2d ago 90
Learning-based agricultural management in partially observable environments subject to climate variability
Learning-based agricultural management in partially observable environments subject to climate variability
2d ago 90
Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks
Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks
2d ago 90
Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spaces
Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spaces
2d ago 90
Kernel-based Optimally Weighted Conformal Time-Series Prediction
Kernel-based Optimally Weighted Conformal Time-Series Prediction
2d ago 90
IGC-Net for conditional average potential outcome estimation over time
IGC-Net for conditional average potential outcome estimation over time
2d ago 90
Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models
Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models
2d ago 90
Measuring Orthogonality as the Blind-Spot of Uncertainty Disentanglement
Measuring Orthogonality as the Blind-Spot of Uncertainty Disentanglement
2d ago 90
Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
2d ago 90
Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
2d ago 90
Hypercube Policy Regularization Framework for Offline Reinforcement Learning
Hypercube Policy Regularization Framework for Offline Reinforcement Learning
2d ago 90
HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems
HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems
2d ago 90
Rethinking Approximate Gaussian Inference in Classification
Rethinking Approximate Gaussian Inference in Classification
2d ago 90
Iterative Importance Fine-tuning of Diffusion Models
Iterative Importance Fine-tuning of Diffusion Models
2d ago 90
From Belief Entrenchment to Robust Reasoning in LLM Agents
From Belief Entrenchment to Robust Reasoning in LLM Agents
2d ago 90
ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model
ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model
2d ago 90
Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning
Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning
2d ago 90
Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
2d ago 90
On Transferring Transferability: Towards a Theory for Size Generalization
On Transferring Transferability: Towards a Theory for Size Generalization
2d ago 90
Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures
Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures
2d ago 90
Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization
Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization
2d ago 90
Adapt before Continual Learning
Adapt before Continual Learning
2d ago 90
Tailored Behavior-Change Messaging for Physical Activity: Integrating Contextual Bandits and Large Language Models
Tailored Behavior-Change Messaging for Physical Activity: Integrating Contextual Bandits and Large Language Models
2d ago 90
Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
2d ago 90
Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
2d ago 90
Uncertainty-driven Embedding Convolution
Uncertainty-driven Embedding Convolution
2d ago 90
Deep Network Trainability via Persistent Subspace Orthogonality
Deep Network Trainability via Persistent Subspace Orthogonality
2d ago 90
Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictors
Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictors
2d ago 90
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
2d ago 90
MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
2d ago 90
Semantic-Enhanced Time-Series Forecasting via Large Language Models
Semantic-Enhanced Time-Series Forecasting via Large Language Models
2d ago 90
Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning
Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning
2d ago 90
Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
2d ago 90
The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
2d ago 90
ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
2d ago 90
A Law of Data Reconstruction for Random Features (and Beyond)
A Law of Data Reconstruction for Random Features (and Beyond)
2d ago 90
Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
2d ago 90
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
2d ago 90
Discrete Variational Autoencoding via Policy Search
Discrete Variational Autoencoding via Policy Search
2d ago 90
GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
2d ago 90
ACT: Agentic Classification Tree
ACT: Agentic Classification Tree
2d ago 90
Lipschitz Bandits with Stochastic Delayed Feedback
Lipschitz Bandits with Stochastic Delayed Feedback
2d ago 90
Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
2d ago 90
LLM Priors for ERM over Programs
LLM Priors for ERM over Programs
2d ago 90
Provably Optimal Reinforcement Learning under Safety Filtering
Provably Optimal Reinforcement Learning under Safety Filtering
2d ago 90
Position: Many generalization measures for deep learning are fragile
Position: Many generalization measures for deep learning are fragile
2d ago 90
Overlap-weighted orthogonal meta-learner for treatment effect estimation over time
Overlap-weighted orthogonal meta-learner for treatment effect estimation over time
2d ago 90
SeeDNorm: Self-Rescaled Dynamic Normalization
SeeDNorm: Self-Rescaled Dynamic Normalization
2d ago 90
Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
2d ago 90
Finding Kissing Numbers with Game-theoretic Reinforcement Learning
Finding Kissing Numbers with Game-theoretic Reinforcement Learning
2d ago 90
KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits
KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits