arXiv:2604.04655v1 Announce Type: cross
Abstract: Neural network grokking — the abrupt memorization-to-generalization transition — challenges our understanding of learning dynamics. Through finite-size scaling of gradient avalanche dynamics across e…
arXiv:2604.02393v1 Announce Type: new
Abstract: Vanishing gradient and overfitting are two of the most extensively studied problems in the literature about machine learning. However, they are frequently considered in some asymptotic setting, which obs…
arXiv:2603.23626v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly deployed as optimization modules in agentic systems, yet the fundamental limits of such LLM-mediated improvement remain poorly understood. Here we propose a …
arXiv:2603.23539v1 Announce Type: cross
Abstract: We show that PLDR-LLMs pretrained at self-organized criticality exhibit reasoning at inference time. The characteristics of PLDR-LLM deductive outputs at criticality is similar to second-order phase tr…