Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learningby Suei-Wen Chen, Keith…
Towards Universal Certified Robustness with Multi-Norm Trainingby Enyi Jiang, David S. Cheung, Gagandeep SinghFirst submitted…
Q-SCALE: Quantum computing-based Sensor Calibration for Advanced Learning and Efficiencyby Lorenzo Bergadano, Andrea Ceschini, Pietro…
MMP: Towards Robust Multi-Modal Learning with Masked Modality Projectionby Niki Nezakati, Md Kaykobad Reza, Ameya…
Learning a Fast Mixing Exogenous Block MDP using a Single Trajectoryby Alexander Levine, Peter Stone,…
Formation of Representations in Neural Networksby Liu Ziyin, Isaac Chuang, Tomer Galanti, Tomaso PoggioFirst submitted…
On Logical Extrapolation for Mazes with Recurrent and Implicit Networksby Brandon Knutson, Amandin Chyba Rabeendran,…
Characterizing Context Influence and Hallucination in Summarizationby James Flemings, Wanrong Zhang, Bo Jiang, Zafar Takhirov,…
MLP-KAN: Unifying Deep Representation and Function Learningby Yunhong He, Yifeng Xie, Zhengqing Yuan, Lichao SunFirst…
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecastingby Marcel Kollovieh, Marten Lienen,…