Researcher Profile
Editor reviewedHybrid Transformer–Mamba language models (Jamba)
Researcher at Bar-Ilan University whose work spans language grounding and the Jamba model line
A useful page because his public trail is broader than the generic Jamba author stub: it runs from earlier language grounding and text-similarity work into Jamba-1.5 and later multimodal hallucination mitigation.
Organizations
Labs
About This Page
This profile is meant to help you get oriented quickly: why this researcher matters, what to read first, and where to explore next.
Last reviewed
March 18, 2026
Official And External Links
The ideas, systems, and research directions that make this person worth knowing.
01
Jamba-1.5
02
Language grounding and text similarity
03
Mitigating hallucinations in vision-language models
04
Hybrid Transformer–Mamba language models (Jamba)
05
Jamba: A Hybrid Transformer-Mamba Language Model
06
Jamba-1.5: Hybrid Transformer-Mamba Models at Scale
Canonical papers, project pages, or repositories that anchor this profile.
Additional papers, projects, or repositories that help flesh out the profile.
Additional links that help verify and flesh out this profile.
People worth exploring next because they share topics, labs, or source material with this profile.
A valuable page in this cluster because his public role description is unusually specific: post-training, steerability, and AI-generated evaluation data are exactly the kinds of practical problems strong researcher pages should make discoverable.
A useful systems-facing page because it ties one of the less-public engineers on the Jamba line to the practical work of turning hybrid-model research into shipped model releases.
One of the higher-signal people to know in the hybrid-LLM line because he sits at the point where AI21’s research architecture, long-context systems work, and real product deployment meet.
Worth tracking on the architecture side of AI21 because his profile sits where infrastructure leadership, hybrid-model design, and the mechanics of shipping long-context systems overlap.
A better page than the default Jamba stub because it gives one of the quieter AI21 researchers a real place in the company’s hybrid-model program instead of treating him as just another author in a long list.
One of the more useful long-tail AI21 pages because it points to the algorithm leadership behind the company’s hybrid-model releases instead of flattening everyone into the same generic coauthor template.