2 papers
cs.CL2026
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
physics.gen-ph2025
On the Relativistic Origin of spin: A Case for the "Rest Angular Momentum"
H. Razmi, A. MohammadKazemi
The intrinsic angular momentum, or spin, is a cornerstone of modern physics with profound applications from nuclear magnetic resonance to spintronics. While its mathematical struct…