AIConfPaper
← Search

Kaveh Alim

2 accepted papers

2025

Activation-Informed Merging of Large Language Models

Amin Heyrani Nobari, Kaveh Alim, Ali ArjomandBigdeli, Akash Srivastava, Faez Ahmed, Navid Azizan
NeurIPS 2025poster

Model merging, a method that combines the parameters and embeddings of multiple fine-tuned large language models (LLMs), offers a promising approach to enhance model performance across various tasks while maintaining computational efficiency. This paper introduces Activation-Informed Merging (AIM),…

Cited by 0Source ↗code ↗Scholar ↗
2025

Know What You Don't Know: Uncertainty Calibration of Process Reward Models

Young-Jin Park, Kristjan Greenewald, Kaveh Alim, Hao Wang, Navid Azizan
NeurIPS 2025poster

Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibrated. Specifically, they tend to overestimate the success probability that a partial reasoning step…

Cited by 0Source ↗Scholar ↗