4 papers
Prompt-Induced Waste in Coding Agents: Reasoning, Effort, Harness Design, and End-to-End Cost
Sarel Weinberger, Amir Hozez
Coding-agent efficiency cannot be characterized by token count or model price alone. End-to-end cost and task success depend jointly on prompt semantics, inference effort, harness…
Token Reduction Is Not Cost Reduction
Sarel Weinberger, Amir Hozez
Token-reduction tools for coding agents are often evaluated by the number of tokens they remove, but token count alone does not determine end-to-end inference cost. We evaluate thr…
Mixture of Experts for Low-Resource LLMs
Ori Bar Joseph, Smadar Arvatz, Noam Kayzer +2
Mixture-of-Experts (MoE) architectures enable efficient model scaling, yet expert routing behavior across underrepresented languages remains poorly understood. We analyze routing d…
HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model
Noam Kayzer, Dan Revital, Ori Bar Joseph +10
We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Training employs a three-phase eas…