Quality follows upgrading
Academic
arXiv:2603.15645v1 Announce Type: new Abstract: Time series forecasters are widely used across various domains. Among them, MLP (multi-layer perceptron)-based forecasters have been proven to be …
arXiv:2603.15646v1 Announce Type: new Abstract: Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable …
arXiv:2603.15647v1 Announce Type: new Abstract: Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy …
arXiv:2603.15650v1 Announce Type: new Abstract: Out-of-Distribution (OOD) detection is crucial for the secure deployment of machine learning models, and prototype-based learning methods are among the …
arXiv:2603.15651v1 Announce Type: new Abstract: The early prediction of sepsis in intensive care unit (ICU) patients is crucial for improving survival rates. However, the development …
arXiv:2603.15654v1 Announce Type: new Abstract: In classification tasks, the long-tailed minority classes usually offer the predictions that are most important. Yet these classes consistently exhibit …
arXiv:2603.15655v1 Announce Type: new Abstract: In decentralized Multi-Agent Reinforcement Learning (MARL), steganographic collusion -- where agents develop private protocols to evade monitoring -- presents a …
arXiv:2603.15656v1 Announce Type: new Abstract: The performance of neural network models deteriorates due to their unreliable behavior on non-robust features of corrupted samples. Owing to …
arXiv:2603.15678v1 Announce Type: new Abstract: Despite hundreds of millions of parameters, transformer training trajectories evolve within only a few coherent directions. We introduce \emph{Spectral Edge …
arXiv:2603.15681v1 Announce Type: new Abstract: Flash floods are the most destructive natural hazard in Himachal Pradesh (HP), India, causing over 400 fatalities and $1.2 billion …
arXiv:2603.15687v1 Announce Type: new Abstract: Accurate Remaining Useful Life (RUL) prediction without labeled target domain data is a critical challenge, and domain adaptation (DA) has …
arXiv:2603.15689v1 Announce Type: new Abstract: Mainstream flow matching methods typically focus on learning the local velocity field, which inherently requires multiple integration steps during generation. …