4 sources
A strong researcher to study if you care about the semantic side of modern language systems, especially where evaluation, structured meaning representation, and tool-using LLM architectures meet.
Start HereProf. Omri Abend
Researcher Profile
Editor reviewedGal Shachaf
Hybrid Transformer–Mamba language models (Jamba)
Researcher working on retrieval, modular reasoning, and hybrid language-model systems
Worth knowing because his work links earlier dense-retrieval research to later MRKL and Jamba systems, which makes his page a good bridge between classic NLP retrieval and newer hybrid LLM stacks.
Organizations
AI21 Labs
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.
Known For
The ideas, systems, and research directions that make this person worth knowing.
01
Dense retrieval without supervision
02
MRKL-style modular language systems
03
Hybrid language models at AI21
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
Start Here
Canonical papers, project pages, or repositories that anchor this profile.
AI21 LabsprofileLearning to Retrieve Passages without SupervisionpaperMRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningpaperJamba: A Hybrid Transformer-Mamba Language ModelpaperJamba-1.5: Hybrid Transformer-Mamba Models at Scalepaper
Related Researchers
People worth exploring next because they share topics, labs, or source material with this profile.
4 sources
A distinctive page in this AI21 cluster because she brings a linguistics and human-evaluation angle to model work, especially around user interaction, multilingual language behavior, and how LLM performance gets tested in practice.
Start HereAI21 Labs
4 sources
A useful profile for the data-and-evaluation side of AI work because it points to the people shaping language data quality, annotation, and analysis inside a frontier-model organization.
Start HereMaria Rozman
4 sources
A useful long-tail AI21 page because it ties one of the less-public contributors to the company’s modular reasoning and hybrid-model line instead of leaving the profile as a generic Jamba coauthor page.
Start HereNoam Rozen
3 sources
Useful for understanding the AI21 line of work that tries to combine tool use, modular reasoning, and hybrid sequence architectures instead of treating LLMs as pure next-token engines.
4 sources
A worthwhile long-tail researcher page because it makes the data-and-evaluation layer of modern language-model work visible instead of treating frontier systems as if they were only architecture or scaling stories.
Start HereTal Ness