activity
20192026
most citedCAT: Compression-Aware Training for bandwidth reduction

10 citations · 10 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Normalized Architectures are Natively 4-Bit

Maxim Fishman, Brian Chmiel, Ron Banner +2

Training large language models at 4-bit precision is critical for efficiency. We show that nGPT, an architecture that constrains weights and hidden representations to the unit hype…

cs.LG20251 cited

FP4 All the Way: Fully Quantized Training of LLMs

Brian Chmiel, Maxim Fishman, Ron Banner +1

We demonstrate, for the first time, fully quantized training (FQT) of large language models (LLMs) using predominantly 4-bit floating-point (FP4) precision for weights, activations…

cs.LG2024

EXAQ: Exponent Aware Quantization For LLMs Acceleration

Moran Shkolnik, Maxim Fishman, Brian Chmiel +3

Quantization has established itself as the primary approach for decreasing the computational and storage expenses associated with Large Language Models (LLMs) inference. The majori…

cs.LG20241 cited

Scaling FP8 training to trillion-token LLMs

Maxim Fishman, Brian Chmiel, Ron Banner +1

We train, for the first time, large language models using FP8 precision on datasets up to 2 trillion tokens -- a 20-fold increase over previous limits. Through these extended train…

cs.LG2022

Bimodal Distributed Binarized Neural Networks

Tal Rozen, Moshe Kimhi, Brian Chmiel +2

Binary Neural Networks (BNNs) are an extremely promising method to reduce deep neural networks' complexity and power consumption massively. Binarization techniques, however, suffer…

cs.LG2020

Colored Noise Injection for Training Adversarially Robust Neural Networks

Evgenii Zheltonozhskii, Chaim Baskin, Yaniv Nemcovsky +3

Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that le…