Generative artificial intelligence (AI) has rapidly become embedded in academic writing, assisting with tasks ranging from language editing to drafting text and producing evidence. Despite

arXiv:2604.27495v1 Announce Type: cross Abstract: Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often

arXiv:2604.27743v1 Announce Type: cross Abstract: We develop a geometric and information-theoretic framework for encoder-decoder learning built on the Information Bottleneck (IB) principle. Recasting IB as

arXiv:2508.21787v2 Announce Type: replace-cross Abstract: Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions

arXiv:2602.07915v2 Announce Type: replace-cross Abstract: Causal discovery from time series is a fundamental task in machine learning. However, its widespread adoption is hindered by a