Program-as-Weights compiles task descriptions into reusable local CPU functions

yuntiandeng · x · 2026-09-21

Following a discussion on cross-task generalization, the author details Program-as-Weights: a larger model is trained to turn English function descriptions directly into LoRA adapters for a shared 0.6B model.

At deployment you describe a new task, compile it once, and reuse the resulting function locally on CPU—the standard compiler emits the adapter without per-task finetuning. Code, weights, and the paper are all public.

Original post →

More from Research

Research channel →