1d ago 90
Simple LLM Baselines are Competitive for Model Diffing
Simple LLM Baselines are Competitive for Model Diffing
1d ago 90
Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs
Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs
1d ago 90
Deep learning outperforms traditional machine learning methods in predicting childhood malnutrition: evidence from survey data
Deep learning outperforms traditional machine learning methods in predicting childhood malnutrition: evidence from survey data
1d ago 90
Time-to-Event Transformer to Capture Timing Attention of Events in EHR Time Series
Time-to-Event Transformer to Capture Timing Attention of Events in EHR Time Series
1d ago 90
Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models
Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models
1d ago 90
Affordances Enable Partial World Modeling with LLMs
Affordances Enable Partial World Modeling with LLMs
1d ago 90
Tensor Methods: A Unified and Interpretable Approach for Material Design
Tensor Methods: A Unified and Interpretable Approach for Material Design
1d ago 90
Experimental Demonstration of Online Learning-Based Concept Drift Adaptation for Failure Detection in Optical Networks
Experimental Demonstration of Online Learning-Based Concept Drift Adaptation for Failure Detection in Optical Networks
1d ago 90
Modular Multi-Task Learning for Chemical Reaction Prediction
Modular Multi-Task Learning for Chemical Reaction Prediction
1d ago 90
Gated Removal of Normalization in Transformers Enables Stable Training and Efficient Inference
Gated Removal of Normalization in Transformers Enables Stable Training and Efficient Inference
1d ago 90
LUCID: Attention with Preconditioned Representations
LUCID: Attention with Preconditioned Representations
1d ago 90
LightGTS-Cov: Covariate-Enhanced Time Series Forecasting
LightGTS-Cov: Covariate-Enhanced Time Series Forecasting
1d ago 90
AI-rithmetic
AI-rithmetic
1d ago 90
Equivariant Evidential Deep Learning for Interatomic Potentials
Equivariant Evidential Deep Learning for Interatomic Potentials
1d ago 90
Binary Flow Matching: Prediction-Loss Space Alignment for Robust Learning
Binary Flow Matching: Prediction-Loss Space Alignment for Robust Learning
1d ago 90
Breaking the Curse of Repulsion: Optimistic Distributionally Robust Policy Optimization for Off-Policy Generative Recommendation
Breaking the Curse of Repulsion: Optimistic Distributionally Robust Policy Optimization for Off-Policy Generative Recommendation
1d ago 90
QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
1d ago 90
A Dual-Stream Physics-Augmented Unsupervised Architecture for Runtime Embedded Vehicle Health Monitoring
A Dual-Stream Physics-Augmented Unsupervised Architecture for Runtime Embedded Vehicle Health Monitoring
1d ago 90
Control Reinforcement Learning: Token-Level Mechanistic Analysis via Learned SAE Feature Steering
Control Reinforcement Learning: Token-Level Mechanistic Analysis via Learned SAE Feature Steering
1d ago 90
LakeMLB: Data Lake Machine Learning Benchmark
LakeMLB: Data Lake Machine Learning Benchmark
1d ago 90
Chamfer-Linkage for Hierarchical Agglomerative Clustering
Chamfer-Linkage for Hierarchical Agglomerative Clustering
1d ago 90
A Unified Theory of Random Projection for Influence Functions
A Unified Theory of Random Projection for Influence Functions
1d ago 90
Constructing Industrial-Scale Optimization Modeling Benchmark
Constructing Industrial-Scale Optimization Modeling Benchmark
1d ago 90
A Multimodal Conditional Mixture Model with Distribution-Level Physics Priors
A Multimodal Conditional Mixture Model with Distribution-Level Physics Priors
1d ago 90
Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation
Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation
1d ago 90
Driving Reaction Trajectories via Latent Flow Matching
Driving Reaction Trajectories via Latent Flow Matching
1d ago 90
Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
1d ago 90
Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
1d ago 90
Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web
Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web
1d ago 90
Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation
Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation
1d ago 90
Don't Eliminate Cut: Exponential Separations in LLM-Based Theorem Proving
Don't Eliminate Cut: Exponential Separations in LLM-Based Theorem Proving
1d ago 90
Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models
Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models
1d ago 90
A Swap-Adversarial Framework for Improving Domain Generalization in Electroencephalography-Based Parkinson's Disease Prediction
A Swap-Adversarial Framework for Improving Domain Generalization in Electroencephalography-Based Parkinson's Disease Prediction
1d ago 90
What Makes Value Learning Efficient in Residual Reinforcement Learning?
What Makes Value Learning Efficient in Residual Reinforcement Learning?
1d ago 90
Bridging the Compression-Precision Paradox: A Hybrid Architecture for Clinical EEG Report Generation with Guaranteed Measurement Accuracy
Bridging the Compression-Precision Paradox: A Hybrid Architecture for Clinical EEG Report Generation with Guaranteed Measurement Accuracy
1d ago 90
$\mu$pscaling small models: Principled warm starts and hyperparameter transfer
$\mu$pscaling small models: Principled warm starts and hyperparameter transfer
1d ago 90
Contrastive Learning for Multi Label ECG Classification with Jaccard Score Based Sigmoid Loss
Contrastive Learning for Multi Label ECG Classification with Jaccard Score Based Sigmoid Loss
1d ago 90
Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points
Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points
1d ago 90
Gauss-Newton Unlearning for the LLM Era
Gauss-Newton Unlearning for the LLM Era
1d ago 90
LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization
LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization
1d ago 90
When Gradient Clipping Becomes a Control Mechanism for Differential Privacy in Deep Learning
When Gradient Clipping Becomes a Control Mechanism for Differential Privacy in Deep Learning
1d ago 90
Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity
Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity
1d ago 90
TRACE: Theoretical Risk Attribution under Covariate-shift Effects
TRACE: Theoretical Risk Attribution under Covariate-shift Effects
1d ago 90
Roughness-Informed Federated Learning
Roughness-Informed Federated Learning
1d ago 90
Learning Mixture Density via Natural Gradient Expectation Maximization
Learning Mixture Density via Natural Gradient Expectation Maximization
1d ago 90
dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
1d ago 90
Hierarchical Zero-Order Optimization for Deep Neural Networks
Hierarchical Zero-Order Optimization for Deep Neural Networks
1d ago 90
On the Role of Consistency Between Physics and Data in Physics-Informed Neural Networks
On the Role of Consistency Between Physics and Data in Physics-Informed Neural Networks
1d ago 90
Pupillometry and Brain Dynamics for Cognitive Load in Working Memory
Pupillometry and Brain Dynamics for Cognitive Load in Working Memory
1d ago 90
Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling