhoods in Anti-Money Laundering Graphs via Statistics-Aware Attention
cs.LG updates on arXiv.org
LeRoPE: Learnable RoPE Frequencies Improve Language Modeling
LeRoPE: Learnable RoPE Frequencies Improve Language Modeling
cs.LG updates on arXiv.org
RDQ: Residual Distribution Quantization for Large Language Models
RDQ: Residual Distribution Quantization for Large Language Models
cs.LG updates on arXiv.org
LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning
LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning
cs.LG updates on arXiv.org
Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
cs.LG updates on arXiv.org
Knowledge-Conditioned, Single-Pass LLM Synthesis of Executable Unity Game Scenes: A Compiler Error Census across 26 Goal Playable Concepts
Knowledge-Conditioned, Single-Pass LLM Synthesis of Executable Unity Game Scenes: A Compiler Error Census across 26 Goal Playable Concepts
cs.LG updates on arXiv.org
PhysMRV: Physical Memory Retrieval and Verification for Physics Plausibility Reasoning
PhysMRV: Physical Memory Retrieval and Verification for Physics Plausibility Reasoning
cs.LG updates on arXiv.org
Generative Augmentation of Raman Spectra for Glioma Classification
Generative Augmentation of Raman Spectra for Glioma Classification
cs.LG updates on arXiv.org
The Differential Neural Tangent Kernel and Its Positivity
The Differential Neural Tangent Kernel and Its Positivity
cs.LG updates on arXiv.org
Two Confounds in Cross-Model Value Comparison: Response Determinism and the Access Harness
Two Confounds in Cross-Model Value Comparison: Response Determinism and the Access Harness
cs.LG updates on arXiv.org
When Does Depth Survive Composition? Compute--Quality Regimes in Latent World Models
When Does Depth Survive Composition? Compute--Quality Regimes in Latent World Models
cs.LG updates on arXiv.org
Exploratory Analysis of Deep Learning Models for Forecasting Meteorological Parameters in the Agricultural Sector
Exploratory Analysis of Deep Learning Models for Forecasting Meteorological Parameters in the Agricultural Sector
cs.LG updates on arXiv.org
DSSMs: State Space Models with Explicit Memory via Delay Differential Equations
DSSMs: State Space Models with Explicit Memory via Delay Differential Equations
cs.LG updates on arXiv.org
Data-Driven Telecom Marketing Optimization: A Machine Learning-Based Churn Prediction and Customer Segmentation Framework
Data-Driven Telecom Marketing Optimization: A Machine Learning-Based Churn Prediction and Customer Segmentation Framework
cs.LG updates on arXiv.org
Sharper Analysis of Single-Loop Methods for Bilevel Optimization
Sharper Analysis of Single-Loop Methods for Bilevel Optimization
cs.LG updates on arXiv.org
Interpreting learning dynamics of autoencoders: Transient scaling and emerging concepts of the Ising model
Interpreting learning dynamics of autoencoders: Transient scaling and emerging concepts of the Ising model
cs.LG updates on arXiv.org
Empowering Long-form Omni-modal Understanding with Robust Audio Perception
Empowering Long-form Omni-modal Understanding with Robust Audio Perception
cs.LG updates on arXiv.org
A Control Theory of Predictability in Latent World Models
A Control Theory of Predictability in Latent World Models
cs.LG updates on arXiv.org
A Hyperbolic Neural Closure for M1 Radiation Transfer
A Hyperbolic Neural Closure for M1 Radiation Transfer
cs.LG updates on arXiv.org
Machine Learning-based Correlation of Charpy Impact Properties Between Sub-sized and Standard-sized Specimens for Nuclear Structural Materials
Machine Learning-based Correlation of Charpy Impact Properties Between Sub-sized and Standard-sized Specimens for Nuclear Structural Materials
cs.LG updates on arXiv.org
Context by Distinct Information: An Auditable Dirichlet-Process Working Memory for Long, Redundant Context Streams
Context by Distinct Information: An Auditable Dirichlet-Process Working Memory for Long, Redundant Context Streams
cs.LG updates on arXiv.org
Pitfalls of Administrative Censoring in Survival Models with Time-Indexed Inputs
Pitfalls of Administrative Censoring in Survival Models with Time-Indexed Inputs
cs.LG updates on arXiv.org
Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards
Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards
cs.LG updates on arXiv.org
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
cs.LG updates on arXiv.org
EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning
EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning
cs.LG updates on arXiv.org
Learning from Noise: Effective-Rank Collapse and Out-of-Distribution Rejection in Restricted Boltzmann Machines
Learning from Noise: Effective-Rank Collapse and Out-of-Distribution Rejection in Restricted Boltzmann Machines
cs.LG updates on arXiv.org
Conditional Optimal Bridge for Riemannian Activation Steering
Conditional Optimal Bridge for Riemannian Activation Steering
cs.LG updates on arXiv.org
LLM-PDESR: Robust PDE Discovery via Subdomain Weighted Residuals and LLM-Guided Symbolic Hypothesis Generation
LLM-PDESR: Robust PDE Discovery via Subdomain Weighted Residuals and LLM-Guided Symbolic Hypothesis Generation
cs.LG updates on arXiv.org
Learning from Local Walks on Dynamic Graphs with Bandit Feedback
Learning from Local Walks on Dynamic Graphs with Bandit Feedback
cs.LG updates on arXiv.org
MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference
MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference
cs.LG updates on arXiv.org
Sharp Concentration Bounds for Bundle-Valued Statistics on Manifolds
Sharp Concentration Bounds for Bundle-Valued Statistics on Manifolds
cs.LG updates on arXiv.org
AutoNorm: Understanding Adaptive Normalization in Transformers through Differentiable Gating
AutoNorm: Understanding Adaptive Normalization in Transformers through Differentiable Gating
cs.LG updates on arXiv.org
M+Adam: Low-Precision Training via Additive-Multiplicative Optimization
M+Adam: Low-Precision Training via Additive-Multiplicative Optimization
cs.LG updates on arXiv.org
modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints
modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints
cs.LG updates on arXiv.org
Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depression Prediction Across Student Cohorts
Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depression Prediction Across Student Cohorts
cs.LG updates on arXiv.org
Modernizing HEBO: a robust Bayesian optimization baseline for practical heteroskedastic and non-stationary problems
Modernizing HEBO: a robust Bayesian optimization baseline for practical heteroskedastic and non-stationary problems
cs.LG updates on arXiv.org
From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers
From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers
cs.LG updates on arXiv.org
LayerNorm as Implicit Gain Control in Looped Transformers
LayerNorm as Implicit Gain Control in Looped Transformers
cs.LG updates on arXiv.org
Learning to Fine-tune Foundation Models under Resource Limitations
Learning to Fine-tune Foundation Models under Resource Limitations
cs.LG updates on arXiv.org
On the modality gap and the contrastive loss in multi-modal representation learning
On the modality gap and the contrastive loss in multi-modal representation learning
cs.LG updates on arXiv.org
Scaffold splits hide structural-frontier failures in ADMET models
Scaffold splits hide structural-frontier failures in ADMET models
cs.LG updates on arXiv.org
To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning
To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning
cs.LG updates on arXiv.org
Multi-Scale Convolution with Optimal Transport Attention Effect on Multivariate Time Series
Multi-Scale Convolution with Optimal Transport Attention Effect on Multivariate Time Series
cs.LG updates on arXiv.org
Policy-Driven CT-Agent: Modeling Phase-Aware Diagnostic Control for Clinically Consistent CT Reasoning
Policy-Driven CT-Agent: Modeling Phase-Aware Diagnostic Control for Clinically Consistent CT Reasoning
cs.LG updates on arXiv.org
The VC dimension of partial concept classes via Radon's theorem
The VC dimension of partial concept classes via Radon's theorem
cs.LG updates on arXiv.org
LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification
LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification
cs.LG updates on arXiv.org
Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
cs.LG updates on arXiv.org
When does distribution shift break graph neural networks calibration?
When does distribution shift break graph neural networks calibration?
cs.LG updates on arXiv.org
Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO)
Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO)
cs.LG updates on arXiv.org
Diachronic Sample Integration: Robust Tail-Risk Estimation with Generative Models
Diachronic Sample Integration: Robust Tail-Risk Estimation with Generative Models
cs.LG updates on arXiv.org
Graph Neural Networks for RFID-Based Spatial Geometry Inference in Spatial AI Systems
Graph Neural Networks for RFID-Based Spatial Geometry Inference in Spatial AI Systems
cs.LG updates on arXiv.org
Predictive Divergence Masks for LLM RL
Predictive Divergence Masks for LLM RL
cs.LG updates on arXiv.org
Reliability Scaling Laws for Quantized Large Language Models
Reliability Scaling Laws for Quantized Large Language Models
cs.LG updates on arXiv.org
Singular perturbations and hierarchical learning in two-layer neural networks
Singular perturbations and hierarchical learning in two-layer neural networks
cs.LG updates on arXiv.org
Infrared Organization and Critical Cognitive Field Formation in Transformer Dynamics
Infrared Organization and Critical Cognitive Field Formation in Transformer Dynamics
cs.LG updates on arXiv.org
The Spectral Structure of Latent Treatment Effects
The Spectral Structure of Latent Treatment Effects
cs.LG updates on arXiv.org
The Singularity Space: A Generative Diffusion Framework for Signal Representation
The Singularity Space: A Generative Diffusion Framework for Signal Representation
cs.LG updates on arXiv.org
Bandit PCA with Minimax Optimal Regret
Bandit PCA with Minimax Optimal Regret
cs.LG updates on arXiv.org
Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion
Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion
cs.LG updates on arXiv.org
WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training
WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training
cs.LG updates on arXiv.org
Reinforcement Learning for Execution under Dynamic Fees in a Closed-Loop DEX Simulator
Reinforcement Learning for Execution under Dynamic Fees in a Closed-Loop DEX Simulator
cs.LG updates on arXiv.org
Efficient Online Proportional Sampling with Applications to Smoothed Online Learning
Efficient Online Proportional Sampling with Applications to Smoothed Online Learning
cs.LG updates on arXiv.org
Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Data
Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Data
cs.LG updates on arXiv.org
A Multi-Agent Framework for Zero-Dimensional Reduced-Order Model Planning
A Multi-Agent Framework for Zero-Dimensional Reduced-Order Model Planning
cs.LG updates on arXiv.org
TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings
TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings
cs.LG updates on arXiv.org
When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR
When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR
cs.LG updates on arXiv.org
Domain-Aware Scaling Laws Uncover Data Synergy
Domain-Aware Scaling Laws Uncover Data Synergy
cs.LG updates on arXiv.org
AeroMELD: A Linear Embedding of Aerosol Populations for Diagnostics and Latent Dynamics
AeroMELD: A Linear Embedding of Aerosol Populations for Diagnostics and Latent Dynamics
cs.LG updates on arXiv.org
Link Adaptation Using Joint-Thompson Sampling
Link Adaptation Using Joint-Thompson Sampling
cs.LG updates on arXiv.org
Adapting Evidential Neural Networks to Test-Time Neighbor Fusion Improves Molecular Property Prediction
Adapting Evidential Neural Networks to Test-Time Neighbor Fusion Improves Molecular Property Prediction
cs.LG updates on arXiv.org
Multi-dimensional training-priority weighting based on physical information propagation paths: a unified residual-weighting framework for physics-informed neural networks
Multi-dimensional training-priority weighting based on physical information propagation paths: a unified residual-weighting framework for physics-informed neural networks
