Author

Mehdi Makni

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

ThinQuant: Scalable Rotation Learning for Weight and Activation Quantization of LLMs

Learned rotations play an important role in enabling low-bit weight and activation quantization of large language models by smoothing outliers in the activation distribution. State-of-the-art approaches include gradient-based procedures such as SpinQuant and computationally friendlier gradient-free approaches such as D...

Mehdi Makni, Ryan Lucas, Rahul Mazumder · 0 citations

#machine learning May 2026

ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models

This work proposes ADMM-Q, a novel weight quantization algorithm that considers the layer-wise quantization problem, based on a combinatorial variant of the Alternating Direction Method of Multipliers (ADMM).

Ryan Lucas, Mehdi Makni, Xiang Meng et al. · arXiv.org · 1 citation