Marco Ciccone PRO

mciccone

·

https://marcociccone.github.io/

AI & ML interests

Decentralized, Modular, and Continual Learning

Recent Activity

upvoted a paper 9 days ago

Initialization Improves LLM-Driven Discovery

submitted a paper 9 days ago

Initialization Improves LLM-Driven Discovery

upvoted a paper 10 days ago

One Model to Loop Them All: Elastic Latent Recurrence for Language Models

View all activity

Organizations

upvoted a paper 9 days ago

Initialization Improves LLM-Driven Discovery

Paper • 2610.00707 • Published 23 days ago • 7

upvoted a paper 10 days ago

One Model to Loop Them All: Elastic Latent Recurrence for Language Models

Paper • 2610.12582 • Published 15 days ago • 19

upvoted a paper 10 months ago

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

Paper • 2512.20757 • Published Dec 23, 2025 • 18

upvoted a collection over 1 year ago

Gemstone Models

Our 22 open source Gemstone models for scaling laws range from 50M to 2B parameters, spanning 11 widths from 256 to 3072 and 18 depths from 3 to 80. • 66 items • Updated 17 days ago • 11

upvoted an article over 1 year ago

Article

The Common Pile v0.1

stellaathena

•

Jun 6, 2025

• 55