cs.LG updates on arXiv.org
A Novel Graph Fraud Detector via Grouped Attribute Completion and Confidence-Aware Contrastive Learning
A Novel Graph Fraud Detector via Grouped Attribute Completion and Confidence-Aware Contrastive Learning
cs.LG updates on arXiv.org
Neural Discovery of Memory and Nonlocal Kernels in Integro-Differential Equations with Constrained Kolmogorov--Arnold Networks
Neural Discovery of Memory and Nonlocal Kernels in Integro-Differential Equations with Constrained Kolmogorov--Arnold Networks
cs.LG updates on arXiv.org
CA-DGCL: Dynamic Graph Continual Learning via Condensation and Attachment
CA-DGCL: Dynamic Graph Continual Learning via Condensation and Attachment
cs.LG updates on arXiv.org
The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning
The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning
cs.LG updates on arXiv.org
ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory
ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory
cs.LG updates on arXiv.org
Learning Subgroup Relations Using Siamese Graph Neural Networks
Learning Subgroup Relations Using Siamese Graph Neural Networks
cs.LG updates on arXiv.org
Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective
Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective
cs.LG updates on arXiv.org
NeuroMem-FHP: A Likelihood-Free Deep Learning Framework for Parameter Estimation of Fractional Hawkes Process
NeuroMem-FHP: A Likelihood-Free Deep Learning Framework for Parameter Estimation of Fractional Hawkes Process
cs.LG updates on arXiv.org
FastTPS: An Optimized Method for LLM Token Phase for AI accelerators
FastTPS: An Optimized Method for LLM Token Phase for AI accelerators
cs.LG updates on arXiv.org
Trustworthy synthetic data for campaign decision support: strategy simulation fidelity and the PolicySynth framework
Trustworthy synthetic data for campaign decision support: strategy simulation fidelity and the PolicySynth framework
cs.LG updates on arXiv.org
SPARC-Net: A Spectral, Causality-Aware, and Hard-Constrained Physics-Informed Architecture for Stiff and Shock-Dominated Partial Differential Equations
SPARC-Net: A Spectral, Causality-Aware, and Hard-Constrained Physics-Informed Architecture for Stiff and Shock-Dominated Partial Differential Equations
cs.LG updates on arXiv.org
PRISM Edit: One Vector for All Temporal Answers
PRISM Edit: One Vector for All Temporal Answers
cs.LG updates on arXiv.org
BackgroundMellow: A Multi-Modal Cohesive Framework for Narrative-Driven Rich Cinematic Soundscape Generation
BackgroundMellow: A Multi-Modal Cohesive Framework for Narrative-Driven Rich Cinematic Soundscape Generation
cs.LG updates on arXiv.org
Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment
Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment
cs.LG updates on arXiv.org
Physics-Aware Conditional SetGAN for Spatially Consistent Multi-User TR 38.901 Channel Generation
Physics-Aware Conditional SetGAN for Spatially Consistent Multi-User TR 38.901 Channel Generation
cs.LG updates on arXiv.org
Generalizing Preference-based Reinforcement Learning: a Rationality Model for Incomparability
Generalizing Preference-based Reinforcement Learning: a Rationality Model for Incomparability
cs.LG updates on arXiv.org
Event-based Neural Decoding for Neuroprosthetic Motor Control
Event-based Neural Decoding for Neuroprosthetic Motor Control
cs.LG updates on arXiv.org
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
cs.LG updates on arXiv.org
Agentic Skill Optimization over Lie Algebroids
Agentic Skill Optimization over Lie Algebroids
cs.LG updates on arXiv.org
IG-GAN: A Generative Adversarial Network for Aerodynamic Data Generation Based on Intrinsic Geometry
IG-GAN: A Generative Adversarial Network for Aerodynamic Data Generation Based on Intrinsic Geometry
cs.LG updates on arXiv.org
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
cs.LG updates on arXiv.org
SCOPE-RL: Optimizing Reasoning Paths Before and After Success
SCOPE-RL: Optimizing Reasoning Paths Before and After Success
cs.LG updates on arXiv.org
CDFM: Towards a General-Purpose Causal Discovery Foundation Model
CDFM: Towards a General-Purpose Causal Discovery Foundation Model
cs.LG updates on arXiv.org
DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms
DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms
cs.LG updates on arXiv.org
AutoMatBench: An Automatic Optimization Toolkit for the Acceleration of Material Properties Prediction Benchmarking
AutoMatBench: An Automatic Optimization Toolkit for the Acceleration of Material Properties Prediction Benchmarking
cs.LG updates on arXiv.org
Random Label Prediction Heads for Studying Memorization in Deep Neural Networks
Random Label Prediction Heads for Studying Memorization in Deep Neural Networks
cs.LG updates on arXiv.org
Condition-Stratified Robustness Analysis of Post-Hoc Calibration Methods for Probabilistic Classifiers
Condition-Stratified Robustness Analysis of Post-Hoc Calibration Methods for Probabilistic Classifiers
cs.LG updates on arXiv.org
Advancing Optimal Subset Oracle via Learning Relaxation of Neural Set Functions
Advancing Optimal Subset Oracle via Learning Relaxation of Neural Set Functions
cs.LG updates on arXiv.org
Heuristic Learning for Active Flow Control Using Coding Agents
Heuristic Learning for Active Flow Control Using Coding Agents
cs.LG updates on arXiv.org
Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization
Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization
cs.LG updates on arXiv.org
DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations
DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations
cs.LG updates on arXiv.org
Privacy-Aware Collaborative and Distributed Bayesian Optimization
Privacy-Aware Collaborative and Distributed Bayesian Optimization
cs.LG updates on arXiv.org
Fundamental Limitations of Fixed-Budget Best-Arm Identification
Fundamental Limitations of Fixed-Budget Best-Arm Identification
cs.LG updates on arXiv.org
Bet on Features: Anytime-Valid and Feature-Aware Auditing of Conditional Quantile Forecasters
Bet on Features: Anytime-Valid and Feature-Aware Auditing of Conditional Quantile Forecasters
cs.LG updates on arXiv.org
How to Tame Grokking: Representation Geometry as a Control Signal
