Efficient Preference-based Reinforcement Learning via Aligned Experience Estimationby Fengshuo Bai, Rui Zhao, Hongming Zhang, Sijia…
Proper Dataset Valuation by Pointwise Mutual Informationby Shuran Zheng, Xuan Qi, Rui Ray Chen, Yongchan…
Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representationby Yeachan Park, Minseok Kim, Yeoneung…
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Modelsby Yongxian Wei, Zixuan Hu, Li Shen,…
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependencyby Runqi Lin, Chaojian Yu, Bo…
Feature Protection For Out-of-distribution Generalizationby Lu Tan, Huei Zhou, Yinxiang Huang, Zeming Zheng, Yujiu YangFirst…
In-context Time Series Predictorby Jiecheng Lu, Yan Sun, Shihao YangFirst submitted to arxiv on: 23…
Unraveling overoptimism and publication bias in ML-driven scienceby Pouria Saidi, Gautam Dasarathy, Visar BerishaFirst submitted…
Adaptive Data Analysis for Growing Databy Neil G. Marchant, Benjamin I. P. RubinsteinFirst submitted to…
Progress Measures for Grokking on Real-world Tasksby Satvik GolechhaFirst submitted to arxiv on: 21 May…