General Flexible $f$-divergence for Challenging Offline RL Datasets with Low Stochasticity and Diverse Behavior Policies
Direct Learning of Calibration-Aware Uncertainty for Neural PDE Surrogates
MerLin: A Discovery Engine for Photonic and Hybrid Quantum Machine Learning
Statistical Learning Analysis of Physics-Informed Neural Networks
From Natural Language to Materials Discovery:The Materials Knowledge Navigation Agent
The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization
Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards
From Circuits to Dynamics: Understanding and Stabilizing Failure in 3D Diffusion Transformers
Just on Time: Token-Level Early Stopping for Diffusion Language Models
Weight Decay Improves Language Model Plasticity
TabICLv2: A better, faster, scalable, and open tabular foundation model
GENIUS: Generative Fluid Intelligence Evaluation Suite
Diffusion-Pretrained Dense and Contextual Embeddings
Enhancing IMU-Based Online Handwriting Recognition via Contrastive Learning with Zero Inference Overhead
Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement
When LLMs get significantly worse: A statistical approach to detect model degradations
Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol
Basic Legibility Protocols Improve Trusted Monitoring
STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations
Beyond Closed-Pool Video Retrieval: A Benchmark and Agent Framework for Real-World Video Search and Moment Localization
EVA: Towards a universal model of the immune system
Dissecting Performative Prediction: A Comprehensive Survey
ACE-RTL: When Agentic Context Evolution Meets RTL-Specialized LLMs
Learning to Evict from Key-Value Cache
Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
Flow Matching with Uncertainty Quantification and Guidance
Are More Tokens Rational? Inference-Time Scaling in Language Models as Adaptive Resource Rationality
Efficient reduction of stellar contamination and noise in planetary transmission spectra using neural networks
Conditional Uncertainty-Aware Political Deepfake Detection with Stochastic Convolutional Neural Networks
Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models
Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
Physically Interpretable AlphaEarth Foundation Model Embeddings Enable LLM-Based Land Surface Intelligence
Causal Effect Estimation with Learned Instrument Representations
Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores
Towards Affordable, Non-Invasive Real-Time Hypoglycemia Detection Using Wearable Sensor Signals
End-to-End Semantic ID Generation for Generative Advertisement Recommendation
Distributed Online Convex Optimization with Nonseparable Costs and Constraints
Compute Only Once: UG-Separation for Efficient Large Recommendation Models
Found-RL: foundation model-enhanced reinforcement learning for autonomous driving
Unlocked Backpropagation using Wave Scattering
Online Generalized-mean Welfare Maximization: Achieving Near-Optimal Regret from Samples
GPU-Fuzz: Finding Memory Errors in Deep Learning Frameworks
Pricing Query Complexity of Multiplicative Revenue Approximation
Privacy-Utility Tradeoffs in Quantum Information Processing
Co-jump: Cooperative Jumping with Quadrupedal Robots via Multi-Agent Reinforcement Learning
LHAW: Controllable Underspecification for Long-Horizon Tasks
Generalized Robust Adaptive-Bandwidth Multi-View Manifold Learning in High Dimensions with Noise
From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models