How to Tame Grokking: Representation Geometry as a Control Signal
cs.LG updates on arXiv.org
A multi-scale feature enhanced graph neural network for fluid dynamics prediction in complex geometries
A multi-scale feature enhanced graph neural network for fluid dynamics prediction in complex geometries
cs.LG updates on arXiv.org
CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery
CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery
cs.LG updates on arXiv.org
Active Offline-to-Online Reinforcement Learning
Active Offline-to-Online Reinforcement Learning
cs.LG updates on arXiv.org
Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories
Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories
cs.LG updates on arXiv.org
HiFi-LLP: High-Fidelity, Low-Cost Latency Predictors with Confidence for Robust HW-NAS
HiFi-LLP: High-Fidelity, Low-Cost Latency Predictors with Confidence for Robust HW-NAS
cs.LG updates on arXiv.org
From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
cs.LG updates on arXiv.org
From Expressivity to Sample Complexity: Narrow Teachers for Transformers via C-RASP
From Expressivity to Sample Complexity: Narrow Teachers for Transformers via C-RASP
cs.LG updates on arXiv.org
An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It Reveals
An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It Reveals
cs.LG updates on arXiv.org
Relaxing Faithfulness with Intervention-Only Causal Discovery
Relaxing Faithfulness with Intervention-Only Causal Discovery
cs.LG updates on arXiv.org
Transformer-Guided Swarm Intelligence for Frugal Neural Architecture Search
Transformer-Guided Swarm Intelligence for Frugal Neural Architecture Search
cs.LG updates on arXiv.org
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
cs.LG updates on arXiv.org
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
cs.LG updates on arXiv.org
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
cs.LG updates on arXiv.org
Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking
Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking
cs.LG updates on arXiv.org
Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent
Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent
cs.LG updates on arXiv.org
ECG-LDC: A Hardware-Efficient Low-Dimensional Computing Framework for ECG Arrhythmia Classification
ECG-LDC: A Hardware-Efficient Low-Dimensional Computing Framework for ECG Arrhythmia Classification
cs.LG updates on arXiv.org
Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems
Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems
cs.LG updates on arXiv.org
Interpreting Latent CoT Reasoning as Dynamical Systems
Interpreting Latent CoT Reasoning as Dynamical Systems
cs.LG updates on arXiv.org
Model Collapse: On Recursion, Noise, and Uncharted Machine Visions
Model Collapse: On Recursion, Noise, and Uncharted Machine Visions
cs.LG updates on arXiv.org
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate
cs.LG updates on arXiv.org
GES-TSP: Graph Edge Sparsification for TSP
GES-TSP: Graph Edge Sparsification for TSP
cs.LG updates on arXiv.org
Saturation-Aware Robust Trajectory Optimization for Reusable Launch Vehicles via Differentiable Physics
Saturation-Aware Robust Trajectory Optimization for Reusable Launch Vehicles via Differentiable Physics
cs.LG updates on arXiv.org
Q-Score: A Quantum-Native Scoring Function for Molecular Docking
Q-Score: A Quantum-Native Scoring Function for Molecular Docking
cs.LG updates on arXiv.org
SupplyNetPy: An Open-Source Python Library for High-Fidelity Modeling and Simulation of Arbitrary Supply Chain and Inventory Networks
SupplyNetPy: An Open-Source Python Library for High-Fidelity Modeling and Simulation of Arbitrary Supply Chain and Inventory Networks
cs.LG updates on arXiv.org
MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry Waveforms
MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry Waveforms
cs.LG updates on arXiv.org
Task-Conditioned Synthetic Data Generation for Improving Machine Learning Performance in Agricultural Prediction Tasks
Task-Conditioned Synthetic Data Generation for Improving Machine Learning Performance in Agricultural Prediction Tasks
cs.LG updates on arXiv.org
Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis
Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis
cs.LG updates on arXiv.org
Cross-Subject Modeling for Widefield Calcium Imaging via Atlas-Aligned Spatiotemporal Tokenization
Cross-Subject Modeling for Widefield Calcium Imaging via Atlas-Aligned Spatiotemporal Tokenization
cs.LG updates on arXiv.org
Knowledge-Constrained Shape Optimization with a Mixture-of-Experts Neural Operator for High-Confidence Design
Knowledge-Constrained Shape Optimization with a Mixture-of-Experts Neural Operator for High-Confidence Design
cs.LG updates on arXiv.org
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
cs.LG updates on arXiv.org
A Risk-Field Enhanced Closed-Loop Digital Twin Framework for Autonomous Driving Safety Validation
A Risk-Field Enhanced Closed-Loop Digital Twin Framework for Autonomous Driving Safety Validation
cs.LG updates on arXiv.org
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
cs.LG updates on arXiv.org
Towards Real-World Wearable Motion Reconstruction
Towards Real-World Wearable Motion Reconstruction
cs.LG updates on arXiv.org
Length Penalties Make Chain-of-Thought Less Monitorable
Length Penalties Make Chain-of-Thought Less Monitorable
cs.LG updates on arXiv.org
Adversarially Guided Diffusion for LiDAR Range Image Synthesis
Adversarially Guided Diffusion for LiDAR Range Image Synthesis
cs.LG updates on arXiv.org
MVMGNN;Multi-View Masked Graph Neural Network for Alzheimer's Disease Diagnosis using Structural MRI
MVMGNN;Multi-View Masked Graph Neural Network for Alzheimer's Disease Diagnosis using Structural MRI
cs.LG updates on arXiv.org
CHM-Net: Center Heatmap-driven Macro-Micro Modeling Network for MRI-based Microbial Density Stratification
CHM-Net: Center Heatmap-driven Macro-Micro Modeling Network for MRI-based Microbial Density Stratification
cs.LG updates on arXiv.org
Generative Testing of Automated Speech Recognition Systems
Generative Testing of Automated Speech Recognition Systems
cs.LG updates on arXiv.org
ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning
ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning
cs.LG updates on arXiv.org
An End-to-End Hybrid Quantum--Classical Sampling Workflow for Discrete Markov Random Fields: A Reproducible Case Study
An End-to-End Hybrid Quantum--Classical Sampling Workflow for Discrete Markov Random Fields: A Reproducible Case Study
cs.LG updates on arXiv.org
When Classical Baselines Are Tuned as Carefully as the Quantum Model, Does Quantum Reservoir Computing Still Win?
When Classical Baselines Are Tuned as Carefully as the Quantum Model, Does Quantum Reservoir Computing Still Win?
cs.LG updates on arXiv.org
Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress
Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress
cs.LG updates on arXiv.org
Learning Partition Trees for Nearest Neighbor Search
Learning Partition Trees for Nearest Neighbor Search
cs.LG updates on arXiv.org
Artificial Intelligence Across the Cardiac Amyloidosis Diagnostic Pathway: From Single-Modality Detection to Multimodal Clinical Integration
Artificial Intelligence Across the Cardiac Amyloidosis Diagnostic Pathway: From Single-Modality Detection to Multimodal Clinical Integration
cs.LG updates on arXiv.org
A Knowledge-Based Multi-Agent Framework for Security Control Recommendation
A Knowledge-Based Multi-Agent Framework for Security Control Recommendation
cs.LG updates on arXiv.org
Inverse-IMPRESSION: A Graph-based Platform for Molecular Structure Elucidation from Experimental NMR Spectroscopic Properties
Inverse-IMPRESSION: A Graph-based Platform for Molecular Structure Elucidation from Experimental NMR Spectroscopic Properties
cs.LG updates on arXiv.org
Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information
Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information
cs.LG updates on arXiv.org
Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts
Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts
cs.LG updates on arXiv.org
Manifold Constrained Conformal Prediction for Spatial Events
Manifold Constrained Conformal Prediction for Spatial Events
cs.LG updates on arXiv.org
Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation
Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation
cs.LG updates on arXiv.org
Tokenizing Numerical and Embedding Features for LLM RecSys
Tokenizing Numerical and Embedding Features for LLM RecSys
cs.LG updates on arXiv.org
A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution
A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution
cs.LG updates on arXiv.org
Local Multimodal Music Alignment from Global Supervision
Local Multimodal Music Alignment from Global Supervision
cs.LG updates on arXiv.org
Robustly Invertible Nonlinear Dynamics and the BiLipREN: From Inversion-Based Control to Generative Trajectory Modelling
Robustly Invertible Nonlinear Dynamics and the BiLipREN: From Inversion-Based Control to Generative Trajectory Modelling
cs.LG updates on arXiv.org
Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough
Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough
cs.LG updates on arXiv.org
DynaFilter: Cloud-driven Dynamic Filtering for Satellite Edge Intelligence
DynaFilter: Cloud-driven Dynamic Filtering for Satellite Edge Intelligence
cs.LG updates on arXiv.org
Adaptive Model Compression (AMC): Saliency-Driven Resource Allocation for Ultra-Low-Power Transformer Inference
Adaptive Model Compression (AMC): Saliency-Driven Resource Allocation for Ultra-Low-Power Transformer Inference
cs.LG updates on arXiv.org
Cost of Reasoning in non-English Languages: A Case Study on Japanese
Cost of Reasoning in non-English Languages: A Case Study on Japanese
cs.LG updates on arXiv.org
On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation
On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation
cs.LG updates on arXiv.org
Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices
Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices
cs.LG updates on arXiv.org
BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography
BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography
cs.LG updates on arXiv.org
How much Data do We Need? Sequential Data Collection for Stochastic Programming
How much Data do We Need? Sequential Data Collection for Stochastic Programming
cs.LG updates on arXiv.org
MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck
MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck
cs.LG updates on arXiv.org
One mechanism for many mental spaces: a shared router over a value slot in language models
One mechanism for many mental spaces: a shared router over a value slot in language models
cs.LG updates on arXiv.org
One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions
One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions
cs.LG updates on arXiv.org
Byzantine Accountability Without Consensus: Strong Eventual Consistency for Non-Associative, Stochastic, Robust Aggregation
Byzantine Accountability Without Consensus: Strong Eventual Consistency for Non-Associative, Stochastic, Robust Aggregation
cs.LG updates on arXiv.org
Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers
Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers
cs.LG updates on arXiv.org
Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models
Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models
cs.LG updates on arXiv.org
Vertical Fusion: Condensing Internal Representations for Robust ViT Classification
Vertical Fusion: Condensing Internal Representations for Robust ViT Classification
cs.LG updates on arXiv.org
TVT-PAPD: Pathology-Aware Prototype Distillation for Self-Supervised Whole Slide Image Classification
TVT-PAPD: Pathology-Aware Prototype Distillation for Self-Supervised Whole Slide Image Classification
cs.LG updates on arXiv.org
TSCoNet: A Two-Stage Copula CNN-LSTM for Uncertainty-Aware Spatio-Temporal Forecasting
TSCoNet: A Two-Stage Copula CNN-LSTM for Uncertainty-Aware Spatio-Temporal Forecasting
cs.LG updates on arXiv.org
SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering
SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering
cs.LG updates on arXiv.org
Is Model Instability just Noise to be Tolerated or a Property that can be Managed?
