Skander Moalla's picture

4 1

Skander Moalla

skandermoalla

·

https://skandermoalla.com/

AI & ML interests

DeepRL, RL finetuning

Recent Activity

upvoted a paper 22 days ago

Efficient RL Training for LLMs with Experience Replay

authored a paper 4 months ago

Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers

authored a paper 4 months ago

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

View all activity

Organizations

upvoted a paper 22 days ago

Efficient RL Training for LLMs with Experience Replay

Paper • 2604.08706 • Published 28 days ago • 21

upvoted a paper 5 months ago

Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis

Paper • 2407.09835 • Published Jul 13, 2024 • 1

upvoted a collection over 1 year ago

Tulu V1 Suite

The set of models associated with the paper "How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources". • 34 items • Updated Mar 4, 2025 • 3