Skander Moalla's picture

3 1

Skander Moalla

skandermoalla

·

https://skandermoalla.com/

AI & ML interests

DeepRL, RL finetuning

Recent Activity

authored a paper about 7 hours ago

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

authored a paper about 7 hours ago

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

authored a paper about 7 hours ago

Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions

View all activity

Organizations

authored 3 papers about 7 hours ago

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

Paper • 2406.16450 • Published Jun 24, 2024

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17 • 14

Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions

Paper • 2507.08068 • Published Jul 10

updated a collection about 10 hours ago

QRPO Reference Datasets

Datasets with reference completions and rewards used in the paper https://arxiv.org/abs/2507.08068. • 29 items • Updated about 10 hours ago

updated a collection 21 days ago

QRPO Reference Datasets

Datasets with reference completions and rewards used in the paper https://arxiv.org/abs/2507.08068. • 29 items • Updated about 10 hours ago