Is Model Instability just Noise to be Tolerated or a Property that can be Managed?
cs.LG updates on arXiv.org
Emergent Generalization by Representation Learning in Artificial Neural Networks
Emergent Generalization by Representation Learning in Artificial Neural Networks
cs.LG updates on arXiv.org
Integrating Background Knowledge for Scalable Causal Discovery
Integrating Background Knowledge for Scalable Causal Discovery
cs.LG updates on arXiv.org
Toward Production-Ready Federated Learning in Healthcare: Privacy, Orchestration, and Governance in MLOps
Toward Production-Ready Federated Learning in Healthcare: Privacy, Orchestration, and Governance in MLOps
cs.LG updates on arXiv.org
Hallucination Detection in Large Language Models Using Diversion Decoding
Hallucination Detection in Large Language Models Using Diversion Decoding
cs.LG updates on arXiv.org
Fast Data-Driven Modeling of Hydraulic Clutch Control Pressure with Latch-State Classification and Gaussian Process Regression
Fast Data-Driven Modeling of Hydraulic Clutch Control Pressure with Latch-State Classification and Gaussian Process Regression
cs.LG updates on arXiv.org
NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations
NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations
cs.LG updates on arXiv.org
Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach
Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach
cs.LG updates on arXiv.org
Representation Learning for Semiparametric Causal Mediation Analysis under No Essential Heterogeneity
Representation Learning for Semiparametric Causal Mediation Analysis under No Essential Heterogeneity
cs.LG updates on arXiv.org
RecRec: Recursive Refinement for Sequential Recommendation
RecRec: Recursive Refinement for Sequential Recommendation
cs.LG updates on arXiv.org
Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering
Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering
cs.LG updates on arXiv.org
Projection-Domain Sensitivity Analysis of Vertebral DRRs Under Intrinsic Calibration Perturbation
Projection-Domain Sensitivity Analysis of Vertebral DRRs Under Intrinsic Calibration Perturbation
cs.LG updates on arXiv.org
Observation-Level Watermarking and Detection for Tabular Data
Observation-Level Watermarking and Detection for Tabular Data
cs.LG updates on arXiv.org
BucketKD: A Safety-Aware Bucket-Based Knowledge Distillation Framework for End-to-End Motion Planning
BucketKD: A Safety-Aware Bucket-Based Knowledge Distillation Framework for End-to-End Motion Planning
cs.LG updates on arXiv.org
When Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design Ablation
When Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design Ablation
cs.LG updates on arXiv.org
Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width
Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width
cs.LG updates on arXiv.org
End-to-End Real-Time Drone-Based Person Detection Framework Using Deep Learning
End-to-End Real-Time Drone-Based Person Detection Framework Using Deep Learning
cs.LG updates on arXiv.org
Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization
Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization
cs.LG updates on arXiv.org
Learning Topological Quantum Phases from Limited Subsystems
Learning Topological Quantum Phases from Limited Subsystems
cs.LG updates on arXiv.org
Edge Cluster Expansion with Radial Rotary Attention for Interatomic Potentials
Edge Cluster Expansion with Radial Rotary Attention for Interatomic Potentials
cs.LG updates on arXiv.org
Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs
Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs
cs.LG updates on arXiv.org
Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classification
Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classification
cs.LG updates on arXiv.org
MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and Confidence-Gated Recovery
MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and Confidence-Gated Recovery
cs.LG updates on arXiv.org
WattCouncil: Context-Aware Household Energy Scenario Generation With Governed LLMs
WattCouncil: Context-Aware Household Energy Scenario Generation With Governed LLMs
cs.LG updates on arXiv.org
Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF
Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF
cs.LG updates on arXiv.org
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
cs.LG updates on arXiv.org
Lightning Fast Matching Dependency Discovery with Desbordante
Lightning Fast Matching Dependency Discovery with Desbordante
cs.LG updates on arXiv.org
Toward Efficient Weakly Supervised Semantic Segmentation Using Only Low-Magnification Histopathological Images
Toward Efficient Weakly Supervised Semantic Segmentation Using Only Low-Magnification Histopathological Images
cs.LG updates on arXiv.org
Q-Learning Lab: Teaching Reinforcement Learning Through Learner-Generated Trace Analysis
Q-Learning Lab: Teaching Reinforcement Learning Through Learner-Generated Trace Analysis
cs.LG updates on arXiv.org
Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation
Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation
cs.LG updates on arXiv.org
Large Language Models for Token-Efficient and Semantic-Preserving Opinion Summarization
Large Language Models for Token-Efficient and Semantic-Preserving Opinion Summarization
cs.LG updates on arXiv.org
Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning
Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning
cs.LG updates on arXiv.org
Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting
Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting
cs.LG updates on arXiv.org
Transferable Implicit Solvent Machine Learning Potential for Drugs and Proteins Approaching Ab Initio Accuracy
