2 papers
cs.LG2026
Generative Criticality in Large Language Model Temperature Scaling
Huajian Ruan, Jinyang Li, Xingyu Guo +1
We propose a statistical-field framework for text generated by large language models (LLMs), treating token embeddings as continuous spin variables on a one-dimensional chain. Defi…
hep-lat2025
Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
Gert Aarts, Kenji Fukushima, Tetsuo Hatsuda +4
The integration of deep learning techniques and physics-driven designs is reforming the way we address inverse problems, in which accurate physical properties are extracted from co…