Julien Launay

About Julien Launay

Julien Launay, With an exceptional h-index of 10 and a recent h-index of 10 (since 2020), a distinguished researcher at École Normale Supérieure, specializes in the field of Large Language Models, Systems, Scaling.

His recent articles reflect a diverse array of research interests and contributions to the field:

The Falcon Series of Open Language Models

The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only

Artificial Neural Network Training on an Optical Processor via Direct Feedback Alignment

AlGhafa Evaluation Benchmark for Arabic Language Models

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

What Language Model to Train if You Have One Million GPU Hours?

Scaling Laws Beyond Backpropagation

What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?

Julien Launay Information

University

Position

Ph.D. Student at / ML Research Scientist at LightOn

Citations(all)

1436

Citations(since 2020)

1436

Cited By

14

hIndex(all)

10

hIndex(since 2020)

10

i10Index(all)

10

i10Index(since 2020)

10

Email

University Profile Page

Google Scholar

Julien Launay Skills & Research Interests

Large Language Models

Systems

Scaling

Top articles of Julien Launay

The Falcon Series of Open Language Models

arXiv preprint arXiv:2311.16867

2023/11/28

Julien Launay
Julien Launay

H-Index: 2

The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only

2023/11/2

Julien Launay
Julien Launay

H-Index: 2

Artificial Neural Network Training on an Optical Processor via Direct Feedback Alignment

2023/6/26

AlGhafa Evaluation Benchmark for Arabic Language Models

2023/12

Julien Launay
Julien Launay

H-Index: 2

What Language Model to Train if You Have One Million GPU Hours?

2022/3/9

Scaling Laws Beyond Backpropagation

arXiv preprint arXiv:2210.14593

2022/10/26

Julien Launay
Julien Launay

H-Index: 2

What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?

2022/4/12

Julien Launay
Julien Launay

H-Index: 2

Colin Raffel
Colin Raffel

H-Index: 29

Method and system for distributed training using synthetic gradients

2022/6/16

Adversarial robustness by design through analog computing and synthetic gradients

2022/5/23

A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model

2022/5

Julien Launay
Julien Launay

H-Index: 2

Is the Number of Trainable Parameters All That Actually Matters?

2022/2/11

Julien Launay
Julien Launay

H-Index: 2

Photonic differential privacy with direct feedback alignment

2021/6/7

Ruben Ohana
Ruben Ohana

H-Index: 1

Julien Launay
Julien Launay

H-Index: 2

PAGnol: An Extra-Large French Generative Model

arXiv preprint arXiv:2110.08554

2021/10/16

Julien Launay
Julien Launay

H-Index: 2

Method and system for machine learning using optical data

2023/2/7

LightOn Optical Processing Unit: Scaling-up AI and HPC with a Non von Neumann co-processor

arXiv preprint arXiv:2107.11814

2021/7/25

ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients

arXiv preprint arXiv:2108.04217

2021/7/6

Julien Launay
Julien Launay

H-Index: 2

Ruben Ohana
Ruben Ohana

H-Index: 1

Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment

arXiv preprint arXiv:2012.06373

2020/12/11

Light-in-the-loop: using a photonics co-processor for scalable training of neural networks

arXiv preprint arXiv:2006.01475

2020/6/2

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

Advances in neural information processing systems

2020

Julien Launay
Julien Launay

H-Index: 2

Florent Krzakala
Florent Krzakala

H-Index: 40

See List of Professors in Julien Launay University(École Normale Supérieure)