Transferable Implicit Solvent Machine Learning Potential for Drugs and Proteins Approaching Ab Initio Accuracy
cs.LG updates on arXiv.org
ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation
ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation
cs.LG updates on arXiv.org
Normative Alignment of Recommender Systems via Internal Label Shift
Normative Alignment of Recommender Systems via Internal Label Shift
cs.LG updates on arXiv.org
Fast Whole-Brain, Geometry-Aware Functional Alignment for Cross-Subject Decoding
Fast Whole-Brain, Geometry-Aware Functional Alignment for Cross-Subject Decoding
cs.LG updates on arXiv.org
CGS: Configurable Graph Summarization with Bounded Neighborhood Loss and Query Support
CGS: Configurable Graph Summarization with Bounded Neighborhood Loss and Query Support
cs.LG updates on arXiv.org
EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion
EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion
cs.LG updates on arXiv.org
Actor-Critic Learning for Extended Mean Field Control with Deterministic Policies
Actor-Critic Learning for Extended Mean Field Control with Deterministic Policies
cs.LG updates on arXiv.org
Overcoming Fourier Locking in Quantum Data Re-uploading Classifiers via Spectral Homotopy
Overcoming Fourier Locking in Quantum Data Re-uploading Classifiers via Spectral Homotopy
cs.LG updates on arXiv.org
Can a Language Model Learn Facts Continually in Its Weights?
Can a Language Model Learn Facts Continually in Its Weights?
cs.LG updates on arXiv.org
Reference-Based Face Super-Resolution Using the Spatial Transformer
Reference-Based Face Super-Resolution Using the Spatial Transformer
cs.LG updates on arXiv.org
MMRM: A Multiplex Multimodal Representation Model for Product Ranking in E-commerce Search
MMRM: A Multiplex Multimodal Representation Model for Product Ranking in E-commerce Search
cs.LG updates on arXiv.org
When cheap gradients fail: the measurement cost of attacking quantum classifiers
When cheap gradients fail: the measurement cost of attacking quantum classifiers
cs.LG updates on arXiv.org
Implicit Neural Networks as Static Controllers: Certificates and Performance Separation
Implicit Neural Networks as Static Controllers: Certificates and Performance Separation
cs.LG updates on arXiv.org
Comparison-Based Ordinal Learning for Proactive Driving Risk Assessment
Comparison-Based Ordinal Learning for Proactive Driving Risk Assessment
cs.LG updates on arXiv.org
A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery
A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery
cs.LG updates on arXiv.org
Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation
Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation
cs.LG updates on arXiv.org
STAMP: Provenance-Guided Credit Assignment for Deep Search Agents
STAMP: Provenance-Guided Credit Assignment for Deep Search Agents
cs.LG updates on arXiv.org
PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection
PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection
cs.LG updates on arXiv.org
LaGuadia: Language-Guided Adaptive Distillation from Pathology Foundation Models
LaGuadia: Language-Guided Adaptive Distillation from Pathology Foundation Models
cs.LG updates on arXiv.org
Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans
Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans
cs.LG updates on arXiv.org
Long-Memory Reservoir Computing for Data-Scarce Dengue Forecasting
Long-Memory Reservoir Computing for Data-Scarce Dengue Forecasting
cs.LG updates on arXiv.org
Fixed-Protocol Amortized MPS Tomography with Conformalized Predictive Uncertainty
Fixed-Protocol Amortized MPS Tomography with Conformalized Predictive Uncertainty
cs.LG updates on arXiv.org
Backpropagation as a Nilpotent Linear System
Backpropagation as a Nilpotent Linear System
cs.LG updates on arXiv.org
Inter-Stop Energy Prediction and Causal Driver Quantification for Dual-Source Trolleybuses via a Time-Aware Tabular Deep Learning Architecture
Inter-Stop Energy Prediction and Causal Driver Quantification for Dual-Source Trolleybuses via a Time-Aware Tabular Deep Learning Architecture
cs.LG updates on arXiv.org
Characterising AI Models for Cataloguing
Characterising AI Models for Cataloguing
cs.LG updates on arXiv.org
Decomposing Runtime, Kernel, and Quantization Speedups via a Matched FP16 Intermediate: A Hardware-Conditioned Case Study on Four NVIDIA RTX A5000 GPUs
Decomposing Runtime, Kernel, and Quantization Speedups via a Matched FP16 Intermediate: A Hardware-Conditioned Case Study on Four NVIDIA RTX A5000 GPUs
cs.LG updates on arXiv.org
StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
cs.LG updates on arXiv.org
Climate-Invariant Conformal Prediction Intervals for Multi-Horizon Solar and Wind Forecasting
Climate-Invariant Conformal Prediction Intervals for Multi-Horizon Solar and Wind Forecasting
cs.LG updates on arXiv.org
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
cs.LG updates on arXiv.org
Compound Interference Recognition for LR-FHSS Satellite IoT Uplinks via Multi-Domain Instance Fusion
Compound Interference Recognition for LR-FHSS Satellite IoT Uplinks via Multi-Domain Instance Fusion
cs.LG updates on arXiv.org
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
cs.LG updates on arXiv.org
Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction
Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction
cs.LG updates on arXiv.org
Tropical Circuits with Scalar Multiplication Gates
Tropical Circuits with Scalar Multiplication Gates
cs.LG updates on arXiv.org
Training-Free Off-Screen Player Imputation for Broadcast-Based Spatial Football Analytics
Training-Free Off-Screen Player Imputation for Broadcast-Based Spatial Football Analytics
cs.LG updates on arXiv.org
Machine Learning-Based Reconstruction for Resistive Silicon Sensors
Machine Learning-Based Reconstruction for Resistive Silicon Sensors
