Ammar Alsiyabi

Small Models, Long Memory: learned forgetting for efficient long-context recall

Compact networks trained to forget the right things recall as well as models ten times their size.

23 Sep 2026Research

Hands-on Introduction to Arabic NLP

15 Sep 2026Workshops & Talks

Why I stopped chasing benchmarks

Leaderboards reward the wrong kind of progress.

4 Sep 2026Writings

Maktaba: searching 40,000 Arabic manuscripts in seconds

2025Projects

Writings

Why I stopped chasing benchmarks

Leaderboards reward the wrong kind of progress. Here is what I measure instead.

4 Sep 2026

Research

Small Models, Long Memory

Learned forgetting for efficient long-context recall.

2026Preprint

Workshops & Talks

Hands-on Introduction to Arabic NLP

A practical, half-day workshop on building tools for Arabic text.

15 Sep 2026Online

Projects

Maktaba

Full-text search over scanned Arabic manuscripts.

2025Python, Rust