1d ago 90
Generative clinical time series models trained on moderate amounts of patient data are privacy preserving
Generative clinical time series models trained on moderate amounts of patient data are privacy preserving
1d ago 90
Coarse-Grained Boltzmann Generators
Coarse-Grained Boltzmann Generators
1d ago 90
Evaluation metrics for temporal preservation in synthetic longitudinal patient data
Evaluation metrics for temporal preservation in synthetic longitudinal patient data
1d ago 90
Domain Knowledge Guided Bayesian Optimization For Autonomous Alignment Of Complex Scientific Instruments
Domain Knowledge Guided Bayesian Optimization For Autonomous Alignment Of Complex Scientific Instruments
1d ago 90
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
1d ago 90
Reducing Estimation Uncertainty Using Normalizing Flows and Stratification
Reducing Estimation Uncertainty Using Normalizing Flows and Stratification
1d ago 90
Interpretable Graph-Level Anomaly Detection via Contrast with Normal Prototypes
Interpretable Graph-Level Anomaly Detection via Contrast with Normal Prototypes
1d ago 90
SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
1d ago 90
Rising Multi-Armed Bandits with Known Horizons
Rising Multi-Armed Bandits with Known Horizons
1d ago 90
Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking
Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking
1d ago 90
Predicting integers from continuous parameters
Predicting integers from continuous parameters
1d ago 90
Exploring the impact of adaptive rewiring in Graph Neural Networks
Exploring the impact of adaptive rewiring in Graph Neural Networks
1d ago 90
Collaborative Threshold Watermarking
Collaborative Threshold Watermarking
1d ago 90
LOREN: Low Rank-Based Code-Rate Adaptation in Neural Receivers
LOREN: Low Rank-Based Code-Rate Adaptation in Neural Receivers
1d ago 90
Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networks
Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networks
1d ago 90
Semi-Supervised Cross-Domain Imitation Learning
Semi-Supervised Cross-Domain Imitation Learning
1d ago 90
Transport, Don't Generate: Deterministic Geometric Flows for Combinatorial Optimization
Transport, Don't Generate: Deterministic Geometric Flows for Combinatorial Optimization
1d ago 90
PRISM: Parallel Residual Iterative Sequence Model
PRISM: Parallel Residual Iterative Sequence Model
1d ago 90
RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization
RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization
1d ago 90
Adaptive Sampling for Private Worst-Case Group Optimization
Adaptive Sampling for Private Worst-Case Group Optimization
1d ago 90
SimuScene: Training and Benchmarking Code Generation to Simulate Physical Scenarios
SimuScene: Training and Benchmarking Code Generation to Simulate Physical Scenarios
1d ago 90
Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval
Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval
1d ago 90
Time Series Foundation Models for Energy Load Forecasting on Consumer Hardware: A Multi-Dimensional Zero-Shot Benchmark
Time Series Foundation Models for Energy Load Forecasting on Consumer Hardware: A Multi-Dimensional Zero-Shot Benchmark
1d ago 90
Automated Model Design using Gated Neuron Selection in Telecom
Automated Model Design using Gated Neuron Selection in Telecom
1d ago 90
ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking Agents
ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking Agents
1d ago 90
The Sample Complexity of Uniform Approximation for Multi-Dimensional CDFs and Fixed-Price Mechanisms
The Sample Complexity of Uniform Approximation for Multi-Dimensional CDFs and Fixed-Price Mechanisms
1d ago 90
FedPS: Federated data Preprocessing via aggregated Statistics
FedPS: Federated data Preprocessing via aggregated Statistics
1d ago 90
Resource-Efficient Model-Free Reinforcement Learning for Board Games
Resource-Efficient Model-Free Reinforcement Learning for Board Games
1d ago 90
Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
1d ago 90
Tuning the burn-in phase in training recurrent neural networks improves their performance
Tuning the burn-in phase in training recurrent neural networks improves their performance
1d ago 90
Near-Constant Strong Violation and Last-Iterate Convergence for Online CMDPs via Decaying Safety Margins
Near-Constant Strong Violation and Last-Iterate Convergence for Online CMDPs via Decaying Safety Margins
1d ago 90
Spatial-Morphological Modeling for Multi-Attribute Imputation of Urban Blocks
Spatial-Morphological Modeling for Multi-Attribute Imputation of Urban Blocks
1d ago 90
CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control
CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control
1d ago 90
Stochastic Parroting in Temporal Attention -- Regulating the Diagonal Sink
Stochastic Parroting in Temporal Attention -- Regulating the Diagonal Sink
1d ago 90
Rotary Positional Embeddings as Phase Modulation: Theoretical Bounds on the RoPE Base for Long-Context Transformers
Rotary Positional Embeddings as Phase Modulation: Theoretical Bounds on the RoPE Base for Long-Context Transformers
1d ago 90
MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs
MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs
1d ago 90
A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions
A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions
1d ago 90
RiemannGL: Riemannian Geometry Changes Graph Deep Learning
RiemannGL: Riemannian Geometry Changes Graph Deep Learning
1d ago 90
Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
1d ago 90
TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents
TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents
1d ago 90
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
1d ago 90
OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories
OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories
1d ago 90
When Fusion Helps and When It Breaks: View-Aligned Robustness in Same-Source Financial Imaging
When Fusion Helps and When It Breaks: View-Aligned Robustness in Same-Source Financial Imaging
1d ago 90
Learning Page Order in Shuffled WOO Releases
Learning Page Order in Shuffled WOO Releases
1d ago 90
Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models
Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models
1d ago 90
MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation
MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation
1d ago 90
Motion Capture is Not the Target Domain: Scaling Synthetic Data for Learning Motion Representations
Motion Capture is Not the Target Domain: Scaling Synthetic Data for Learning Motion Representations
1d ago 90
In-the-Wild Model Organisms: Mitigating Undesirable Emergent Behaviors in Production LLM Post-Training via Data Attribution
In-the-Wild Model Organisms: Mitigating Undesirable Emergent Behaviors in Production LLM Post-Training via Data Attribution
1d ago 90
Token-Efficient Change Detection in LLM APIs
Token-Efficient Change Detection in LLM APIs
1d ago 90
GRASP: group-Shapley feature selection for patients
GRASP: group-Shapley feature selection for patients