cs.LG updates on arXiv.org
Globally Consistent Coloring Schemes for Language Identification
Globally Consistent Coloring Schemes for Language Identification
cs.LG updates on arXiv.org
Auditing the Risk Claims of Distributional Reinforcement Learning
Auditing the Risk Claims of Distributional Reinforcement Learning
cs.LG updates on arXiv.org
Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns
Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns
cs.LG updates on arXiv.org
SKooP: Symmetric Koopman Predictions for Faster and More Generalizable Legged Robot Locomotion with Reinforcement Learning
SKooP: Symmetric Koopman Predictions for Faster and More Generalizable Legged Robot Locomotion with Reinforcement Learning
cs.LG updates on arXiv.org
Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling
Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling
cs.LG updates on arXiv.org
Imputation-free transformer learning enables robust Alzheimer's disease prediction and calibrated uncertainty quantification across heterogeneous clinical cohorts
Imputation-free transformer learning enables robust Alzheimer's disease prediction and calibrated uncertainty quantification across heterogeneous clinical cohorts
cs.LG updates on arXiv.org
Diversified Multinomial Logit Contextual Bandits
Diversified Multinomial Logit Contextual Bandits
cs.LG updates on arXiv.org
Self-Healing Visual Recovery for Autonomous Ground Vehicles Using Camera-Only Visual Odometry
Self-Healing Visual Recovery for Autonomous Ground Vehicles Using Camera-Only Visual Odometry
cs.LG updates on arXiv.org
$\mathtt{Q^2SAR}$: overcoming classical bottlenecks in drug discovery via quantum multiple kernel learning
$\mathtt{Q^2SAR}$: overcoming classical bottlenecks in drug discovery via quantum multiple kernel learning
cs.LG updates on arXiv.org
NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception
NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception
cs.LG updates on arXiv.org
When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
cs.LG updates on arXiv.org
Paradoxes of Game Theoretic Equilibria and Price of Anarchy
Paradoxes of Game Theoretic Equilibria and Price of Anarchy
cs.LG updates on arXiv.org
Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks
Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks
cs.LG updates on arXiv.org
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol
cs.LG updates on arXiv.org
A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation
A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation
cs.LG updates on arXiv.org
Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards
Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards
cs.LG updates on arXiv.org
Federated Topic Model and Model Pruning Based on Variational Autoencoder
Federated Topic Model and Model Pruning Based on Variational Autoencoder
cs.LG updates on arXiv.org
Randomized Confidence Bounds for Stochastic Partial Monitoring
Randomized Confidence Bounds for Stochastic Partial Monitoring
cs.LG updates on arXiv.org
Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms
Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms
cs.LG updates on arXiv.org
Neural Active Learning Meets the Partial Monitoring Framework
Neural Active Learning Meets the Partial Monitoring Framework
cs.LG updates on arXiv.org
Constrained Reinforcement Learning for Safe Heat Pump Control
Constrained Reinforcement Learning for Safe Heat Pump Control
cs.LG updates on arXiv.org
Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs
Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs
cs.LG updates on arXiv.org
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
cs.LG updates on arXiv.org
Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations
Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations
cs.LG updates on arXiv.org
Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization
Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization
cs.LG updates on arXiv.org
Meta-Dependence in Conditional Independence Testing
Meta-Dependence in Conditional Independence Testing
cs.LG updates on arXiv.org
Riemannian Denoising Diffusion Probabilistic Models
Riemannian Denoising Diffusion Probabilistic Models
cs.LG updates on arXiv.org
A Learning-Based Ansatz Satisfying Boundary Conditions in Variational Problems
A Learning-Based Ansatz Satisfying Boundary Conditions in Variational Problems
cs.LG updates on arXiv.org
Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning
Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning
cs.LG updates on arXiv.org
Adaptive Reinforcement Learning for Unobservable Random Delays
Adaptive Reinforcement Learning for Unobservable Random Delays
cs.LG updates on arXiv.org
On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
cs.LG updates on arXiv.org
Memory Savings at What Cost? A Study of Alternatives to Backpropagation
Memory Savings at What Cost? A Study of Alternatives to Backpropagation
cs.LG updates on arXiv.org
Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion
Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion
cs.LG updates on arXiv.org
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
cs.LG updates on arXiv.org
Beyond Na\"ive Prompting: Strategies for Improved Context-aided Forecasting with LLMs
Beyond Na\"ive Prompting: Strategies for Improved Context-aided Forecasting with LLMs
cs.LG updates on arXiv.org
Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
cs.LG updates on arXiv.org
A Data-Driven Interpolation Method on Smooth Manifolds via Diffusion Processes and Voronoi Tessellations
A Data-Driven Interpolation Method on Smooth Manifolds via Diffusion Processes and Voronoi Tessellations
cs.LG updates on arXiv.org
Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints
Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints